KR102449377B1 - Platforms for implementing signal detection metrics in adaptive response deadline procedures - Google Patents

Abstract

cognitive platforms for applying signal detection metrics in computer implemented adaptive response deadline procedures to data collected based at least in part on user interaction(s) with computerized tasks and/or interferences; Example systems, methods, and apparatus are provided. The apparatus may include a response classifier for generating a quantifier of the individual's cognitive ability. The apparatus may also be configured to coordinate tasks and/or interventions to enhance the individual's cognitive ability.

Description

Platforms for implementing signal detection metrics in adaptive response deadline procedures

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to U.S. Provisional Application No. 62/364,297, entitled "SIGNAL DETECTION METRICS IN ADAPTIVE RESPONSE-DEADLINE PROCEDURES", filed on July 19, 2016, and filed on September 30, 2016 is a continuation-in-part of U.S. Design Application No. 29/579,480 entitled "GRAPHICAL USER INTERFACE FOR A DISPLAY SCREEN OR PORTION THEREOF," each of which includes drawings, It is incorporated herein by reference in its entirety.

During the normal aging process, people may experience a certain amount of cognitive decline. This may cause the individual to experience increased difficulty in difficult situations, such as time-limited and attention-demanding conditions. In both older people and younger people, certain cognitive conditions, diseases, or executive function disorders include attention, memory, motor function, reaction, executive function, decision-making ability ( may result in compromised performance in tasks requiring decision-making skills, problem-solving skills, language processing, or comprehension.
As a prior art document, there is Japanese Patent Publication No. 2014-508309 (published on April 3, 2014).

In view of the foregoing, apparatuses, systems and methods are provided for quantifying aspects of cognition (including cognitive abilities). In certain configurations, the devices, systems and methods may be implemented to enhance certain cognitive abilities.

Exemplary apparatuses, systems, and methods provide signal detection metrics in computer-implemented adaptive response-deadline procedures for user interaction with computerized tasks and/or interferences. ) is configured to apply to the collected data based at least in part on For example, the apparatus may include a response classifier for generating a quantifier of an individual's cognitive ability. As another example, the apparatus may also be configured to coordinate tasks and/or interventions to enhance the individual's cognitive abilities.

In a general aspect, an apparatus is provided for generating a quantifier of an individual's cognitive skills using a response classifier. The device includes a user interface; a memory for storing processor-executable instructions; and a processing unit communicatively coupled to the user interface and the memory, wherein upon execution of the processor-executable instructions by the processing unit, the processing unit is configured to render the task with interference to the user interface, the user interface one or more of the tasks and interferences are time-varying and have a response deadline, such that . The user interface is configured to measure data indicative of two or more different types of responses to a task or to an interference. the processing unit receives data representing a first response of the individual to the task and a second response of the individual to the interference; analyze the data representative of the first response and the second response to calculate at least one response profile representative of the individual's performance; determine a decision boundary metric from the response profile, wherein the decision boundary metric is a quantitative measure of an individual's propensity to provide at least one type of response of two or more different types of responses to a task or interference. ) including -; and execute the response classifier based at least in part on the calculated values of the decision boundary metric to generate a classifier output indicative of cognitive response capabilities of the individual.

In another general aspect, a computer implemented method for generating a quantifier of an individual's cognitive ability using a response classifier is provided. The method includes rendering a task with an interference in a user interface; measuring data indicative of two or more different types of responses to a task or to an interference; and receiving data representative of a first response of the individual to the task and a second response of the individual to the interference. The method includes analyzing data representative of the first response and the second response to calculate at least one response profile representative of the individual's performance. The method includes determining a decision boundary metric from a response profile, the decision boundary metric comprising a quantitative measure of an individual's propensity to provide a response of at least one of two or more different types of responses to interference. include The method includes executing a response classifier based at least in part on the decision boundary metric to generate a classifier output indicative of a cognitive response ability of the individual.

In another general aspect, an apparatus for improving cognitive abilities of an individual is provided. The device includes a user interface; a memory for storing processor-executable instructions; and a processing unit communicatively coupled to the user interface and the memory, wherein upon execution of processor-executable instructions by the processing unit, the processing unit renders a primary task to the user interface with interfering wherein the one or more of the tasks and interventions are time-varying and have a response deadline, such that the user interface imposes a limited time period for receiving at least one type of response from the individual; The user interface is configured to measure data indicative of two or more different types of responses to a task or to an interference. the processing unit receives data representing a first response of the individual to the task and a second response of the individual to the interference; and analyze the data representative of the first response and the second response to calculate at least one response profile representative of performance of the individual. The processing unit is configured to determine a first decision boundary metric based at least in part on the at least one response profile, wherein the first decision boundary metric is an individual providing at least one type of response of two or more different types of responses to interference. It contains a quantitative measure of the tendency of - to be constructed. The processing unit is configured to determine, based at least in part on the calculated first decision boundary metric, that the further response to the task and/or the further response to the interference is an earlier response to the task and/or a previous response to the interference. and adjust the task and/or interference to derive a modification in the calculated at least one decision boundary metric so as to be modified relative to the response, thereby indicating a modification of the individual's cognitive response ability.

In another general aspect, a computer-implemented method for improving cognitive ability in an individual is provided. The method includes rendering a task with an interference in a user interface; measuring data indicative of two or more different types of responses to a task or to an interference; receiving data representative of a first response of the individual to the task and a second response of the individual to the interference; and analyzing the data representative of the first response and the second response to calculate at least one response profile representative of the individual's performance. The method includes determining a first decision boundary metric based at least in part on the at least one response profile, the first decision boundary metric providing at least one type of response of two or more different types of responses to interference. includes a quantitative measure of an individual's tendency to The method includes, based at least in part on the calculated first decision boundary metric, the first response and/or the second response are modified, thereby indicating a modification of the individual's cognitive response ability, the calculated first decision boundary metric adjusting the task and/or interference to derive a modification in .

In another general aspect, an apparatus for improving cognitive abilities of an individual is provided. The device includes a user interface; a memory for storing processor-executable instructions; and a processing unit communicatively coupled to the user interface and the memory, wherein upon execution of the processor-executable instructions by the processing unit, the processing unit comprises: a pharmaceutical agent being or will be administered to the individual; drug), or an amount, concentration, or dose titration of a biologic. the processing unit is configured to render the primary task with the interference to the user interface, wherein at least one of the task and the interference is time-varying and such that the user interface imposes a limited time period for receiving at least one type of response from the individual. have a response deadline; The user interface is configured to measure data indicative of two or more different types of responses to a task or to an interference. the processing unit receives, from the first session, data representing a first response of the individual to the task and a second response of the individual to the interference; analyze the data representing the first response and the second response to calculate a first response profile representing the first performance of the individual; determine a first decision boundary metric based at least in part on the at least one response profile, wherein the first decision boundary metric is a measure of an individual's tendency to provide at least one type of response of two or more different types of responses to interference. Includes quantitative measures - constructed. The processing unit is configured to adjust the task and/or intervention to generate the second session based at least in part on the calculated first decision boundary metric and the amount or concentration of the drug, drug, or biological agent. The processing unit is configured to analyze the collected data representative of the first response and the second response from the second session to calculate a second response profile and a second decision boundary metric representative of a second performance of the individual. The processing unit determines, based at least in part on the first decision boundary metric and the second decision boundary metric, (i) a likelihood that the individual will experience an adverse event in response to administration of the medicament, drug, or biological agent, (ii) ) a recommended change in one or more of the amount, concentration, or dose titration of an agent, drug, or biological agent, (iii) a change in an individual's cognitive response ability, (iv) a recommended treatment regimen, (v) behavior A user interface indicating at least one of a recommendation of at least one of behavioral therapy, counseling, or physical exercise, or (vi) a degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. is configured to produce an output to

In another general aspect, a computer-implemented method for improving cognitive ability in an individual is provided. The method includes receiving data indicative of one or more of an amount, concentration, or dose titration of an agent, drug, or biological agent that is being or will be administered to an individual. The method includes rendering a task with an interference in a user interface; measuring data indicative of two or more different types of responses to a task or to an interference; receiving data representative of a first response of the individual to the task and a second response of the individual to the interference; and analyzing the data representative of the first response and the second response to calculate a first response profile representative of the individual's performance. The method includes determining a first decision boundary metric based at least in part on the at least one response profile, the first decision boundary metric providing at least one type of response of two or more different types of responses to interference. Includes a quantitative measure of an individual's tendency. The method includes adjusting the task and/or intervention such that the at least one response profile is modified based at least in part on the calculated first decision boundary metric and the amount or concentration of the drug, drug, or biological agent. . The method includes analyzing the collected data representative of the first response and the second response to calculate a second decision boundary metric representative of a second performance of the individual. The method comprises, based at least in part on the first decision boundary metric and the second decision boundary metric, (i) a change in one or more of an amount, concentration, or dose titration of an agent, drug, or biological agent, (ii) the individual At least one of the following: the likelihood of experiencing an adverse event in response to administration of the drug, drug, or biologic, (iii) a change in an individual's cognitive response ability, (iv) a recommended treatment regimen, (v) behavioral therapy, counseling, or physical exercise. or (vi) generating an output to a user interface indicating at least one of a degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise.

The details of one or more of the above aspects and implementations are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, drawings, and claims.

Those skilled in the art will understand that the drawings described herein are for illustrative purposes only. It should be understood that in some instances, various aspects of the described implementations may be shown exaggerated or enlarged to facilitate understanding of the described implementations. In the drawings, like reference characters generally refer to like features, functionally similar, and/or structurally similar elements throughout the various figures. The drawings are not necessarily to scale, emphasis is instead placed upon illustrating the principles of the teachings. The drawings are in no way intended to limit the scope of the present teachings. A system and method may be better understood from the following illustrative description with reference to the following figures:
1 shows a block diagram of an exemplary system, in accordance with the principles herein.
2 shows a block diagram of an example computing device, in accordance with the principles herein.
3 shows an exemplary plot of signal and noise distribution curves calculated based on an exemplary cognitive test, in accordance with the principles herein.
4A shows an exemplary graphical depiction of a drift-diffusion model for linear belief accumulation, in accordance with the principles herein;
4B shows an exemplary graphical depiction of a drift-diffusion model for non-linear belief accumulation, in accordance with the principles herein.
5 shows an exemplary plot of signal (right curve) and noise based on an exemplary cognitive platform, in accordance with the principles herein.
6 shows an exemplary plot of the conditional probability of a quantifier of belief given a signal, in accordance with the principles herein.
7A and 7B show plots of curves for values of conservative and impulsive measures, in accordance with the principles herein.
7C and 7D show exemplary plots of the formation of confidence for linear and non-linear confidence accumulations, respectively, in accordance with the principles herein;
8A-8D show exemplary plots of probability curves for signal distribution and noise distribution at the time points shown in FIGS. 7A-7D , in accordance with the principles herein;
9 shows an example of an exemplary projected two-dimensional (2D) representation of a three-dimensional (3D) joint distribution, in accordance with the principles herein.
10A-10D illustrate example user interfaces with instructions for a user that may be rendered in the example user interface, in accordance with the principles herein.
11A-11D are examples of time-varying features of example objects (targets or non-targets) that may be rendered in an example user interface, in accordance with principles herein; are shown
12A-12T illustrate the dynamics of tasks and interferences that may be rendered in user interfaces, in accordance with the principles herein.
13A-13D illustrate multi-tasking involving user interaction with and interfering with implementation of a navigation task rendered to a user interface of an exemplary user interface, in accordance with principles herein; Examples of dynamics of -tasking) are shown.
14A-14D illustrate examples of dynamics of an instructions panel rendered to a user interface of an exemplary user interface, in accordance with principles herein;
15A-15V illustrate examples of the dynamics of multi-tasking involving user interaction with the implementation of a navigation task and with interference.
16A-16C show flowcharts of example methods, in accordance with the principles herein.
17 illustrates an architecture of an exemplary computer system, in accordance with the principles herein.

It should be appreciated that all combinations of concepts discussed in greater detail below (provided that such concepts are not mutually inconsistent) may be considered as being part of the inventive subject matter disclosed herein. It should also be appreciated that terms explicitly employed herein, which may also appear in any disclosure incorporated by reference, are to be accorded the meaning most consistent with the specific concepts disclosed herein.

In the following there is a more detailed description of various concepts and embodiments thereof relating to inventive methods, apparatuses and systems comprising a cognitive platform configured to apply signal detection metrics in computer implemented adaptive response deadline procedures.

It should be appreciated that the various concepts introduced above and discussed in greater detail below may be implemented in any of a variety of ways, as the disclosed concepts are not limited to any particular implementation manner. Examples of specific implementations and applications are provided primarily for illustrative purposes.

As used herein, the term “includes” means includes but is not limited to, and the term “including” includes but is not limited to means including but not limited to. The term “based on” means based at least in part on.

As used herein, the term “target” refers to a type of stimulus that is specific to an individual (eg, in instructions) that is the focus for the interaction. A target differs from a non-target in at least one characteristic or characteristic. The two targets may differ from each other by at least one characteristic or characteristic, but if the individual (such as, but not limited to, between a happy face and a happier face or between an angry face and an angry face In one example where the dog is instructed/required to make a choice (between different degrees of facial expression or other characteristic/feature differences), the individual as a whole is still directed as a target.

As used herein, the term “non-target” refers to a type of stimulus that is not a focal point for interaction, whether explicitly or implicitly directed to an individual.

As used herein, the term “task” refers to a goal and/or objective to be achieved by an individual. A task may require the individual to provide or withhold a response to a particular stimulus. A “task” may consist of a baseline cognitive function being measured.

As used herein, the term “interference” refers to a stimulus presented to an individual to interfere with the individual's performance of a primary task. In any of the examples herein, interference is a type of task presented/rendered in a manner that diverts or interferes with an individual's attention when performing another task. In some examples herein, the interference is over a short, discrete time period or over an extended time period (smaller than the time frame in which the primary task is presented), or Over the entire time period of the primary task, it is configured as a secondary task presented concurrently with the primary task. In any of the examples herein, the interference may be presented/rendered continuously, or continuously (ie, repeated at a certain frequency, irregularly, or somewhat randomly). For example, the interference may be presented at the end of the primary task or at discrete, interim periods during presentation of the primary task. The degree of interference may be modulated based on the type, amount, and/or time length of presentation of the interference to the primary task.

As used herein, the term “stimulus” refers to a sensory event configured to evoke a specified functional response from an individual. The degree and type of response can be quantified based on an individual's interactions using a measurement component (including using a sensor device or other measurement components). Non-limiting examples of stimuli include a navigation path (in which an individual is instructed to control an avatar or other processor-rendered guide to navigate a route), or a user interface. Discrete objects (individuals are instructed to control computing components to provide input or other indications for discrete objects), whether targeted or non-target, rendered to In any example herein, a task and/or interference includes a stimulus.

As used herein, “trial” includes at least one iteration of the rendering of a task and/or interference, and at least one reception of an individual's response(s) to the task and/or interference. . As non-limiting examples, the execution may include at least a portion of a single-tasking task and/or at least a portion of a multi-tasking task. For example, enforcement may indicate that an individual's actions in interacting with a platform guide (including a computerized avatar) along at least a portion of a particular path or within an environment (in fractions of a second). , resulting in navigating for a time interval such as, but not limited to, 1 second, a few seconds, or more, and/or causing a guide (including a computerized avatar) to navigate the route A navigation in which an individual's performance is assessed, such as, but not limited to, assessing the degree of success along or within the environment to traverse (or avoid crossing) performance milestones. It may be a period of time during a task (including a visual-motor navigation task). In another example, enforcement may indicate that the individual's actions in interacting with the platform result in identification/selection of target versus non-target (eg, red object versus yellow object), or two different types of target (happy face). vs. happy face) may be a period of time during a targeting task in which an individual's performance is assessed, such as, but not limited to, determining whether or not he or she is successful. In such examples, the segment of the individual's performance designated as the trial for the navigation task need not be co-extensive or aligned with the segment of the individual's performance designated as the trial for the targeting task.

As used herein, “session” refers to at least one trial or may include at least one trial and at least one other type of measurement and/or other user interaction. As a non-limiting example, a session may include at least one trial and one or more of measurements using a physiological or monitoring component and/or a cognitive testing component. As another non-limiting example, a session may include at least one trial and at least one reception of data representative of one or more measures of an individual's condition, including a physiological condition and/or a cognitive state. have.

In any of the examples herein, an object may be rendered as a physical object (including polygons or other objects), a face (human or non-human), or a caricature, a depiction of another type of object.

In any of the examples herein, instructions may be provided to an individual to specify how the individual is expected to perform tasks and/or interventions in an enforcement and/or session. In non-limiting examples, the instructions may include a navigation task (eg, maintaining this route, going to these parts of the environment, traversing or avoiding certain milestone objects in the route or environment), a targeting task (eg, , describing or showing the type of object that is a target object versus a non-target object, or the type of object that is a target object versus a non-target object, or two different types of target objects an individual is expected to select (eg, a happy face). may inform the individual of expected performance of (e.g., explaining or showing a happier face), and/or explain how the individual's performance should be scored. based on the user interface) or through sound. In various examples, the instructions may be provided once prior to performance of two or more trials or sessions, repeated each time prior to performance of trials or sessions, or some combination thereof.

While some example systems, methods, and apparatuses described herein are based on an individual being instructed/required to decide/select between a target versus a non-target, in other example implementations, the example systems, Methods, and apparatuses may be configured such that an individual is instructed/required to decide/select between two different types of targets (such as, but not limited to, two different degrees of facial expressions or other characteristic/feature differences). have.

In addition, while example systems, methods, and apparatuses may be described herein for one individual, in other example implementations, the example systems, methods, and apparatuses are directed to two or more individuals. , or members of a group (including a clinical population), individually or concurrently, may be configured to perform tasks and/or interventions.

This disclosure relates to the application of signal detection metrics such as criteria, biases, and sensitivity indices to computer implemented adaptive time-deadline procedures.

Exemplary systems, methods, and apparatuses in accordance with the principles herein provide for impulsive (limited information) in psychophysical computer implemented adaptive testing procedures, using at least one processing unit of a programmed computing device. It can be implemented to characterize the response profiles of individuals and groups on a spectrum between (trends to respond using

As described in more detail below, a computing device may include an application (“app”) for performing functions such as analyzing data. For example, data from the at least one sensor component may include a computed response profile, a decision boundary metric (such as, but not limited to, response criteria), a response classifier, and other metrics and analyzes described herein. may be analyzed as described herein by a processor executing an app on an exemplary computing device to provide

An example system in accordance with the principles herein provides for generating a quantifier of an individual's cognitive ability (using a machine learning response classifier) and/or enhancing an individual's cognitive ability. In an example implementation, the example system utilizes an app running on a mobile communication device or other handheld devices. Non-limiting examples of such mobile communication devices or handheld devices are smartphones, tablets, slates, electronic-readers, such as, but not limited to, an iPhone®, a BlackBerry®, or Android-based smartphone. (e-reader), digital assistant, or other electronic reader or handheld, portable, or wearable computing device, or any other equivalent device, to be used to render game-like elements Xbox®, Wii®, or other computing system. In some example implementations, the example system can include a head-mounted device, such as smart glasses with built-in displays, smart goggles with built-in displays, or a smart helmet with built-in displays, and a user can use one or more sensors can have a controller or input device having a In some demonstrative implementations, the computing system can be stationary, such as a desktop computing system that includes a main computer and a desktop display (or projector display), where the user can use a keyboard, computer mouse, joystick, handheld console. Provide inputs to the app using devices, wristbands, or other wearable devices with sensors that communicate with the main computer using wired or wireless communication. In examples herein, sensors may be configured to measure movements of a user's hand, foot, and/or any other part of the body. In some example implementations, the example system is a virtual reality (VR) system (simulated environment, including as an immersive, interactive three-dimensional experience for a user), an augmented reality (AR) system (sound, video, graphics and /or a live direct or indirect view of a physical, real-world environment with elements augmented by computer-generated sensory input, such as, but not limited to, GPS data), or mixed reality (MR) ) system (also referred to as hybrid reality, which merges the real and virtual worlds to create new environments and visualizations in which physical and digital objects coexist and interact in substantially real-time).

1 illustrates an example apparatus 100 in accordance with the principles herein that may be used to implement a cognitive platform in accordance with the principles herein. The exemplary apparatus 100 includes at least one memory 102 and at least one processing unit 104 . The at least one processing unit 104 is communicatively coupled to the at least one memory 102 .

Exemplary memory 102 includes, but is not limited to, hardware memory, non-transitory tangible media, magnetic storage disks, optical disks, flash drives, computational device memory, DRAM, SRAM, EDO RAM, and the like. random access memory, any other type of memory, or a combination thereof. Exemplary processing unit 104 may include a microchip, processor, microprocessor, special purpose processor, application specific integrated circuit, microcontroller, field programmable gate array, any other suitable processor, or combinations thereof.

At least one memory 102 is configured to store processor-executable instructions 106 and computing component 108 . In a non-limiting example, computing component 108 may be used to calculate signal detection metrics in computer implemented adaptive response deadline procedures. 1 , memory 102 may also be used to store data 110 , such as, but not limited to, measurement data 112 . In various examples, measurement data 112 may be an individual's physiological measurement data received from a physiological component (not shown) and/or rendered in a user interface of device 100 (as described in more detail below). data indicative of an individual's response to tasks and/or interventions, and/or titration of amounts, concentrations, or doses, or other treatment regimens, of drugs, agents, biologics, or other medications being or will be administered to the individual; It may include data representing one or more of

In a non-limiting example, the at least one processing unit 104 is processor executable stored in the memory 102 to at least calculate signal detection metrics in computer implemented adaptive response deadline procedures using the computing component 108 . Execute the instructions 106 . The at least one processing unit 104 includes processor-executable instructions for controlling the transmitting unit to transmit values indicative of the calculated signal detection metrics and/or for controlling the memory 102 to store values indicative of the signal detection metrics. Also executes 106.

In another non-limiting example, at least one processing unit 104 executes processor-executable instructions 106 stored in memory 102 to at least apply signal detection metrics in computer implemented adaptive response deadline procedures. .

In any example herein, the user interface may be a graphical user interface.

In another non-limiting example, measurement data 112 may be collected from measurements using one or more physiological or monitoring components and/or cognitive testing components. In any example herein, the one or more physiological components are configured to perform physiological measurements. Physiological measurements provide quantitative measurement data of physiological parameters and/or data that can be used for visualization of physiological structure and/or functions.

In any example herein, measurement data 112 includes response time, response variance, correct hits, omission errors, (such as response to non-target, (but not limited to) number of false alarms, learning rate, spatial deviance, subjective assessment, and/or performance threshold, or percent accuracy, hit in a recently completed trial or session data from the analysis, including s, and/or misses. Other non-limiting examples of measurement data 112 include response time, task completion time, number of tasks completed within a set amount of time, preparation time for a task, accuracy of responses, set conditions (eg, stimulus difficulty or magnitude level ( magnitude level) and the association of multiple stimuli), the number of responses a participant can register within a set time limit, the number of responses a participant can make without a time limit, and the number of responses in the task required to complete the task. number of attempts, movement stability, accelerometer and gyroscope data, and/or self-rating.

For a target discrimination task, the cognitive platform selects between a target and a non-target (eg, in a GO/NO-GO task) or, eg, between two different degrees of facial expression or other characteristic/feature difference. In a two-alternative forced choice (2AFC) task, including to select between two different types of targets, temporally-specific and/or position-specific responses can be requested from the individual. For navigation tasks, the cognitive platform may require a location-specific and/or motion-specific response from the user. For a facial expression recognition or object recognition task, the recognition platform may require time-specific and/or location-specific responses from the user. In non-limiting examples, a user response to tasks such as, but not limited to, targeting and/or navigation and/or facial expression recognition or object recognition task(s) may be recorded using an input device of the cognitive platform. can Non-limiting examples of such input devices include a device for capturing a touch, swipe, or other gesture on a user interface, including any form of graphical user interface configured to record user interaction, an audio capture device (such as , microphone input), or an image capture device (such as, but not limited to, a touch screen or other pressure-sensitive or touch-sensitive surface, or camera). In other non-limiting examples, the user response recorded using the cognitive platform to tasks such as, but not limited to, targeting and/or navigation and/or facial expression recognition or object recognition task(s) may include: user actions that cause changes in position, orientation, or movement of the computing device comprising Such changes in the position, orientation, or movement of the computing device may be recorded using an input device disposed on or otherwise coupled to the computing device, such as, but not limited to, a sensor. Non-limiting examples of sensors include a motion sensor, a position sensor, and/or an image capture device (such as, but not limited to, a camera).

In any example herein, multi-tasking tasks may include any combination of two or more tasks. The multi-task interactive elements of one implementation are interactive mechanics configured to engage an individual in multiple temporally overlapping tasks, ie, tasks that may require the individual to multiple substantially simultaneous responses. includes In non-limiting examples herein, in the individual's performance of at least a portion of a multi-tasking task, the system, method, and apparatus are configured to measure in real time data indicative of multiple responses of the individual and also (which is a secondary task). ) measure a first response from the individual to the task (which is the primary task) substantially simultaneously with measuring a second response from the individual to the interference.

In an example implementation involving multi-tasking tasks, the computer device causes the cognitive platform (such as using at least one specially programmed processing unit) to cause target determination and/or navigation and/or facial expression recognition or object recognition. and present two or more different types of tasks, such as, but not limited to, tasks, to the user during a short time frame (including in real time and/or substantially simultaneously). The computer device sends data indicative of the type of user response received for multi-tasking tasks (such as using at least one specially programmed processing unit) in a short time (including in real time and/or substantially simultaneously). Within the frame, it is also configured to collect. In such examples, two or more different types of tasks may be presented to an individual within a short time frame (including in real time and/or substantially simultaneously), and the computing device responds to the two or more different types of tasks. ) within a short time frame (including in real time and/or substantially simultaneously).

In some examples, the short time frame may have any time interval with a resolution of up to about 1.0 millisecond or greater. The time intervals may be, but are not limited to, time durations of any division of periodicity of about 2.0 milliseconds or more, until any reasonable end time. The time intervals are about 3.0 milliseconds, about 5.0 milliseconds, about 10 milliseconds, about 25 milliseconds, about 40 milliseconds, about 50 milliseconds, about 60 milliseconds, about 70 milliseconds, about 100 milliseconds, or the like. or more, but is not limited thereto. In other examples, the short time frame can be, but is not limited to, fractions of a second, about a second, about 1.0 to about 2.0 seconds, or up to about 2.0 seconds, or more.

In any of the examples herein, the cognitive platform may be configured to collect data indicative of a reaction time of a user's response to the presentation time of tasks (including interference with the task). For example, the computing device may cause a platform product or cognitive platform to provide a smaller or larger reaction time window for a user to provide a response to tasks as an example way of adjusting a difficulty level. can be configured to

In any example herein, the one or more physiological components include electrical activity, heart rate, blood flow, and oxygenation levels to provide measurement data 112 , It may include any means of measuring physical properties of the body and nervous system. It uses camera based heart rate detection, measurement of galvanic skin response, blood pressure measurement, electroencephalogram, electrocardiogram, magnetic resonance imaging to provide measurement data 112 . , near-infrared spectroscopy, and/or pupil dilation measurements. The one or more physiological components may include one or more sensors for measuring parameter values of physical properties of the body and nervous system, and one or more signal processors for processing signals detected by the one or more sensors.

Other examples of physiological measurements to provide measurement data 112 include body temperature using an electrocardiogram (ECG), measurement of the heart or other heart related function, electrical activity using an electroencephalogram (EEG), event-related potentials (ERPs) ), functional magnetic resonance imaging (fMRI), blood pressure, potential in a portion of the skin, galvanic skin response (GSR), magneto-encephalogram (MEG), eye tracking including processing units programmed to determine the extent of pupil dilation devices include, but are not limited to, eye-tracking devices or other optical detection devices, functional near-infrared spectroscopy (fNIRS), and/or positron emission tomography (PET) scanners. EEG-fMRI or MEG-fMRI measurement enables simultaneous acquisition of electrophysiology (EEG/MEG) data and hemodynamic (fMRI) data.

The example apparatus of FIG. 1 may be configured as a computing device for performing any of the example methods described herein. The computing device may include an app for performing some of the functions of the example methods described herein.

2 depicts another example apparatus in accordance with the principles herein, configured as a computing device 200 that may be used to implement a cognitive platform in accordance with the principles herein. The example computing device 200 may include a communication module 210 and an analysis engine 212 . The communication module 210 may be implemented to receive data representing the individual's response to the task and/or the individual's response to the interference. The analysis engine 212 is configured to analyze the data to generate a response profile, a decision boundary metric (such as, but not limited to, response criteria), a response classifier, and/or other metrics and analyzes described herein. can be implemented. As shown in the example of FIG. 2 , the computing device 200 includes processor-executable instructions such that the processor unit may execute an application (app) 214 that a user may implement to initialize the analysis engine 212 . can do. In one example, processor-executable instructions may include software, firmware, or other instructions.

The example communication module 210 may be configured to implement any wired and/or wireless communication interface through which information may be exchanged between the computing device 200 and another computing device or computing system. Non-limiting examples of wired communication interfaces include, but are not limited to, USB ports, RS232 connectors, RJ45 connectors, and Ethernet connectors, and any suitable circuitry associated therewith. Non-limiting examples of wireless communication interfaces include Bluetooth® technology, Wi-Fi, Wi-Max, IEEE 802.11 technology, radio frequency (RF) communication, Infrared Data Association (IrDA) compliant protocols, local area networks (LAN), wide area networks (WAN), and interfaces implementing a Shared Radio Access Protocol (SW AP).

In the example implementation, the example computing device 200 includes at least one other component configured to transmit a signal from the apparatus to the second computing device. For example, the at least one component may include a transmitter or transceiver configured to transmit a signal including data indicative of a measurement by the at least one sensor component to the second computing device.

In any example herein, the app 214 on the computing device 200 determines that the processor unit of the computing device has a response profile, a decision boundary metric (such as, but not limited to, response criteria), a response classifier, and processor-executable instructions to implement an analysis engine for analyzing data indicative of an individual's response to the rendered tasks and/or interference to provide other metrics and analyzes described herein. In some examples, the app 214 provides (i) a classifier output indicating the cognitive response ability of the individual, (ii) the likelihood that the individual will experience an adverse event in response to administration of the agent, drug, or biologic, (iii) the agent, drug, or drug. , or a change in one or more of the amount, concentration, or dose titration of a biological agent, and (iv) a change in an individual's cognitive response ability, a recommended treatment regimen, or the degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. may include processor-executable instructions for providing one or more of recommending or determining

In any of the examples herein, the app 214 is an individual's physiological measurement data received from a physiological component, and/or rendered to the user interface of the device 100 (as described in more detail below). data indicative of the individual's response to the task and/or intervention, and/or one or more of an amount, concentration, or dose titration, or other treatment regimen, of a drug, agent, biological, or other agent being or will be administered to the individual may be configured to receive measurement data including data representing

Non-limiting examples of a computing device include a smartphone, tablet, slate, e-reader, digital assistant, or any other equivalent device, including any of the mobile communication devices previously described herein. As an example, the computing device may include a processor unit configured to execute an application including an analysis module for analyzing data representative of an individual's response to the rendered tasks and/or interference.

Exemplary systems, methods, and apparatuses include a computing device that uses computer-implemented adaptive psychophysical procedures to assess human performance or delivers psychological/perceptual therapy. It can be implemented as a component in

A non-limiting, exemplary characteristic of a type of decision boundary metric that may be calculated based on a response profile is a response criterion (time scale -point measure)). See, eg, Macmillan and Creelman (2004), "Signal Detection: A Users Guide" ^2nd edition, Lawrence Erlbaum USA.

In other non-limiting examples, the decision boundary metric is more than a single quantitative measure and rather can be a curve defined by quantitative parameters, based on the curve, such as, but limited to, an area on one side or the other of a response profile curve. Decision boundary metrics that do not exist can be computed. Another non-limiting and exemplary type of decision boundary metrics that may be computed to characterize decision boundary curves for evaluating the time-varying nature of a decision process are an initial bias point (the starting point of a belief accumulation trajectory) and a reference distance between, distance to decision boundary, “waiting cost” (eg, distance from initial and maximum decision boundary, or total area of curve to that point), or between decision boundary and baseline (including the normalized area in response deadlines to yield a measure of "average decision boundary" or "average criterion") of

Although examples herein may be described based on calculation of a response criterion, other types of decision boundary metrics are applicable.

3 is a signal of individual or group psychophysical data (right curve) based on data collected from individuals who performed the Test of Variables of Attention (TOVA®) test (The TOVA Company, Los Alamitos, CA). (302)) and noise (left curve 304) distributions, and an exemplary plot of the calculated response criterion are shown. The TOVA® test is intended to be used as an aid by healthcare professionals in the assessment of attention deficit and impulsivity in individuals, including attention-deficit/hyperactivity disorder (ADHD). This is an example of a computerized test that can be

In FIG. 3 , vertical lines represent response criteria 300 . The intercept of the reference line on the X-axis (in Z) is an indication of an individual's tendency to respond 'yes' (more right) or 'no (more left)' from the point p of zero bias. can be used to provide 3, p is located on the x-axis where the signal distribution (right curve 302) and the noise distribution (left curve 304) intersect. The response criterion intercepts on the left side of p may represent an individual's overall tendency toward a more impulsive strategy, and the intercepts on the right side of p may indicate an individual's overall tendency toward a more conservative strategy. The response criterion intercepts in p represent a balanced strategy.

The example systems, methods, and apparatus can be configured to implement a further extension of signal detection theory to a time-limited task (as described in more detail below). Exemplary systems, methods, and apparatuses reflect computational models of human decision-making (such as, but not limited to, drift-diffusion models (DDM) and/or Bayesian models), and different strategies. It can be configured to extend the accumulation of belief information, modeled using decision boundaries.

The following is a description of a non-limiting, exemplary use of a computational model of human decision-making (based on a drift diffusion model). The drift diffusion model is used as an example, but other types of models are applied, including the Bayesian model. The drift-diffusion model (DDM) can be applied for systems with two-choice decision making. See, e.g., Ratcliff, R. (1978), "A theory of memory retrieval." Psychological Review, 85, 59-108; Ratcliff, R., & Tuerlinckx, F. (2002), "Estimating parameters of the diffusion model: Approaches to dealing with contaminant reaction times and parameter variability," Psychonomic Bulletin & Review, 9, 438-481]. The diffusion model is based on the assumption that binary decision processes are systematic and driven by random effects.

4A shows an exemplary plot of a diffusion model with a stimulus that results in a linear drift rate, showing exemplary pathways of accumulation of confidence from the stimulus. 4A shows the distributions of drift rates across trials for targets (signal) and non-targets (noise). The vertical line is the response criterion. The drift rate in each trial is determined by the distance between the drift criterion and the sample from the drift distribution. The process starts at point x and moves over time until it reaches a lower threshold at “A” or an upper threshold at “B”. DDM assumes that at every time step an individual accumulates evidence for one or another of the alternative thresholds, and integrates that evidence to develop confidence until a decision threshold is reached. Depending on which threshold is reached, different responses (ie, Response A or Response B) are initiated by the individual. In psychological applications, this means that the decision process is complete and the response system is being activated, in which the individual initiates a corresponding response. As described in the non-limiting examples below, this involves a physical action of an individual to actuate a component of a system or apparatus to provide a response (such as, but not limited to, tapping on a user interface in response to a target). can request Systematic influences are called drift rates and drive the process in a given direction. Random effects add erratic fluctuations to a constant path. Using a given set of parameters, the model predicts distributions of process durations (ie, response times) for two possible outcomes of the process.

4A also shows an exemplary drift-diffusion path of a process, illustrating that the path is not a straight line, but rather oscillates between two boundaries due to random effects. In a situation where individuals are required to categorize stimuli, the process accounts for the proportion of information collected over time that causes the individual to foster each of two possible stimulus interpretations. Once the confidence points with sufficient clarity are reached, the individual initiates a response. In the example of FIG. 4A , processes reaching the upper threshold exhibit a positive drift rate. In some trials, random effects may outweigh the drift, and the process ends at the lower threshold.

Exemplary parameters of the drift diffusion model include quantifiers of thresholds (“A” or “B”), starting point (x), drift rate, and a response time constant (t ₀ ). DDM can provide a measure of conservatism, an indication that a process will take more time to reach one threshold and reach another threshold less frequently (as opposed to drift). The starting point x provides an indicator of bias (reflecting differences in the amount of information required before alternative responses are initiated). If x is closer to "A", then a smaller (relative) amount of information is needed to develop confidence to execute response A, compared to the larger (relative) amount of information that an individual would need to execute response B. ask for information The smaller the distance between the starting point x and the threshold, the shorter the process durations for the individual to execute the corresponding response. A positive value of the drift rate v serves as a measure of the mean rate of approach to the upper threshold "A". Drift rate represents the relative amount of information per unit of time that an individual absorbs information about a stimulus to develop confidence in initiating and executing a response. In one example, a comparison of a drift rate computed from data of one individual with a drift computed from data from another individual may provide a measure of the relative perceptual sensitivity of individuals. In another example, a comparison of drift rates may provide a relative measure of task difficulty. For the calculation of the response time, DDM makes it possible to estimate their total duration, and the response time constant t ₀ represents the duration of extra-decisional processes. DDM has been found to account for the accuracy and response times of human data for tasks. In the non-limiting example of FIG. 4A , the total response time is calculated as the sum of the magnitude of the time for stimulus encoding (t _s ), the time it takes for the individual to make a decision, and the time for executing the response.

Compared to a traditional drift diffusion model based on stimuli that result in linear drift rates, exemplary systems, methods, and apparatus in accordance with the principles herein are configured to render stimuli that result in non-linear drift rates and , these stimuli are time-varying and based on tasks and/or interferences with specified response deadlines. As a result, exemplary systems, methods, and apparatus in accordance with the principles herein are configured to apply a modified diffusion model (modified DDM) based on these stimuli resulting in non-linear drift rates.

4B shows an exemplary plot of the non-linear drift rate in the drift spread calculation. Exemplary parameters of the modified DDM also include quantifiers of thresholds (“A” or “B”), starting point (x), drift rate, and response time constant (t ₀ ). Based on data gathered from user interaction with the exemplary systems, methods, and apparatuses herein, the systems, methods, and apparatuses may be adapted in user interaction with the exemplary platforms herein. It is configured to apply a modified DDM with non-linear drift rates to provide a measure of the conservatism or impulsivity of the strategy used. Exemplary systems, methods, and apparatus employ a modified DDM model to provide (as opposed to drift) an indication of the time it takes for a given individual to reach one threshold as compared to reaching another threshold (as opposed to drift). is configured to calculate a measure of the conservatism or impulsivity of the strategy used by the individual based on the The starting point x in FIG. 4B provides an indicator of bias (reflecting differences in the amount of information required before alternative responses are initiated). For the calculation of the response time, DDM makes it possible to estimate their total duration, and the response time constant t ₀ represents the duration of further decision processes.

In exemplary systems, methods, and apparatuses in accordance with the principles herein, the non-linear drift rate is (i) a time-varying feature of portions of a task and/or interference rendered to a user interface for user response (and consequently , the amount of information available to an individual to develop trust is presented in a non-linear manner in time), and (ii) that can influence an individual's sense of timing to develop trust to initiate a response. derived from the time-varying nature of the stimuli, including the time limits of the response deadlines of the task and/or interference. Again in this example, the positive value of the drift rate v serves as a measure of the average rate of access to the upper threshold "A". The non-linear drift rate represents the relative amount of information per unit of time that an individual absorbs to develop confidence in initiating and executing a response. In one example, a comparison of a drift rate calculated from response data collected from one individual with a drift rate calculated from response data collected from another individual may be used to provide a measure of the relative perceptual sensitivity of individuals. In another example, a comparison of drift rates calculated from response data collected from a given individual from two or more different interaction sessions may be used to provide a relative measure of task difficulty. For the calculation of the response time of an individual's responses, DDM also makes it possible to estimate the total duration of the response time, the response time constant t ₀ representing the duration of further decision processes. In the non-limiting example of FIG. 4A , the total response time is calculated as the sum of the magnitude of the time for stimulus encoding (t _s ), the time it takes for the individual to make a decision, and the time for executing the response.

For modified DDM, the distance between the thresholds (i.e., between "A" and "B") provides a measure of conservatism - that is, the larger the separation, the more information the individual has before executing a response. is collected The starting point x also provides an estimate of relative conservatism: if the process starts above or below the midpoint between two thresholds, different amounts of information are required for both responses. That is, a more conservative decision criterion is applied to one response, and a more liberal criterion (ie, impulsive) is applied to the other response. The drift rate (v) represents the (relative) amount of information collected per hour, and represents either perceptual sensitivity or task difficulty.

5 is based on data collected from tasks rendered in a user interface of a computing device in accordance with the principles herein (as described in more detail herein below) and/or individual responses to interference. Thus, an exemplary plot of the signal (right curve 502) and noise (left curve 504) distributions of individual or group psychophysical data, and a calculated response criterion 500 are shown. The intercept of the reference line on the X axis (in Z units) can be used to provide an indication of an individual's tendency to respond 'yes' (more right) or 'no (more left)'. The response criterion 500 is to the left of the zero bias decision point p and where the signal distribution and the noise distribution intersect. In the non-limiting example of FIG. 5 , p is the position of the zero bias decision on the decision axis in units of Z, the response reference values to the left of p represent an impulsive strategy, and the response reference values to the right of p are conservative strategy, and the intercepts on the zero bias point represent a balanced strategy.

Exemplary systems, methods, and apparatuses in accordance with the principles herein respond based on detection or classification task(s) described herein consisting of signal (as stimuli) and non-signal responsive targets. calculate a criterion, wherein the user exhibits a response indicating the presence of a feature, or multiple features, in a series of sequential presentations of stimuli or simultaneous presentation of stimuli.

Data representing the results of classification of an individual according to the principles herein (including classifier output) may be a change in one or more of an amount, concentration, or dose titration of a drug, biologic, or other agent being or will be administered to the individual. Existing treatment or to enable formulation of a course of treatment for an individual, including determining the optimal type or combination of drugs, biologics, or other agents to be administered to the individual, and/or to one or more of a medical device, a healthcare computing system, or other device as a signal to modify a procedure, and/or to a medical practitioner, health practitioner, physical therapist, behavioral therapist; may be transferred (with appropriate consent) to a sports healthcare practitioner, pharmacist, or other practitioner.

The exemplary systems, methods, and devices herein may be used by a medical, behavioral, healthcare, or other professional as an aid in the assessment and/or improvement of an individual's attention, working memory, and/or goal management. computerized classifiers, treatment tools, and other tools that can be In an example implementation, the exemplary systems, methods, and apparatus herein apply a modified DDM to the collected data to provide measures of conservatism or impulsivity. An exemplary analysis performed using exemplary systems, methods, and apparatus in accordance with the principles herein may be used to provide measures of attention deficit and impulsivity (including ADHD). Exemplary systems, methods, and devices herein include, but are not limited to, attention, memory, motor, reaction, executive function, decision-making, problem-solving, language processing, and comprehension. Computerized classifiers, therapeutic tools, and other tools that can be used as aids in assessment and/or improvement in cognitive domains are provided. In some examples, the present systems, methods, and devices can be used to calculate metrics for use for cognitive monitoring and/or disease monitoring. In some examples, the present systems, methods, and devices can be used to calculate metrics for use for cognitive monitoring and/or disease monitoring during treatment of one or more cognitive disorders and/or diseases and/or executive dysfunction. have.

6 shows an exemplary plot of the conditional probability of a quantifier of confidence given time as the x-axis, signal along the z-axis (P(confidence | signal)), where the quantifier of confidence is the y-axis. The curve labeled Valid Target and the curve labeled Invalid Target (each in the xy plane) are plotted over time in order for the user to somehow develop strong confidence about the appropriate response. Represents data values that quantify confidence trajectories of accumulated (noisy) information. Each of the four curves labeled signal and the four curves labeled noise has a magnitude in the z-direction and are data values of a "signal" distribution and a "noise" distribution at different time points. Each signal curve is paired with a noise, which pair is time-displaced along the x-axis (at times t = t ₀ , t ₁ , t ₂ , t ₃ ). As shown in Figure 6, each signal-noise curve pair is spread out (i.e., as time increases from t ₀ to t ₃ ) to represent the probability of a given degree of confidence at a given point in time, given the type of signal. a wider curve). In this time-evolving model, a decision is made when the trust trajectory crosses a decision boundary. 6 shows exemplary curves serving as projected decision boundaries for response data values representing an impulsive strategy (narrower curve in the xy plane) and response data values representing a conservative strategy (broader curve in the xy plane). are doing As described herein, impulsive strategies require much less extreme confidence (ie, less extreme values of the quantifier of confidence) to arrive at a decision. As also described herein, a conservative strategy requires even more extreme confidence (ie, more extreme values of the quantifier of confidence) to arrive at a decision. As the perceived response deadline approaches, these decision boundaries converge to the reference values described in signal detection theory.

An exemplary system, method, or apparatus in accordance with the principles herein provides for interfering with and/or tasks rendered in a user interface to determine a measure of whether an individual is using a more conservative or more impulsive strategy. It may be applied to the data values as indicated according to FIG. 6 to compute a classifier to apply to the data representing the user's responses.

For example, as described in connection with FIG. 6 , such an exemplary model enables Bayesian inference of the shape of an individual's decision boundary based on response times and correctness of a set of decisions. In a non-limiting example, a metric characterizing the degree of impulsivity of an individual's response strategy is derived based on the area of this decision boundary compared to the area of the "ideal" decision boundary (response deadline x total width of the confidence axis). can be

7A and 7B show exemplary plots of curves for values of conservative and impulsive measures from trial start (t = 0) to perceived response deadline (RD _P ). 7A is exemplary curves for a two-alternative forced choice (2AFC) task, wherein an individual has two types (such as, but not limited to, targets with different degrees of facial expression or other characteristic/feature differences); They are ultimately targets because they are instructed/required to discriminate between the stimuli of 7B depicts exemplary curves for the GO/NO-GO task, where the individual responds/requires a response/action (based on instructions) to a stimulus (based on instructions). Instructed/required to determine whether it is a non-target that does not require an action. In some examples herein, the stimuli are designated as GO/NO-GO tasks (ie, with instructions to take/provide a response or not take/provide a response to the target). . In FIG. 7A , the plots are plotted for the time-varying stimuli described herein as well as curves for the development of confidence (for two types of target stimuli at various time points (t = 0, a, b, c, d)). Decision boundaries are shown for the values of the response criteria for . Figure 7b shows the time from trial start to response deadline for a traditional GO/NO GO task (target vs. non-target), pass/fail, or yes/no type test with two boundary conditions or binary classification. Different types of values and shapes of conservative and impulsive measures are shown. As shown in Figure 7b, the curves for the values of the conservative and impulsive measures for the GO/NO GO task show that waiting to take/respond to an action is not an instantaneous decision reached by the individual, but rather until the end of the trial ( or at least until the individual's attention is assigned elsewhere), and therefore has no right decision boundary.

7C and 7D show exemplary plots of the formation of confidence for linear and non-linear confidence accumulations, respectively. In a system with a linear confidence accumulation, FIG. 7C shows the values of mean belief for targets ( _MB (targets)) and mean confidence for non-targets ( _MB (non-targets)). It shows the evolution of confidence (on target versus non-target) at various time points (t = 0, a, b, c, d) for the value of the response criterion versus the response. Figure 7c also shows the target confidence interval and the non-target confidence interval for the linear confidence build-up. In a system with a non-linear confidence build-up, FIG. 7D shows the values of the mean confidence for targets ( _MB (targets)) and the mean confidence for non-targets (MB (non-targets)) for the non-linear confidence build-up. It shows the evolution of confidence (on target versus non-target) at various time points (t = 0, a, b, c, d) for the value of the response criterion versus the response. 7D also shows target confidence intervals and non-target confidence intervals. The traditional GO/NO GO task involves presenting a stimulus to an individual for a specific period of time that does not have a time-varying pattern, and supports the linear accumulation of trust from information available to the individual to develop trust. In contrast, exemplary tasks and/or interferences in accordance with the principles herein have at least one time-varying feature (based on their characteristic dynamics), resulting in a non-linear confidence build-up.

8A-8D show plots of probability curves for the "signal" distribution and the "noise" distribution at different time points (t = a, b, c, d) shown in FIGS. 7A-7D . each of FIGS. 8A-8D is a signal at different time points displaced along the x-axis (similar to the signal and noise curves shown at points t = t ₀ , t ₁ , t ₂ , t ₃ in FIG. 6 ) Curves and noise curves are shown. 8A-8D, as time increases from t = a to t = d, the signal-noise curve pair spreads out (i.e. becomes a wider curve), and at a given time point for a given type of signal, Expresses the probability of a given degree of confidence in In this time-evolution model, a decision is made when the trust trajectory crosses a decision boundary. 8A-8D also show the evolution of confidence versus values of average confidence in targets ( _MB (targets)) and average confidence in non-targets ( _MB (non-targets)); are doing In FIG. 8D , the decision boundaries (conservative and impulsive) converge at the criterion.

Example systems, methods, and apparatus consistent with the principles herein may be configured to implement the example response classifier to generate a quantifier of an individual's cognitive ability. Exemplary response classifiers may employ machine learning tools such as, but not limited to, linear/logistic regression, principal component analysis, generalized linear mixed models, random decision forests, support vector machines, and/or artificial neural networks. can be built using In a non-limiting example, classification techniques that can be used to train a classifier using performance measures of a labeled population of individuals (eg, individuals with a known cognitive impairment, executive dysfunction, disease, or other cognitive disorder). . A trained classifier may be applied to measures of the individual's responses to tasks and/or intervention to classify the individual with respect to a population label (eg, a cognitive impairment, executive dysfunction, disease, or other cognitive disorder). In one example, machine learning may be implemented using cluster analysis. Each measure of the cognitive response ability of participating individuals can be used as a parameter to group individuals into subsets or clusters. For example, the subset or cluster labels may be a diagnosis of a cognitive impairment, cognitive impairment, executive dysfunction, disease or other cognitive disorder. Using cluster analysis, the similarity metric of each subset and the spacing between the different subsets can be computed, and these similarity metrics calculate the individual's responses to tasks and/or interferences to classify the individual into subsets. It can be applied to the data represented. In another example, the classifier may be a supervised machine learning tool based on an artificial neural network. In this case, performance measures of individuals with known cognitive ability can be used to train a neural network algorithm to model complex relationships between different performance measures. A trained classifier can be applied to a given individual's performance/response measures to produce a classifier output that is representative of the individual's cognitive response capabilities. Other applicable techniques for generating classifiers include regression or Monte Carlo techniques for projecting cognitive abilities based on an individual's cognitive performance. Classifiers can be built using other data, including physiological measures (eg, EEG) and demographic measures.

In an example implementation, the programmed processing unit is configured to execute processor-executable instructions to render a task with interference to a user interface. As described in more detail herein, one or more of the tasks and interventions are time-varying and responsive such that the user interface imposes a limited time period for receiving at least one type of response from an individual interacting with the device or system. have a deadline The processing unit is configured to control the user interface to measure data indicative of two or more different types of responses to the task or to the interference. The programmed processing unit causes the exemplary system or apparatus to receive data representative of a first response of the individual to a task and a second response of the individual to interference, and calculate at least one response profile representative of performance of the individual. and further configured to execute the processor-executable instructions to analyze the at least some portion of the data to: As described herein, including in connection with FIGS. 4A and 4B , a decision boundary metric (such as, but not limited to, a response criterion) is a response (response) of two or more different types to a task or interference. It provides a quantitative measure of an individual's propensity to provide a response of at least one type of A versus response B). The programmed processing unit is processor executable to execute the response classifier based on computed values of a decision boundary metric (such as, but not limited to, a response criterion) to generate a classifier output indicative of an individual's cognitive response capabilities. and further configured to execute instructions.

In one example, the processing unit is configured to alter one or more of an amount, concentration, or dose titration of a drug, drug, biological agent, or other drug, causing the individual to experience side effects in response to administration of the drug, drug, biologic, or other drug. one of identifying the likelihood of experiencing a change in an individual's cognitive response ability, recommending a treatment plan, or recommending or determining the degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. We additionally use the classifier output for the above.

In any of the examples herein, the exemplary response classifier can be used as an intelligent proxy for a quantifiable assessment of an individual's cognitive abilities. That is, once the response classifier is trained, the classifier output can be used to provide an indication of the cognitive response ability of multiple individuals without using other cognitive or behavioral assessment tests.

Monitoring cognitive deficits enables individuals, and/or medical, healthcare, behavioral, or other professionals to monitor the status or progression of a cognitive disease, disorder, or executive dysfunction (with consent). For example, people with Alzheimer's disease may have mild symptoms at first, while others may have more debilitating symptoms. If the state or progression of cognitive symptoms can be quantified regularly or periodically, this can provide an indication of when one form of medication or another may be administered, or when quality of life may be compromised. may indicate a need for assisted living, etc.). Monitoring cognitive deficits may also be helpful for individuals and/or medical, healthcare, behavioral, or other professionals (consent under) to monitor an individual's response to any treatment or treatment. In one example, the classifier-based cognitive assessment tool herein may be an individual patient with attention deficit hyperactivity disorder (ADHD). In another example, classifiers and other tools can be used for any treatment from treatments with known cognitive effects, such as, but not limited to, chemotherapy, or involving uncharacterized or poorly characterized pharmacodynamics. It can be used as a monitor for the presence and/or severity of cognitive adverse events. In any example herein, the classifier analysis of cognitive performance measures and/or data is performed every 30 minutes, every few hours, daily, twice or more per week, weekly, biweekly, monthly, or once a year. can be

In one example, the response classifier can be used as an intelligent proxy for quantifiable measures of an individual's degree of conservatism or impulsivity.

In one example, the analysis of the data representative of the first response and/or the second response generates a first response profile that is an impulsive response profile or a conservative response profile.

In a non-limiting example, tasks and interventions may be rendered in a user interface such that an individual is required to provide a first response and a second response within a limited time period. In one example, the individual is required to provide a first response and a second response substantially simultaneously.

In examples herein, "substantially simultaneously" means within less than about 5 milliseconds of each other, or about 10 milliseconds, about 20 milliseconds, about 50 milliseconds, about 75 milliseconds, about 100 milliseconds from each other, or within about 150 milliseconds or less, about 200 milliseconds or less, about 250 milliseconds or less, tasks are rendered or response measurements are performed. In any instance herein, “substantially simultaneously” is a period of time that is less than the average human reaction time. In another example, two tasks may be substantially concurrent when an individual switches between two tasks within a preset amount of time. The set amount of time for switching considered to be “substantially simultaneous” may be about 1/10 second, 1 second, about 5 seconds, about 10 seconds, about 30 seconds, or more.

In a non-limiting example, the classifier output may indicate a degree of impulsivity or conservatism of an individual's cognitive response ability.

In an example, the processing unit applies at least one adaptive procedure to modify the task and/or interference, such that analysis of the data representative of the first response and/or the second response indicates a modification of the first response profile. Executes additional instructions including

In one example, the at least one response profile is configured from an impulsive response profile to a conservative response profile based on received data collected from measurements of a first response and/or a second response to the modified task and/or the modified interference. change

In one example, the task or interference includes a response deadline procedure with a response deadline; Here, the at least one adaptive procedure modifies the response deadline to modify the performance characteristic of the individual into an impulsive response profile or a conservative response profile.

In one example, the processing unit controls the user interface to modify the length of time of the response window associated with the response deadline procedure.

In one example, the processing unit controls the user interface to modify the time-varying nature of an aspect of a task or interference rendered to the user interface.

4A and 4B, the time-varying nature of the task and/or interference is such that the linear drift rate is no longer sufficient to capture the evolution of confidence over time (rather requiring a non-linear drift rate). ), resulting in time-varying availability of information about the target. A time-varying characteristic may be a characteristic such as, but not limited to, color, shape, type of organism, facial expression, or other characteristic that an individual requires to discriminate between target and non-target, allowing different temporal characteristics of availability. can result Trial-by-trial adjustment of response window length may also be a time-varying property that changes an individual's perception of where decision criteria need to be in order to respond successfully to a task and/or intervention. . Another time-varying characteristic that can be modified is the degree to which interference interferes with a parallel task that can introduce interruptions in confidence accumulation and/or response selection and execution.

In one example, modifying the time-varying nature of an aspect of a task or interference includes adjusting the length of time of rendering of the task or interference in a user interface between two or more interactive sessions of an individual.

In one example, the time-varying characteristic is one or more of a velocity of the object, a rate of change of a facial expression, a trajectory direction of the object, a change in the orientation of the object, at least one color of the object, a type of the object, or a size of the object.

In one example, the change of the type of object is morphing from an object of a first type to an object of a second type, or a blendshape is a proportional combination of an object of a first type and an object of a second type ( This is done using rendering as a proportionate combination.

In a non-limiting example, the processing unit may reward an individual for a degree of success in rendering a user interface or causing another component to interact with a task and/or interference, or other feature or other element of a system or apparatus. It may be configured to execute at least one element for representing A reward computer element may be a computer generated feature delivered to a user to enhance user satisfaction with the exemplary system, method, or device, and, as a result, to increase positive user interaction and thus enjoyment of the individual experience. can

In one example, the processing unit is sensitive to bias sensitivity derived from data representative of the first response and the second response, non-decision time sensitivity for parallel tasks, and parallel task requests. parameters representing one or more of a belief accumulation sensitivity, a reward rate sensitivity, or a response window estimation efficiency for the ? Bias sensitivity may be a measure of how sensitive an individual is to some of the tasks (propensity for one type of response versus another (eg, response A versus response B)) based on the bias of the tasks. Non-decision time sensitivity for parallel tasks may be a measure of how much interference interferes with an individual's performance of the primary task. Trust accumulation sensitivity to parallel task requests may be a measure of an individual's rate of developing/accumulating trust to counteract interference while the individual performs a primary task. The reward rate sensitivity can be used to measure how an individual's response changes based on the length of time of the response deadline window. At the end of the response deadline (eg, when the individual sees an interference trying to get out of sight), the individual finds that he or she lacks time to make a decision. It measures how an individual's responses change accordingly. The response window estimation efficiency is described as follows. When an individual decides to take/respond or not to take/respond an action, that decision needs to be based on when the individual feels that he or she lacks time to respond. For various windows, an individual will not be able to measure that window perfectly, but using sufficient trials/sessions, based on the response data, the individual will be able to base the time-varying behavior (eg, trajectory) of objects within the task or interference. Thus, it may be possible to infer how well it performs the estimation.

Exemplary systems, methods, and apparatus in accordance with the principles herein provide a method for recognizing individuals based on feedback data from the output of a computational model of human decision-making for individuals previously classified with respect to a measure of cognitive ability of interest. and may be configured to train a classifier model of a measure of cognitive ability. For example, the response classifier may be trained using a plurality of training data sets, where each training data set is associated with a previously classified individual from a group of individuals. Each of the training data sets includes data indicative of a classified individual's first response to a task and a classification for interference based on the classified individual's interactions with the example apparatus, system, or computing device described herein. and data representing the second response of the individual. Exemplary response classifiers may also include data indicative of a classified individual's performance on a cognitive test, and/or a behavioral test, and/or a state or Data indicative of a diagnosis of progression may be taken as input.

In any of the examples herein, the at least one processing unit causes an actuation component (including a cognitive platform) of the device to effect a computerized auditory, tactile, or vibrational stimuli or other interaction with the individual. It can be programmed to actuate elements. In a non-limiting example, the at least one processing unit causes a component of the cognitive platform to display at least one response from the individual based on user interaction with the task and/or interference, including responses provided using the input device. It can be programmed to receive data. In an example where at least one graphical user interface is rendered to present a computerized stimulus to an individual, the at least one processing unit may be programmed to cause the graphical user interface to receive data representative of at least one response from the individual. have.

In any of the examples herein, data indicative of an individual's response to a task and/or interference may include: a gyroscope, an accelerometer, a motion sensor, a position sensor, a pressure sensor, an optical sensor, an auditory sensor, a vibration sensor, a video camera, to be measured using at least one sensor device included in and/or coupled to the exemplary systems or apparatus herein, such as, but not limited to, a pressure sensitive surface, a touch sensitive surface, or other type of sensor. can In other examples, data indicative of an individual's response to a task and/or interference may be a video camera, microphone, joystick, keyboard, mouse, treadmill, elliptical, bicycle, stepper, or gaming device. can be measured using other types of sensor devices, including systems (including Wii®, Playstation®, or Xbox® or other gaming systems). Data may be generated based on the individual's physical actions detected and/or measured using the at least one sensor device when the individual executed the task and/or response to stimuli presented with the interference.

A user may respond to tasks by interacting with a computer device. In an example, a user may include, among other things, a keyboard for alphanumeric or directional inputs; mouse for go/no go clicking, screen position inputs, and motion inputs; joystick for motion inputs, screen position inputs, and clicking inputs; microphone for audio inputs; camera for still or motion optical inputs; Sensors such as accelerometers and gyroscopes for device motion inputs can be used to implement the response. Non-limiting example inputs to a game system include, but are not limited to, a game controller for navigation and clicking inputs, a game controller with accelerometer and gyroscope inputs, and a camera for motion optical inputs. Exemplary inputs for a mobile device or tablet include, inter alia, a touch screen for screen location information inputs, virtual keyboard alphanumeric inputs, go/no go tapping inputs, and touch screen movement inputs; accelerometer and gyroscope for motion inputs; microphone for audio inputs; Includes a camera for still or motion optical inputs. In other examples, data indicative of an individual's response may include electrodermal responses such as electroencephalogram (EEG), magnetoencephalography (MEG), heart rate, heart rate variability, blood pressure, weight, eye movements, pupil dilation, galvanic skin response, physiological sensors/scales for integrating inputs from the user's physical state, such as, but not limited to, blood glucose level, respiratory rate, and blood oxygenation.

In any of the examples herein, the individual may include a physical action, head movement, finger or hand movement, voice response, eye movement, or other action of the individual, such as clicking a button and/or moving the cursor to the correct location on the screen. may be instructed to provide a response via

As a non-limiting example, the individual's response to a task or intervention rendered in a user interface that requires the user to navigate a course or environment or perform another visual motor activity may be communicated to the individual using at least one type of sensor device. may request to make movements (such as, but not limited to, steering) that are detected and/or measured. The data from the detection or measurement provides a response to the data indicative of the response.

As a non-limiting example, the individual's response to a task or interference rendered to a user interface that requires the user to discriminate between a target and a non-target may be detected and/or measured by the individual using at least one type of sensor device. may request to perform movements (such as, but not limited to, tapping or other spatially or temporally discriminating indication). Data collected by a component of a system or apparatus (such as, but not limited to, at least one sensor or other device or component described herein) based on detection or other measurement of the individual's movements may determine the individual's responses. It provides data representing

Exemplary systems, methods, and apparatus apply a classifier model to linear/logistic regression, principal component analysis, to generate complex variables or profiles that are more sensitive than each measure alone to produce a classifier output indicative of an individual's cognitive response ability. , using computational techniques and/or machine learning tools, such as, but not limited to, generalized linear mixed model, random decision forest, support vector machine, or artificial neural network, for tasks and/or interference. data indicative of the response of, and/or data from one or more physiological measures. In an example, the classifier output may be configured for other indications, such as, but not limited to, detecting an indication of a disease, disorder or cognitive disorder, or evaluating cognitive health.

The example response classifiers herein may be trained to apply data collected from interaction sessions of individuals with a cognitive platform to provide an output. In a non-limiting example, a classifier model may be used to generate a standards table that may be applied to data collected from an individual's response to a task and/or intervention to classify the individual's cognitive response ability.

Non-limiting examples of assessment of cognitive ability include the Mini Mental State Exam, the CANTAB cognitive battery, the Test of Variables of Attention (TOVA), iterations for assessing neuropsychological status. Repeatable Battery for the Assessment of Neuropsychological Status, Clinical Global Impression Scale Relevant to Specific Conditions, Clinician's Interview-Based Impression of Change, Severe Disability Severe Impairment Battery, Alzheimer's Disease Assessment Scale, Positive and Negative Syndrome Scale, Schizophrenia Cognition Rating Scale, Connors Adult ADHD Rating Scale ( Conners Adult ADHD Rating Scales, Hamilton Rating Scale for Depression, Hamilton Anxiety Scale, Montgomery-Asberg Depressing Rating Scale, Young Maniac Rating Scale Mania Rating Scale, Children's Depression Rating Scale, Penn State Worry Questionnaire, Hospital Anxiety and Depression Scale, Abnormal Behavior Checklist (Aberrant Behavior Checklist), Activities for Daily Living scale, ADHD self-report scale, Positive and Negative Affect Schedule, Depression Anxiety Stress assessment scales or questionnaires such as the Depression Anxiety Stress Scales, the Quick Inventory of Depressive Symptomatology, and the PTSD Checklist.

In other examples, assessments include specific functions of various cognitions in cognitive or behavioral research, including tests on perceptual ability, reaction and other motor functions, vision, long-term memory, working memory, short-term memory, logic, and decision-making, and TOVA, MOT (motion-object tracking), SART, CDT (Change detection task), UFOV (useful field of view), Filter task, WAIS digit symbol, Troop, Simon task , Attentional Blink, N-back task, PRP task, task-switching test, and Flanker task.

In non-limiting examples, exemplary systems, methods, and devices in accordance with the principles described herein can be used for dementia, Parkinson's disease, cerebral amyloid angiopathy, familial amyloid neuropathy, Huntington's disease, or other neurodegenerative disease; Many different types of neuropsychological disorders, such as, but not limited to, autism spectrum disorder (ASD), the presence of 16p11.2 overlap, and/or attention deficit hyperactivity disorder (ADHD), sensory processing disorder (SPD) ), mild cognitive impairment (MCI), Alzheimer's disease, multiple sclerosis, schizophrenia, major depressive disorder (MDD), or executive dysfunction such as, but not limited to, anxiety.

The present disclosure provides a computer implementation formed as an exemplary cognitive platform configured to implement software and/or other processor-executable instructions for the purpose of measuring data indicative of a user's performance in one or more tasks, to provide a user performance metric. It's about devices. Exemplary performance metrics may be used to derive an assessment of the user's cognitive abilities and/or to measure the user's response to cognitive therapy and/or data of the user's condition (including physiological status and/or cognitive status). or other quantitative markers. Non-limiting exemplary cognitive platforms in accordance with the principles herein include neuropsychological disorders, autism spectrum disorders (ASD), presence of 16p11.2 overlap, and/or executive dysfunction, and/or individuals with cognitive platforms. Based on data collected from the interaction of and/or metrics calculated based on analysis of that data (and related calculations), when an individual is receiving (or is scheduled to receive) a drug, biologic, or other drug. ) can be configured to classify individuals with respect to the potential efficacy of the use of the cognitive platform. Still other non-limiting exemplary cognitive platforms in accordance with the principles herein are data collected from an individual's interaction with the cognitive platform and/or metrics calculated based on analysis of that data (and related calculations). can be configured to classify individuals in terms of their likelihood and/or stage of progression of a neuropsychological disease, including in terms of neurodegenerative disease. The neurodegenerative disease may be, but is not limited to, Alzheimer's disease, dementia, Parkinson's disease, cerebral amyloid angiopathy, familial amyloid neuropathy, or Huntington's disease.

Any classification of an individual with respect to the stage of onset and/or progression of a neurodegenerative disease in accordance with the principles herein refers to determining a change in the dose of a drug, biologic, or other agent for the individual, or A medical device, healthcare computing system, or other as a signal to modify an existing course of treatment or to enable the formulation of a course of treatment for an individual, including determining the optimal type of drug, biologic, or other drug. to the device and/or to a healthcare practitioner, health practitioner, physical therapist, behavioral therapist, sports healthcare practitioner, pharmacist, or other practitioner.

In any example herein, the cognitive platform may be configured as any combination of a medical device platform, a monitoring device platform, a screening device platform, or other device platform.

The present disclosure also relates to example systems that include cognitive platforms configured to couple with one or more physiological or monitoring components and/or cognitive testing components. In some examples, systems include cognitive platforms integrated with one or more other physiological or monitoring components and/or cognitive testing components. In other examples, systems include cognitive platforms individually housed from and in communication with one or more physiological or monitoring components and/or cognitive testing components configured to receive data indicative of measurements made using such one or more components.

In the exemplary systems, methods, and apparatus herein, a task or interference may include a response deadline procedure with a response deadline; Here, the at least one adaptive procedure modifies the response deadline to modify the performance characteristic of the individual into an impulsive response profile or a conservative response profile.

In the exemplary systems, methods, and apparatus herein, the processing unit may be programmed to control the user interface to modify the length of time of the response window associated with the response deadline procedure.

In the exemplary systems, methods, and apparatus herein, the processing unit may be configured to control the user interface to modify the time-varying nature of the aspect of the task or interference rendered to the user interface. For example, modifying the time-varying nature of an aspect of a task or interference may include adjusting the length of time of rendering of the task or interference in a user interface between two or more interactive sessions of an individual. As another example, the time-varying characteristic is one or more of a speed of the object, a rate of change of a facial expression, a trajectory direction of the object, a change in the orientation of the object, at least one color of the object, a type of the object, or a size of the object.

In the exemplary systems, methods, and apparatus herein, changing a type of an object includes morphing a first type of object to a second type of object or converting a blendshape between an object of a first type and an object of a second type. is implemented using rendering as a proportional combination of .

In the exemplary systems, methods, and apparatus herein, a processing unit has a bias sensitivity derived from data representative of a first response and a second response, a non-decision time sensitivity for parallel tasks, and a non-decision time sensitivity for parallel task requirements. It may be further programmed to compute as the classifier output parameters indicative of one or more of confidence accumulation sensitivity, compensation rate sensitivity, or response window estimation efficiency.

In the exemplary systems, methods, and apparatus herein, the processing unit may be further programmed to control the user interface to render the task as a continuous visual-kinesis tracking task.

In the exemplary systems, methods, and apparatus herein, the processing unit controls the user interface to render the interference as a target determination task.

As used herein, a target discrimination task may also be referred to as a perceptual response task, wherein the individual responds to a two-feature response task comprising target stimuli and non-target stimuli via a specified type of response. Instructed to perform a feature reaction task). As a non-limiting example, the specified type of response may result in an individual responding to a target stimulus to a specified physical action (eg, moving or changing the orientation of a device, coupled with a sensor such as a screen). tapping a sensor-coupled surface, moving against an optical sensor, making a sound, or other physical action that activates the sensor device) and taking such action in response to a non-target stimulus It may be that the specified physical action is not taken.

In a non-limiting example, an individual is required to perform a visual motor task (primary task) with the target discrimination task as an interference (secondary task). To perform the visual motor task, the programmed processing unit renders visual stimuli that require fine motor movement as an individual's response to the stimuli. In some examples, the visual motor task is a continuous visual motor task. The processing unit is programmed to change the visual stimuli over time (eg, at regular intervals including 1, 5, 10 or 30 times per second) and record data representative of the individual's motor movements. Exemplary stimuli rendered using a processing unit programmed for a visual motor task requiring fine motor movement may be a visual presentation of the path the avatar is required to remain within. A programmed processing unit may render a path with certain types of obstacles that the individual is required to avoid or navigate towards. In one example, fine motor movements performed by the individual, such as, but not limited to, tilting or rotating the device (eg, moving the avatar on the path while avoiding or traversing obstacles as specified) to steer or otherwise guide) using an accelerometer and/or gyroscope. The target discrimination task (acting as an interference) may be based on targets and non-targets that differ in shape and/or color.

In some examples, the task and/or interference may be a visual motor task, a target determination task, and/or a memory task.

In the context of a computer implemented adaptive response deadline procedure, a response deadline may be adjusted between trials or blocks of trials to manipulate an individual's performance characteristics toward specific goals. A common goal is to drive an individual's average response accuracy towards a certain value by controlling the response deadline.

Measurements at different response deadlines may provide different data regarding the shape and/or area of their decision boundary, and thus the computer implemented adaptive procedure may inform the calculation of the impulsive strategy metric.

In a non-limiting example, a metric from signal detection theory representing cognitive function may be a hit rate from a target discrimination task. In that context, the hit rate is the number of correct responses to target stimuli divided by the total number of presented target stimuli, or the false alarm rate (eg, the number of responses to detractor stimuli). number divided by the number of presented detractor stimuli), miss rate (e.g., the number of non-responses to target stimuli, including non-responses to target stimuli added to the number of responses to detractor stimuli) , divided by the number of incorrect responses), and the correct response rate (the proportion of correct responses that do not contain a signal). In one example, the correct response rate may be calculated as the number of non-responses to the detractor stimuli divided by the sum of the number of non-responses to the detractor stimuli and the number of responses to the target stimuli.

Exemplary systems, methods, and apparatus in accordance with the principles herein can be configured to apply adaptive performance procedures to modify measures of performance for a particular stimulus intensity. This procedure can be adjusted based on the percent correct (PC) or D-Prime (d') signal detection metric of the sensitivity to the target. In the example system, the value of the percent correct (ie, percentage of an individual's correct responses to a task) or D-prime adjusts the stimulus level of tasks and/or interventions rendered in the user interface for user interaction at every trial. It can be used in an adaptive algorithm as a basis for However, the inventors have developed a computational model of human decision-making (such as, but not limited to, modified DDM), classifiers built from the outputs of such models, and the analysis described herein based on the output of the computational model. It has been unexpectedly found that an adaptive procedure based adaptive procedure can be more quantitatively informative with respect to individual differences or changes in sensitivity to specific stimulus levels. Decision boundary metrics (such as, but not limited to, response criteria) provide a flexible tool for determining an individual's propensity to provide a particular type of response. As such, an adjustment procedure based on decision boundary metric measurements (such as, but not limited to, response criteria) at the individual or group level may determine performance at the individual or group level at the time of measurement and over time in the case of repeated measurements. It is a desirable source of information on impulsive or conservative response strategies as a quantifier of changes in

Executive function training, such as achieved by the exemplary systems, methods, and apparatuses described herein, is stimulated between trials, depending on an individual's needs or preferences or based on the clinical population receiving treatment. By modifying the levels, it may be configured to apply an adaptive algorithm to shift the user's response strategy to a more conservative or impulsive strategy, as indicated by their measured criteria.

Exemplary systems, methods, and apparatuses described herein can be used as described herein to modify difficulty levels of interference and/or tasks rendered in a user interface for user interaction at every trial ( and apply an adaptive algorithm that is adjusted based on a calculated decision boundary metric, such as, but not limited to, a response criterion.

9 shows an exemplary plot representing a stimulus adjusted for a single characteristic having a range of possible intensities. 9 shows a projected two-dimensional (2D) representation of a three-dimensional (3D) coupling distribution composed of stimuli when an observer pays attention to multiple features at once. 9 shows one of several techniques for measuring the reference of a multidimensional stimulus. In this example, a combined 80% PC or d' of 1.81 for the multidimensional stimuli is located at the point labeled 900. The band 902 is a set of possible hit rates and false alarm rates in a system or device that coordinates tasks and/or interference based on an adaptive performance procedure whose performance is oriented to PC = 80% correct. The possible d' obtained from the range is indicated. In Figure 9, the central noise distribution is centered at (0,0), which is a simplification to constrain the band 902 of possible d' positions, but the distance between the noise distribution and the signal distribution is a vector of the length of the d' value. In practice, the noise distribution center can be located anywhere on the axes as long as they are connected by . Multidimensional criteria may be estimated for individuals or groups of individuals, generating estimates of conservative or impulsive response strategies in measurement or in response to training using the computing device. Adjusting tasks and/or interference based on output from the response classifiers herein may provide greater flexibility than adjustment based on percent correct.

In one example, the task and/or interference tracks the current estimates and features of the targeting task, the trajectory and response window, and the parallel task interference to the next trial, in order to maximize the information that the trial can provide. By selecting the level/type it can be modified based on iterative estimation of the metrics.

In some examples, the task and/or interference are adaptive tasks. Tasks and/or interferences may have their difficulty levels adjusted or modified based on decision boundary metrics (such as, but not limited to, response criteria) as previously described herein. Such difficulty adjustments can be used to determine a participant's ability.

In one example, the difficulty of the task is adjusted for every stimulus presented, which will occur more often than once at regular time intervals (eg, every 5 seconds, every 10 seconds, every 20 seconds, or other regular schedule). can

In another example, the difficulty of the continuous task may be adjusted on a set schedule, such as, but not limited to, every 30 seconds, every 10 seconds, every second, twice a second, or 30 times a second.

In one example, the length of time of the trial depends on the number of repetitions of rendering (of tasks/interference) and receiving (of individual responses) and may vary in time. In one example, the trial is about 500 milliseconds, about 1 second(s), about 10 seconds, about 20 seconds, about 25 seconds, about 30 seconds, about 45 seconds, about 60 seconds, about 2 minutes, about 3 minutes, It may be on the order of about 4 minutes, about 5 minutes, or more. Each trial may have a preset length or may be set dynamically by the processing unit (eg, according to an individual's performance level or the request of adjustment from one level to another).

In one example, the features, trajectory, and response window of the targeting task, and the level/type of parallel task interference, to progressively require the device to improve in its metrics to inform the individual that it has successfully performed the task. The task and/or interference may be modified based on targeting changes in one or more specific metrics by selecting . This may include specific reinforcement, including explicit messaging, to guide the individual to modify performance according to desired goals.

In one example, user input (individual or clinician performing task/interference) to select a set of metrics for a target for comparison or change in a particular order or comparison of an individual's performance with normative data or computer model. Tasks and/or interventions may be modified based on taking other individuals, such as This may include feedback to the individual or other individual performing the task/intervention to serve as notification of changes to the procedure, potentially allowing them to approve or revise these changes before they take effect.

In various examples, the difficulty level may remain constant, or the adaptive task (primary task or secondary task) increases or decreases in difficulty based on a decision boundary metric (such as, but not limited to, a response criterion). , may change over at least a portion of the session in an adaptive implementation.

Example systems, methods, and apparatus consistent with the principles herein may be configured to enhance cognitive abilities in an individual. In an example implementation, the programmed processing unit is configured to execute processor-executable instructions to render a task with interference to a user interface. As described in more detail herein, one or more of the tasks and interventions are time-varying and responsive such that the user interface imposes a limited time period for receiving at least one type of response from an individual interacting with the device or system. have a deadline The processing unit is configured to control the user interface to measure data indicative of two or more different types of responses to the task or to the interference. The programmed processing unit causes the exemplary system or apparatus to receive data representative of a first response of the individual to a task and a second response of the individual to interference, and calculate at least one response profile representative of performance of the individual. and to execute the processor-executable instructions to analyze the at least some portion of the data to: As described herein, including in connection with FIGS. 4A and 4B , a decision boundary metric (such as, but not limited to, a response criterion) is a response (response) of two or more different types to a task or interference. It provides a quantitative measure of an individual's propensity to provide a response of at least one type of A versus response B). The programmed processing unit is configured to, in a calculated decision boundary metric (such as but not limited to a response criterion), such that the first response and/or the second response are modified, thereby indicating a modification of the individual's cognitive response ability. and execute the processor-executable instructions to coordinate the task and/or interference to derive the modification.

In one example, an indication of a modification of a cognitive response ability may be based on observation of a change in a measure of the degree of impulsivity or conservatism of an individual's cognitive response ability.

In one example, an indication of modification of cognitive response ability is sustained attention, selective attention, attention deficit, impulsivity, inhibition, perceptual ability, reaction and other motor functions, vision, long-term memory, working memory, short-term memory, It may involve a change in one or more measures of logic, or decision making.

In one example, adjusting the task and/or interference based on a first decision boundary metric (such as, but not limited to, a response criterion) may include modifying the length of time of the response window, the type of reward or the individual. modifying the presentation rate of the reward, and modifying the time-varying nature of the task and/or interference.

In one example, modifying the time-varying nature of an aspect of a task or interference may include adjusting a length of time of rendering of a task or interference in a user interface between two or more interactive sessions of an individual.

In one example, the time-varying characteristic may be a velocity of an object, a rate of change of a facial expression, a direction of a trajectory of an object, a change in an orientation of an object, at least one color of an object, a type of an object, or a size of an object, or targets versus targets in a user interface. one or more of modifying the sequence or balance of rendering of non-targets.

In one example, changing the type of an object is effected using morphing from an object of a first type to an object of a second type or rendering the blendshape as a proportional combination of the object of the first type and the object of the second type. do.

By designing a computer-implemented adaptive procedure with the goal of explicitly measuring the shape and/or area of a decision boundary, response deadlines can be adjusted to the points at which measurements generate the maximum amount of information useful to define this boundary. have. These optimal deadlines can be determined using an information theory approach to minimize the expected information entropy.

Exemplary systems, methods, and apparatuses in accordance with the principles herein employ a programmed computing device comprising at least one processing unit to determine a potential biomarker for clinical populations. can be implemented.

Exemplary systems, methods, and apparatuses in accordance with the principles herein include at least one processing unit as a metric for individuals and groups for assessing propensity for impulsive and/or conservative response strategies. may be implemented using a programmed computing device.

Exemplary systems, methods, and apparatuses in accordance with the principles herein provide a programmed computing device comprising at least one processing unit to improve computer-implemented adaptive procedures for compensating impulsive or conservative response profiles. It can be implemented using

Exemplary systems, methods, and apparatuses in accordance with the principles herein employ a programmed computing device comprising at least one processing unit to measure a change in response profile in individuals or groups after use of a treatment. can be implemented.

Exemplary systems, methods, and apparatus in accordance with the principles herein provide computer-implemented methods for greater psychophysical threshold measurement accuracy and other measurable characteristics of individual or group data that may be implemented for evaluation of response profiles. In addition to adaptive psychophysical procedures, it may be implemented using a computing device programmed to include at least one processing unit to apply the example metrics herein.

Exemplary systems, methods, and apparatus in accordance with the principles herein are described herein to add a new dimension to available data that can be used to increase the amount of information harvested from psychophysical testing. may be implemented using a computing device programmed to include at least one processing unit to apply the example metrics of

Example systems, methods, and apparatus consistent with the principles herein may be configured to enhance cognitive abilities in an individual. In an example implementation, the programmed processing unit is configured to execute processor-executable instructions to render a task with interference to a user interface. As described in more detail herein, one or more of the tasks and interventions are time-varying and responsive such that the user interface imposes a limited time period for receiving at least one type of response from an individual interacting with the device or system. have a deadline The processing unit is configured to control the user interface to measure data indicative of two or more different types of responses to the task or to the interference. The programmed processing unit causes the exemplary system or apparatus to receive (from a first session) data representative of a first response of the individual to a task and a second response of the individual to interference, and represent the first performance of the individual. analyze at least a portion of the data to compute a first response profile that further configured to run. As described herein, including in connection with FIGS. 4A and 4B , a decision boundary metric (such as, but not limited to, a response criterion) is a response (response) of two or more different types to a task or interference. It provides a quantitative measure of an individual's propensity to provide a response of at least one type of A versus response B). The programmed processing unit adjusts the task and/or interference based on a calculated first decision boundary metric (such as, but not limited to, a response criterion) (to create a second session), and Receive data representative of a first response and a second response of the individual to the interference, and analyze at least a portion of the data to provide a second response profile indicative of a second performance of the individual (such as, but not limited to, response criteria) ) is further configured to execute the processor-executable instructions to calculate a second decision boundary metric. Based on a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion), the programmed processing unit determines whether (i) the individual , the likelihood of experiencing adverse events in response to administration of the drug, or biological agent, (ii) a change in one or more of the amount, concentration, or dose titration of the agent, drug, biological agent or other agent being or will be administered to the individual, and ( iii) to generate output to a user interface indicative of one or more of recommending or determining a change in the individual's cognitive responsiveness ability, a recommended treatment plan, or a degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. and further configured to execute processor-executable instructions.

In a non-limiting example, based on the results of analysis of a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion), A medical, healthcare, or other professional may (with the individual's consent) gain a better understanding of an individual's cognitive responsiveness, and potentially more specifically (with other physiological, behavioral, and/or diagnostic measures). (including by reviewing the results of relevant analyzes) may identify a cognitive disorder, executive dysfunction, or type of disorder that may be affecting an individual's cognitive abilities. For example, the results may be used to identify a group of individuals who may better benefit from a first type of drug, drug, biologic, or other drug, while other individuals in the group may benefit from a second type of drug. You can benefit.

In a non-limiting example, based on the results of analysis of a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion), A medical, healthcare, or other professional may (with the individual's consent) administer a drug, drug, biologic, or other drug of a particular type, amount, concentration, or dose titration, including potentially affecting cognition. A better understanding of the potential side effects that may occur (or potentially are occurring) when administered may be obtained.

In a non-limiting example, a result of analysis of a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion) for specific individuals data representing the known efficacy levels of at least one type of drug, drug, biologic, or other drug experienced by individuals, and/or at least one type of drug, drug, biologic, or other drug. Provided herein is a searchable database comprising quantifiable information regarding one or more side effects experienced by an individual with administration of The searchable database may store response measures, response profiles, and/or decision boundary metrics (such as, but not limited to, response criteria) obtained for the individual when interacting with the task and/or intervention rendered on the computing device. may be configured to provide metrics for use in determining whether a given individual is a candidate for benefiting from a particular type of drug, drug, biologic, or other drug based on it.

As a non-limiting example, based on data indicative of user interaction with tasks and/or interventions rendered in a user interface of the computing device, a decision boundary metric (such as, but not limited to, a response criterion) may include: may provide information about an individual's predisposition to a particular type of response, such as, but not limited to, the degree of impulsivity or conservatism of a cognitive response strategy. This data can be helpful in identifying the extent of effectiveness of treatment plans, or behavioral therapy, counseling, and/or physical exercise.

In a non-limiting example, based on data indicative of user interaction with tasks and/or interventions rendered in a user interface of the computing device, a decision boundary metric (such as, but not limited to, a response criterion) may include: Based on the degree of impulsivity or conservatism of a person's cognitive response strategy, information about the individual can be provided. This data may include tasks rendered on the computing device and whether the individual is a candidate for a particular type of drug (such as, but not limited to, a stimulant, eg, methylphenidate or amphetamine) and /or cooperating with multiple specified repeated interactions with the intervention may help identify whether an individual would benefit from receiving the drug. Other non-limiting examples of biological agents, medicaments or other agents applicable to any of the examples described herein include methylphenidate (MPH), scopolamine, donepezil hydrochloride, rivasti rivastigmine tartrate, memantine HCI, solanezumab, aducanumab and crenezumab.

Other example systems, methods, and apparatus consistent with the principles herein may be configured to enhance cognitive abilities of an individual. In an example implementation, the programmed processing unit is configured to execute processor-executable instructions to render a task with interference to a user interface. As described in more detail herein, one or more of the tasks and interventions are time-varying and responsive such that the user interface imposes a limited time period for receiving at least one type of response from an individual interacting with the device or system. have a deadline The processing unit is configured to receive data indicative of one or more of an amount, concentration, or dose titration of a medicament, drug, or biological agent being or will be administered to an individual, and two or more different types of responses to a task or to an intervention. and control the user interface to measure data representing The programmed processing unit causes the exemplary system or apparatus to receive (from a first session) data representative of a first response of the individual to a task and a second response of the individual to interference, and represent the first performance of the individual. analyze at least a portion of the data to compute a first response profile that further configured to run. As described herein, including in connection with FIGS. 4A and 4B , a decision boundary metric (such as, but not limited to, a response criterion) is a response (response) of two or more different types to a task or interference. It provides a quantitative measure of an individual's propensity to provide a response of at least one type of A versus response B). The programmed processing unit is configured to perform a task and/or based on a first decision boundary metric (such as, but not limited to, a response criterion) and an amount or concentration of a pharmaceutical, drug, or biological agent (to generate a second session). a second response profile that coordinates the interference, receives data representative of a first response of the individual to the task and a second response of the individual to the interference, and analyzes at least a portion of the data to represent a second performance of the individual and to calculate a second decision boundary metric (such as, but not limited to, a response criterion), the processor-executable instructions. Based on a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion), the programmed processing unit determines whether (i) the individual , the likelihood of experiencing an adverse event in response to administration of the drug, or biologic, (ii) a recommended change in one or more of the amount, concentration, or dose titration of the drug, drug, biologic, or other drug, and (iii) the individual's awareness processor-executable instructions to generate output to a user interface representing one or more of recommending or determining a change in responsiveness, a recommended treatment plan, or a degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. further configured to run.

In a non-limiting example, based on the results of analysis of a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion), A medical, healthcare, or other professional (with the individual's consent) is a person who receives a drug, drug, biologic, or other drug in different amounts, concentrations, or dose titrations, including those that potentially affect cognition. You can get a better understanding of the potential side effects that could happen (or are potentially happening).

In a non-limiting example, a result of analysis of a first decision boundary metric (such as, but not limited to, a response criterion) and a second decision boundary metric (such as, but not limited to, a response criterion) for specific individuals data representing the known efficacy levels of at least one type of drug, drug, biologic, or other drug experienced by individuals, and/or at least one type of drug, drug, biologic, or other drug. Provided herein is a searchable database comprising quantifiable information regarding one or more side effects experienced by an individual with administration of The searchable database may store response measures, response profiles, and/or decision boundary metrics (such as, but not limited to, response criteria) obtained for the individual when interacting with the task and/or intervention rendered on the computing device. may be configured to provide metrics for use in determining whether a given individual is a candidate for benefiting from a particular type of drug, drug, biologic, or other drug based on it. As a non-limiting example, based on data indicative of user interaction with tasks and/or interferences rendered in a user interface of the computing device, a decision boundary metric (such as, but not limited to, a response criterion) may include: Based on the degree of impulsivity or conservatism of a person's cognitive response strategy, information about the individual can be provided. This data may indicate whether an individual is a candidate for a particular type of drug (such as, but not limited to, a stimulant, eg, methylphenidate or amphetamine) or a number of specified interactions with tasks and/or interference rendered to the computing device. Working in concert with repeated interactions, it can help an individual identify if it would be beneficial to receive a drug. Other non-limiting examples of biological agents, medicaments or other agents applicable to any of the examples described herein include methylphenidate (MPH), scopolamine, donepezil hydrochloride, rivastigmine tartrate, memantine HCl , solanezumab, aducanumab and crenezumab.

In one example, the change in the individual's cognitive response ability comprises an indication of a change in the degree of impulsivity or conservatism of the individual's cognitive response strategy.

As a non-limiting example, given that impulsive behavior accompanies ADHD, the exemplary cognitive platform configured to administer treatment (including treatment of executive function) may promote less impulsive behavior in the regimen. have. It targets the brain's dopamine systems, which may increase normal regulation, which may result in transferring the benefits of a reduction in impulsive behavior into an individual's daily life. .

Stimulants such as methylphenidate and amphetamine are also administered to individuals with ADHD to increase levels of norepinephrine and dopamine in the brain. Their cognitive effects may be due to their actions in the prefrontal cortex, but without cognitive control deficits or other cognitive remediation. Exemplary cognitive platforms herein can be configured to administer treatments (including treatment of executive function) to correct cognitive control deficits in an individual.

Use of the exemplary systems, methods, and devices in accordance with the principles described herein may include dementia, Parkinson's disease, cerebral amyloid angiopathy, familial amyloid neuropathy, Huntington's disease, or other neurodegenerative disease, autism spectrum disorder ( ASD), many different types of neuropsychological disorders, such as, but not limited to, presence of 16p11.2 overlap, and/or attention deficit hyperactivity disorder (ADHD), sensory processing disorder (SPD), mild cognitive It may be applicable to executive dysfunction such as, but not limited to, disability (MCI), Alzheimer's disease, multiple sclerosis, schizophrenia, major depressive disorder (MDD), or anxiety.

In certain example implementations, data and other information from an individual is collected, transmitted, and analyzed with the individual's consent.

By way of non-limiting example, the cognitive platform described in connection with any of the exemplary systems, methods, and apparatus herein, including a cognitive platform based on interference processing, is a project of Akili Interactive Labs, Inc. of Boston, Massachusetts: EVO?? It may be based on or include a platform.

Non-limiting exemplary tasks and interventions

Effects of interference processing on cognitive control abilities of individuals have been reported. See, for example, A. Anguera, Nature vol. 501, p. 97 (September 5, 2013)] ("Nature Papers"). See also U.S. Publication No. 20140370479A1 (U.S. Application Serial No. 13/879,589), filed on November 10, 2011, which is incorporated herein by reference. Some of those cognitive abilities include attention (selectivity, sustainability, etc.), working memory (capacity in working memory and quality of retention of information), and goal management (effectively parallelizing or executing tasks requiring two attention cognitive control abilities in areas of the ability to switch tasks). As an example, children diagnosed with Attention Deficit Hyperactivity Disorder (ADHD) show difficulty maintaining attention. Attention selectivity is characterized by reliance on neural processes involved in ignoring goal-irrelevant information and processes that facilitate focusing on goal-relevant information. turned out This publication reports neural data showing that focusing attention on one object can drag visual processing resources away from the other when two objects are viewed simultaneously. Studies have also been reported that show that memory is more dependent on effectively ignoring distractions and that the ability to memorize information is susceptible to interference by both distractions and distractions. Interference by distraction may be, for example, non-targeted interference, in which the instructions distract the individual from the primary task but indicate that the individual should not react. Interference by a jammer/disturbance is, for example, one target or two or more targets, and also distracts the individual's attention from the primary task, but the individual must respond (eg, in the case of a single target) or select (eg, in the case of a single target). , the instructions may indicate that the individual is in a forced-choose situation where he decides between different degrees of characteristic.

Decreased memory recall in the presence of a distractor may be associated with disruption of neural networks involving prefrontal cortex, visual cortex, and hippocampus (involved in memory consolidation). fMRI results showing that it can also be reported. Prefrontal cortical networks (playing a role in selective attention) may be vulnerable to disconnection by distraction. This publication also reports that goal management, which requires cognitive modulation in areas of working memory or selective attention, may be affected by secondary goals that also require cognitive modulation. This publication also reported data showing the beneficial effects of interference processing, including for reducing the deleterious effects of distractions and distractions, as a treatment with effects on an individual's cognitive ability. This publication has described cost measures (including cost of intervention) that can be calculated to quantify an individual's performance, including for assessing single-tasking or multi-tasking performance.

The exemplary cost measures disclosed in these publications are such that when an individual is engaged in a single-tasking task versus multi-tasking, a higher cost (ie, a more negative percentage cost) indicates increased interference with a multi-tasking task. is the percentage change in an individual's performance on a single-tasking task compared to .

Tangible benefits of computer implemented interference processing are also reported. For example, according to the Nature paper, multi-tasking performance assessed using computer-implemented interference processing showed a linear age-related decline in adults aged 20 to 79 years. performance) could be quantified. Nature also reports that older adults (60-85 years) who interacted with an adaptive form of computer-implemented interference processing exhibited reduced multi-tasking costs, and the gains persist for 6 months. Nature found that age-related deficits in neural signatures, as measured by electroencephalography, improved midline frontal theta power and frontal-occipital theta. It was also reported to have been corrected by multi-tasking training (using computer implemented interference processing) with frontal-posterior theta coherence. Interacting with computer-implemented interfering processing resulted in extended performance benefits (improved sustained attention and working memory) with untrained cognitive control abilities, and increases in median prefrontal theta power were associated with increases in sustained attention and multi- Foresee the maintenance of tasking improvements.

Exemplary systems, methods, and apparatus in accordance with the principles herein provide for classifying an individual with respect to cognitive ability and/or enhancing cognitive ability based on implementation of interference processing using a computerized cognitive platform. is composed of Exemplary systems, methods, and apparatus are configured to implement a form of multi-tasking using the capabilities of a programmed computing device, in which an individual is required to perform a task and interference substantially simultaneously, wherein sensing of the computing device and the measurement capability collects data representative of physical actions taken by the individual during response execution time to respond to the task at substantially the same time as the computing device collects data representative of physical actions taken by the individual to respond to the interference. configured to do The ability of computing devices and programmed processing units to render a task and/or interference to a user interface in real-time, and to measure data representative of an individual's responses to the task and/or interference in real-time and substantially concurrently, is dependent on different tasks. and rapidly switching to and from interferences or multiple different tasks or interferences in a row (including the single-tasking case, where an individual is required to perform a single type of task for a set period of time) in a row) can provide quantifiable measures of the performing individual's cognitive ability.

In any example herein, the task and/or interference includes a response deadline such that the user interface imposes a limited time period for receiving at least one type of response from an individual interacting with the apparatus or computing device. do. For example, the period of time during which an individual is required to interact with a computing device or other apparatus to perform a task and/or intervention may be about 30 seconds, about 1 minute, about 4 minutes, about 7 minutes, about 10 minutes, or a predetermined amount of time, such as, but not limited to, greater than 10 minutes.

Exemplary systems, methods, and apparatuses provide measures of an individual's cognitive ability in executive function control, as a measure of an individual's ability to determine whether to perform one action in place of another. may be configured to implement a form of multi-tasking to provide and activate rules of the current task in the presence of the interference so that the interference diverts the individual's attention from the task.

Exemplary systems, methods, and apparatus when interacting with a single type of task (ie, without interference) (such as, but not limited to, a navigation task only or a target determination task only) for a set period of time. may be configured to implement a form of single-tasking, in which measures of an individual's performance may also be used to provide a measure of an individual's cognitive ability.

Example systems, methods, and apparatus may be configured to implement sessions involving different sequences and combinations of single-tasking and multi-tasking trials. In a first example implementation, a session includes a first single-tasking trial (with a first type of task), a second single-tasking trial (with a second type of task), and a multi-tasking trial (with a primary task). is rendered with interference). In a second example implementation, a session may include two or more multi-tasking trials (primary tasks rendered with interference). In a third example implementation, a session may include two or more single-tasking trials, all based on the same type of tasks or at least one based on different types of tasks.

Performance may be further analyzed to compare the effects of two different types of interference (eg, distraction or distraction) on the performance of various tasks. Some comparisons may include performance without interference, performance with distraction, and performance with interference. The cost of each type of interference at the performance level of the task (eg, distractor cost and distractor/multi-tasking cost) is analyzed and reported to the individual.

In any of the examples herein, the interference is a stimulus that is either a non-target (which is a distraction) or a target (which is a distractor), or different types of targets (eg, different degrees of facial expressions or other characteristics). /characteristic difference) may be a secondary task containing stimuli.

effecting multiple separate sources (including sensors and other measurement components) and optionally data from multiple different sources substantially simultaneously (ie, at approximately the same time or within a short time interval); and Based on the ability of a programmed processing unit to control real-time reception, the exemplary systems, methods, and apparatuses herein are intended to address tasks and/or interventions that could not be accomplished using normal human capabilities. can be used to collect quantitative measures of responses from As a result, the exemplary systems, methods, and apparatus herein may be configured to implement a processing unit programmed to render interference substantially concurrently with the task over specific time periods.

In some example implementations, the exemplary systems, methods, and apparatus herein provide a measure of the degree and type of response of an individual to interference (regardless of whether the interference includes target or non-target). It may also be configured to receive data indicative of a measure of the degree and type of response of the individual to the task at substantially the same time the data indicative is being collected. In some examples, the exemplary systems, methods, and apparatuses, to calculate an interference cost, ratio different scoring or weighting factors than the scoring or weighting factors applied to measured data indicative of an individual's response to a target. -constructed to perform an analysis by applying it to measured data representing an individual's response to a target.

In some example implementations, the exemplary systems, methods, and apparatuses herein provide substantially simultaneous (ie, substantially identical to selectively receive data indicative of a degree and type of response of an individual to interference comprising a target stimulus (ie, a disturber) (at time) and data indicative of a magnitude and type of response of the individual to a task also configured not to selectively collect measures of the degree and type of an individual's response to interference comprising a non-targeted stimulus (i.e., a distraction element) substantially simultaneously with (i.e., substantially at the same time as) being collected. can be That is, exemplary systems, methods, and apparatus provide an individual's response to a target versus a non-target by selectively controlling the state of sensing/measurement components for measuring a response either in time and/or spatially. is configured to discriminate between the windows of This can be done by selectively activating or deactivating sensing/measurement components based on the presentation of a target or non-target, or by receiving measured data about an individual's response to a target and responding to the individual's response to a non-target. This may be achieved by selectively not receiving the measured data (eg, ignoring, rejecting, or rejecting).

As described herein, use of the exemplary systems, methods, and apparatuses herein is based on persistence of attention over time, selectivity of attention, and ability to reduce attention deficits. may be implemented to provide a measure of an individual's cognitive ability in the domain of attention. Other areas of an individual's cognitive ability that can be measured using the exemplary systems, methods, and devices herein include impulsivity, inhibition, perception, reaction and other motor functions, vision, long-term memory, task Includes memory, short-term memory, logic, and decision-making.

As described herein, using the example systems, methods, and apparatuses herein may be implemented to coordinate tasks and/or any effective plasticity-harnessing tool. ) is the most critical design element for Also, we wanted to control every single game element - the timing, location, and nature of stimuli - so that we could record neural activity during gameplay and understand what changed in the brain in response to training.

10A-15V illustrate non-limiting example user interfaces that may be rendered using the example systems, methods, and apparatuses herein for rendering tasks and/or interferences for user interactions. is showing The non-limiting exemplary user interfaces of FIGS. 10A-15V include displaying to an individual instructions for performing tasks and/or interventions, collecting data representing the individual's responses to tasks, and proceeding. It may also be used for one or more of showing metrics, and providing analysis metrics.

10A-10D illustrate non-limiting example user interfaces rendered using the example systems, methods, and apparatuses herein. As shown in FIGS. 10A and 10B , an exemplary programmed processing unit provides display features 1000 for displaying to an individual instructions for performing tasks and/or interventions, and providing analysis metrics. To show results from applying analytics to data collected from individual interactions (including responses to tasks/interferences) and/or status indicators from progress metrics It can be used to render metric features 1002 in user interfaces (including graphical user interfaces). In any of the exemplary systems, methods, and apparatuses herein, a response classifier may be used to provide analysis metrics provided as a response output. In any of the example systems, methods, and apparatuses herein, data collected from user interaction may be used as input to train a response classifier. As shown in FIGS. 10A and 10B , the exemplary programmed processing unit allows an individual (such as to navigate a path or other environment in a visual-motor task and/or to select an object in a target discrimination task, but It may also be used to render to user interfaces (including graphical user interfaces) an avatar or other processor rendered guide 1004 that is required to control (including but not limited to). As shown in FIG. 10B , display features 1000 indicate (using dashed lines) the type of movement of guide 1004 rendered by an avatar or other processor that the user interface required to perform a navigation task. During depiction, it can be used to instruct the individual what to expect to perform a navigation task. As shown in FIG. 10C , display features 1000 are expected to perform a target determination task, while the user interface depicts the type of object(s) 1006 and 1008 that may be rendered in the user interface. One type of object 1006 may be designated as a target while another type of object 1008 that may be rendered in a user interface (eg, cross-out designated as non-target (by being crossed out). As shown in FIG. 10D , display features 1000 indicate (using dashed lines) the type of movement of guide 1004 rendered by an avatar or other processor that the user interface required to perform a navigation task. While depicting and rendering the user interface of the object type designated as the target object 1006 and the object type designated as the non-target object 1008 , the primary task, the navigation task, and the secondary task (ie, interference), determine the target It can be used to instruct the individual what to expect to do different things.

11A-11D illustrate examples of features of an object(s) (targets or non-targets) that may be rendered as a time-varying characteristic in an example user interface, in accordance with the principles herein. 11A illustrates an example in which a modification to the time-varying nature of an aspect of an object 1100 rendered in a user interface is a dynamic change in the position and/or velocity of the object 1100 with respect to an environment rendered in a graphical user interface. . 11B shows that modifications to the time-varying nature of aspects of the object 1102 rendered in the user interface are of the size and/or trajectory/motion direction, and/or orientation of the object 1102 relative to the environment rendered in the graphical user interface. An example of dynamic change is shown. 11C illustrates an example in which a modification to the time-varying nature of an aspect of an object 1104 rendered in a user interface is a dynamic change in shape or other type of object 1104 relative to an environment rendered in a graphical user interface. In this non-limiting example, the time-varying properties of object 1104 are implemented using morphing from a first type of object (star object) to a second type of object (round object). . In another non-limiting example, the time-varying nature of object 1104 is effected by rendering the blendshape as a proportional combination of an object of a first type and an object of a second type. 11C shows the shape of an object 1104 rendered in a graphical user interface (in this non-limiting example, from a star object to a circular object) with modifications to the time-varying nature of an aspect of the object 1104 rendered in the user interface. or another type of dynamic change is shown. 11C shows that modifications to the time-varying nature of an aspect of the rendered object 1106 in the user interface (in this non-limiting example, from a star object having a first pattern to a circular object having a first pattern) are shown in FIG. An example is shown that is a dynamic change in a pattern, or color, or visual characteristic of an object 1106 relative to an environment rendered in the interface. In another non-limiting example, the time-varying characteristic of the object may be a rate of change of a facial expression depicted on or for the object.

12A-12T illustrate a non-limiting example of the dynamics of tasks and interferences that may be rendered in user interfaces, in accordance with the principles herein. In this example, the task is a visual-motor navigation task and the interference is target discrimination (which is a secondary task). 12D, 12I-12K, and 12O-12Q, the individual is asked to perform a navigation task by controlling the motion of the avatar 1202 along a path consistent with the milestone objects 1204. receive 12A-12T are non-limiting and exemplary in which an individual is expected to actuate an apparatus or computing device (or other sensing device) to cause an avatar 1202 to match a milestone object 1204 in response in a navigation task. An example implementation is shown, where scoring is based on an individual's success in traversing (eg, hitting) paths with milestone objects 1204 . In another example, the individual is expected to actuate an apparatus or computing device (or other sensing device) to cause the avatar 1202 to miss the milestone object 1204 , and the scoring may result in the milestone object 1204 being missed. It is based on the individual's success in avoiding. 12A-12C illustrate the dynamics of a target object 1206 (a star having a first type of pattern), where the time-varying characteristic is the trajectory of the object's motion. 12E-12H illustrate the dynamics of a non-target object 1208 (a star having a second type of pattern), where the time-varying characteristic is the trajectory of the object's motion. 12I-12T illustrate the dynamics of different parts of a navigation task, where the individual will guide the avatar 1202 to traverse with the routes with the milestone object 1204 in the absence of interference (secondary task). expected.

In the example of FIGS. 12A-12T , the processing unit of the example systems, methods, and apparatus is configured to receive data representative of the individual's physical actions to cause the avatar 1202 to navigate a route. For example, an individual may be required to perform physical actions to "steer" the avatar, eg, by changing the rotational orientation or otherwise moving the computing device. Such an action may cause a gyroscope or accelerometer or other motion or position sensor device to detect movement, thereby providing measurement data indicative of an individual's degree of success in performing a navigation task.

In the example of FIGS. 12A-12C and 12E-12H , the processing unit of the example systems, methods, and apparatus is configured to receive data representative of physical actions of an individual for performing the target determination task. For example, the individual may tap or make other physical indicia in response to display of target object 1206 prior to trial or other session and tap to make physical indicia in response to display of non-target object 1208 . You may be instructed not to. 12A-12C and 12E-12H , the target determination task functions as an interference (ie, secondary task) to the primary navigation task, in an interference processing multi-tasking implementation. As previously described herein, example systems, methods, and apparatuses cause a processing unit to render a display feature (eg, display feature 1000 ) to display instructions to an individual regarding expected performance. can do it As also described hereinabove, the processing units of the exemplary systems, methods, and apparatus are configured to: (i) the extent and type of an individual's response to interference (regardless of whether the interference includes a target or a non-target) receive data indicative of a measure of the degree and type of response of the individual to the primary task at substantially the same time as the data indicative of the measure of selectively receive data representative of a measure of the degree and type of response of an individual to interference comprising a target stimulus (ie, a disturber) substantially at the same time (ie, at substantially the same time as the data indicative of the data is being collected; and At substantially the same time (i.e., at substantially the same time) that data representing a measure of the degree and type of response of the individual to the task is collected, the individual's response to interference involving non-targeted stimuli (i.e., distractions) is It may be configured not to selectively collect a measure of the degree and type of response.

13A-13D illustrate another non-limiting example of the dynamics of tasks and interferences that may be rendered in user interfaces, in accordance with the principles herein. In this example, the task is a visual-motor navigation task, and the interference is target discrimination (which is a secondary task), where the individual navigates the avatar 1302 to traverse paths with the milestone object 1304 as the primary task. It is required to perform physical actions to gate and interact with object 1306, which is target discrimination (interference, which is a secondary task). 13A-13D illustrate an example of a type of reward 1308 that may be shown on a graphical user interface in response to an individual's indication of selecting a target object. In this non-limiting example, the reward 1308 is a set of rings rendered in the vicinity of the target 1306 substantially simultaneously with the individual making a second response that selects the target. In a non-limiting example, the second response is by tapping or other physical action on the portion of the user interface based on the individual's decision to enter the response.

14A-14D illustrate examples of dynamics of an instructions panel rendered in a user interface of an exemplary user interface. In this example, the processing unit causes the user interface to show the dynamics of movement of the instructions panel 1402 from the right side of the user interface. 14A-14A also show non-limiting examples of target objects 1404 and non-target objects 1406 . In this non-limiting example, target objects 1404 and non-target objects 1406 are different in color. As shown in FIG. 14D , the instructions panel 1402 may include a visual representation of the target object in addition to written instructions for the individual.

15A-15V illustrate other examples of the dynamics of multi-tasking involving user interaction with the implementation of a navigation task and with interference. In this example, the task is a visual-motor navigation task and the interference is target discrimination (which is a secondary task). The individual is instructed to perform a navigation task by controlling the motion of the avatar 1502 along a path consistent with the milestone objects 1504 . 15A-15V are non-limiting and exemplary in which an individual is expected to actuate an apparatus or computing device (or other sensing device) to cause an avatar 1502 to match a milestone object 1504 as a response in a navigation task. An example implementation is shown, where scoring is based on an individual's success in encountering or otherwise traversing paths with milestone objects 1504 . In another example, the individual operates the apparatus or computing device (or other sensing device) to cause the avatar 1502 to miss the milestone object 1504 (ie, not traverse paths with the milestone object 1504 ). and scoring is based on the individual's success in avoiding the milestone object 1504 . 15A-15V also show the dynamics of the target object 1506 , where the time-varying characteristic is the trajectory of the motion of the target object 1506 . 15A-15V also show the dynamics of the non-target object 1508 , where the time-varying characteristic is the trajectory of the motion of the non-target object 1508 .

15K-15V illustrate non-limiting examples of types of rewards that may be rendered to an individual to signal a degree of success in interacting with tasks and/or interference. 15K-15R, a feature 1510 containing the word "GOOD" is an avatar ( 1502) is rendered nearby. 15V shows a change in rendering of feature 1500 to display the word "GREAT", jet booster elements 1506 being in the shape of rings 1504 or other active element and/or star shape. It illustrates an example of a change in the type of rewards presented to an individual as another indication of satisfactory performance, including, but not limited to, at least one modification to the avatar 1502 to symbolize excitement. . Many other types of compensation elements may be used, and the rate and type of compensation elements displayed may be varied and modulated as a time-varying element.

As previously described herein, the exemplary systems, methods, and apparatus herein are adapted to apply a computational model of human decision-making to received response data based on the time-varying nature of the task and/or interference. is composed The time-varying nature of tasks and/or interventions results in a non-linear accumulation of confidence in an individual's decision-making. Accordingly, based on response data from the individual's interaction with the task and/or interference, the processing unit computes at least one response profile representing the individual's performance and from the response profile (such as response criteria, but not accordingly) and not limited to) determine a decision boundary metric. As previously also described herein, a response classifier may be executed based on calculated values of a decision boundary metric (such as, but not limited to, a response criterion) to generate a classifier output indicative of an individual's cognitive response ability. can

In various examples, the degree of nonlinearity in the accumulation of trust for an individual's decision-making (ie, regarding whether to execute a response) may be modulated based on adjusting the time-varying nature of the task and/or interference. As a non-limiting example, if the time-varying characteristic is the trajectory, velocity, orientation, or size of an object (target or non-target), then the information available to the individual to develop trust (to make a decision as to whether to execute a response). The amount may initially be less, e.g., if the object becomes more difficult to determine by being more distant or rendered smaller, {e.g., to make the object appear larger, change orientation, move more slowly, etc. , or when rendered to move closer to the environment} may be allowed to increase (non-linearly) at different rates depending on how quickly more information becomes available to an individual to develop trust. Other non-limiting and exemplary time-varying characteristics of the task and/or interference that may be adjusted to modulate the degree of non-linearity in the build-up of trust include: a rate of change in facial expression, at least one color of an object, a type of object, a first type of object the rate of morphing to a second type of object, and (eg, when the second type of object is a target and the first type of object is a non-target) of the first type of object and the second type of forming a blendshape. Contains one or more of the proportional amount of the object.

As also described hereinabove, the programmed processing unit may be configured to execute processor-executable instructions to coordinate tasks and/or interventions to derive modifications in the calculated response profile. When a response profile is calculated based on an individual's response data (eg, data based on a first response to a task and/or data based on a second response to an interference), the change in the calculated response profile is based on the individual's responses. and as an indication of change in performance measures. This in turn can provide an indication of the modification of an individual's cognitive response ability.

As previously described herein, adjusting tasks and/or interference based on the output from the response classifiers is more effective than adjusting based on the D-prime (d') signal detection metric or percent correct of sensitivity to the target. It can provide greater flexibility. That is, the interaction is based on an individual's interaction based on output from a response classifier trained using a computed decision boundary metric (such as, but not limited to, response criteria) and/or response data from a previous trial or session. It is coordinated by modifying parameters of the tasks and/or interventions to be rendered in the user interface in a subsequent execution or session of the action. For example, a decision criterion metric (such as, but not limited to, a response criterion) determines the number of individuals providing a first type of response of two or more different types of responses (response A versus response B) to a task or interference. In the event of a trend, the difficulty levels of the tasks and/or interventions rendered in the user interface may be modified for user interaction on a subsequent level. A methodology for adjusting difficulty levels of a task and/or intervention of a subsequent session based on a calculated decision boundary metric (such as, but not limited to, a response criterion) for an individual's performance from a previous session is of a first type. A first decision boundary metric (and first performance) of an individual (such as, but not limited to, response criteria) representing a response strategy of a second type of response strategy (such as, but not limited to, a response criterion) ) can be optimized to modify with a second decision boundary metric (and a second performance).

As a non-limiting example, a first decision boundary metric (such as, but not limited to, response criteria) of an individual representing a more impulsive response strategy (and a response criterion and a first performance) representing a more conservative response strategy (response criteria and One implementation of the exemplary systems, methods, and apparatus herein to seek to promote less impulsive behavior of an individual by modifying it with a second decision boundary metric (and second performance), such as, but not limited to, a second decision boundary metric. The difficulty level of subsequent sessions may be adjusted.

In a non-limiting example, the adjustment of the difficulty of the task and/or the intervention may be adjusted using each different stimulus presented.

In other non-limiting examples, the exemplary systems, methods, and apparatus herein set forth a difficulty level of a task and/or interference one or more times at a fixed time interval, or every second, every 10 seconds, every 30 seconds. or other established schedules, such as, but not limited to, at a frequency of once per second, twice per second, or more (such as, but not limited to, 30 times per second).

In one example, the difficulty level of the task or intervention may be a speed of the object, a rate of change of a facial expression, a trajectory direction of the object, a change in the orientation of the object, at least one color of the object, type of object, or size of the object, or target may be adjusted by altering time-varying properties, such as, but not limited to, altering the sequence or balance of presentation of stimuli versus non-target stimuli.

In a non-limiting example of a visual-motor task (a type of navigation task), the navigation speed, the shape of the course (frequency of turns, turning radius) and the number of obstacles or One or more of the sizes may be changed to modify the difficulty level of the navigation game level, the difficulty level increasing as the speed increases and/or as the number and/or size of obstacles (milestone objects) increases.

In a non-limiting example, the difficulty level of a task and/or interference of a subsequent level may also be changed in real time as feedback, eg, the difficulty level of a subsequent level may be increased or decreased with respect to data indicative of performance of the task. .

16A-16C show flowcharts of example methods, in accordance with the principles herein. In any example, the method is executed based on execution of processor-executable instructions using a programmed processing unit.

16A illustrates a method for generating a quantifier of an individual's cognitive ability using a machine learning response classifier, using a programmed processing unit. At block 1602 , the task and/or interference is time-varying and responsive such that the task is rendered to a user interface with the interference, wherein the user interface imposes a limited time period for receiving at least one type of response from the individual. have a deadline At block 1604 , data representing a first response of the individual to the task and a second response of the individual to the interference is received. At block 1606 , data representative of the first response and the second response are analyzed to calculate at least one response profile representative of the individual's performance. At block 1608, a decision boundary metric is determined from the response profile, wherein the decision boundary metric is a quantitative measure of an individual's propensity to provide at least one type of response of two or more different types of responses to a task or interference. include At block 1610, a response classifier is run based on the calculated values of the decision boundary metric to generate a classifier output indicative of the individual's cognitive response ability.

16B illustrates a method for enhancing an individual's cognitive abilities using a programmed processing unit. At block 1612 , the task and/or interference is time-varying and responsive such that the task is rendered to a user interface with the interference, wherein the user interface imposes a limited time period for receiving at least one type of response from the individual. have a deadline At block 1614 , data representing a first response of the individual to the task and a second response of the individual to the interference is received. At block 1616 , data representative of the first response and the second response are analyzed to calculate at least one response profile representative of the individual's performance. At block 1618, a decision boundary metric is determined from the response profile, wherein the decision boundary metric provides a quantitative measure of an individual's propensity to provide at least one type of response of two or more different types of responses to a task or interference. include At block 1620 , based on the calculated first decision boundary metric, the first response and/or the second response are modified, thereby indicating a modification of the individual's cognitive response ability (such as, but not based on a response criterion). Tasks and/or interferences are adjusted to derive modifications in the calculated at least one decision boundary metric (not limited).

16C illustrates a method for improving an individual's cognitive abilities using a programmed processing unit. At block 1622 , data indicative of one or more of an amount, concentration, or dose titration of an agent, drug, or biological agent that is being or will be administered to an individual is received. At block 1624 , the task and/or interference is time-varying and responsive such that the task is rendered to a user interface with the interference, wherein the user interface imposes a limited time period for receiving at least one type of response from the individual. have a deadline At block 1626 , data is received from the first session indicative of the individual's first response to the task and the individual's second response to the interference. At block 1628 , data representative of the first response and the second response are analyzed to calculate a first response profile representative of the individual's first performance. At block 1630 , a first decision boundary metric is determined based on a first response profile, wherein the first decision boundary metric is an individual providing at least one type of response of two or more different types of responses to interference. includes a quantitative measure of the tendency of At block 1632 , the task and/or intervention is adjusted to generate the second session based at least in part on the calculated first decision boundary metric and the amount or concentration of the drug, drug, or biological agent. At block 1634 , the collected data representing the first and second responses from the second session is analyzed to calculate a second response profile and a second decision boundary metric representing a second performance of the individual. At block 1636, based on the first decision boundary metric and the second decision boundary metric, (i) the likelihood that the individual will experience an adverse event in response to administration of the medicament, drug, or biological agent, (ii) the medicament, drug, or a recommended change in one or more of the amount, concentration, or dose titration of the biological agent, and (iii) a change in the individual's cognitive response ability, recommended treatment regimen, or effectiveness of at least one of behavioral therapy, counseling, or physical exercise. Output is generated to a user interface representing one or more of recommending or determining the degree.

17 is a block diagram of an example computing device 1710 that may be used as a computing component in accordance with the principles herein. In any example herein, computing device 1710 is to be configured as a console that receives user input to implement a computing component, including for applying signal detection metrics in computer implemented adaptive response deadline procedures. can For clarity, FIG. 17 also reiterates various elements of the example system of FIG. 1 and the example computing device of FIG. 2 and provides more details regarding them. Computing device 1710 may include one or more non-transitory computer-readable media for storing one or more computer-executable instructions or software for implementing the examples. Non-transitory computer-readable media includes one or more types of hardware memory, non-transitory tangible media (eg, one or more magnetic storage disks, one or more optical disks, one or more flash drives), and the like. may include, but are not limited to. For example, memory 302 included in computing device 1710 may store computer-readable and computer-executable instructions or software for performing the operations disclosed herein. For example, the memory 302 may be configured to perform many of the disclosed operations (eg, analyzing cognitive platform measurement data and response data, applying signal detection metrics in an adaptive response deadline procedure, or performing a calculation). may store a software application 1740 configured to perform (various). Computing device 1710 includes configurable and/or programmable processor 304 and associated Core 1714, and optionally one or more additional configurable and/or programmable processing devices, such as processor(s) 1712' and associated core(s) 1714' (e.g., multiple processors) in the case of computing devices with s/cores). Each of the processor 304 and processor(s) 1712' may be a single core processor or a multi-core 1714 and 1714' processor.

Virtualization may be employed in the computing device 1710 such that infrastructure and resources within the console may be dynamically shared. A virtual machine 1724 may be provided to handle a process running on multiple processors, such that the process appears to use only one computing resource rather than multiple computing resources. Multiple virtual machines on one processor may also be used.

Memory 302 may include computational device memory or random access memory, such as DRAM, SRAM, EDO RAM, and the like. Memory 302 may include other types of memory as well, or combinations thereof.

A user interacts with a computing device 1710 via a visual display unit 1728 , such as a computer monitor, that may display one or more user interfaces (UIs) 1730 that may be provided in accordance with example systems and methods. can interact Computing device 1710 may include other I/O devices for receiving input from a user, such as a keyboard or any suitable multi-point touch interface 1718 , pointing device 1720 (eg, a mouse). may include A keyboard 1718 and pointing device 1720 may be coupled to a visual display unit 1728 . Computing device 1710 may include other suitable conventional I/O peripherals.

Computing device 1710 may include one or more storage, such as a hard drive, CD-ROM, or other computer readable media, for storing data and computer readable instructions and/or software to perform the operations disclosed herein. A device 1734 may also be included. The example storage device 1734 may also store one or more databases for storing any suitable information required to implement the example systems and methods. Databases may be updated manually or automatically at any suitable time to add, delete, and/or update one or more entries in the databases.

Computing device 1710 may include standard telephone lines, LAN or WAN links (eg, 802.11, T1, T3, 56kb, X.25), broadband connections (eg, ISDN, Frame Relay, ATM), wireless One or more networks, e.g., a Local Area Network (LAN), via a variety of connections including, but not limited to, connections, a controller area network (CAN), or any combination of any or all of the foregoing. ), a wide area network (WAN), or the Internet and a network interface 1722 configured to interface via one or more network devices 1732 . Network interface 1722 may be a built-in network adapter, network interface card, PCMCIA network card, Card Bus network adapter, wireless network adapter, USB network adapter, modem, or other device that performs the operations described herein and communicates. It may include any other device suitable for interfacing the capable computing device 1710 to any type of network. Moreover, computing device 1710 may be a workstation, desktop computer, server, laptop, handheld computer, tablet computer, or capable of communicating and having sufficient processor power and memory to perform the operations described herein. It may be any computing device, such as any other type of computing or communication device with capacity.

Computing device 1710 can be any of the versions of Microsoft® Windows® operating systems, different releases of Unix and Linux operating systems, any version of MacOS® for Macintosh computers, any embedded operating system, any real-time operating system. may run any operating system 1726 , such as a system, any open source operating system, any proprietary operating system, or any other operating system running on a console and capable of performing the operations described herein. . In some examples, operating system 1726 may run in a native mode or an emulated mode. In one example, operating system 1726 may run on one or more cloud machine instances.

Examples of the systems, methods, and operations described herein include digital electronic circuitry, computer software, firmware, or hardware, including the structures disclosed herein and structural equivalents thereof, or combinations of one or more thereof. can be implemented as Examples of the systems, methods, and operations described herein are one or more computer programs, encoded on a computer storage medium, for execution by or for controlling operation of a data processing apparatus. It may be implemented as one or more modules of instructions. The program instructions may be generated in an artificially generated propagated signal, e.g., machine-generated electrical, optical, or encoded on an electromagnetic signal. The computer storage medium may be, or may be included in, a computer readable storage device, a computer readable storage substrate, a random or serial access memory array or device, or a combination of one or more thereof. Moreover, although a computer storage medium is not a propagated signal, the computer storage medium may be a source or destination of computer program instructions encoded in an artificially generated propagated signal. Computer storage media may also be or be included in one or more separate physical components or media (eg, multiple CDs, disks, or other storage devices).

The operations described herein may be implemented as operations performed by a data processing apparatus on data stored on one or more computer-readable storage devices or received from other sources.

The term “data processing apparatus” or “computing device” refers to data, including, by way of example, a programmable processor, computer, system on a chip, or many of the foregoing or combinations of the foregoing. covers all kinds of apparatuses, devices, and machines for processing The device may include special purpose logic circuitry, for example, a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The apparatus may include, in addition to hardware, code that creates an execution environment for the computer program in question, such as processor firmware, protocol stack, database management system, operating system, cross-platform runtime environment, virtual machine, or one or more of these. Codes that make up the combination may also be included.

A computer program (also called a program, software, software application, script, application, or code) may be any language, including compiled or interpreted languages, declarative or procedural languages. may be written in a programming language in the form of a computer program, as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment It may be deployed in any form, including as A computer program can, but need not, correspond to a file in the file system. A program may be stored in a portion of a file that holds other programs or data (eg, one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files ( For example, it may be stored in one or more modules, sub-programs, or files storing portions of code). A computer program may be distributed for execution on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communications network.

The processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs to perform actions by manipulating input data to produce output. Processes and logic flows may also be performed, for example, by special purpose logic circuitry, such as a field programmable gate array (FPGA) or application specific integrated circuit (ASIC), and apparatuses may also be implemented as them.

Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from either read-only memory or random access memory or both. The essential elements of a computer are a processor for performing actions according to the instructions and one or more memory devices for storing instructions and data. Generally, a computer also includes one or more mass storage devices for storing data, such as magnetic, magneto-optical disks, or optical disks, operatively coupled to receive data from, or transmit data to. or both. However, the computer need not have such devices. Moreover, the computer may be, for example, connected to another device, such as a mobile phone, personal digital assistant (PDA), mobile audio or video player, game console, Global Positioning System (GPS) receiver, or portable storage device (eg, USB (USB) It can be embedded in a universal serial bus (flash drive). Devices suitable for storing computer program instructions and data include, by way of example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and all forms of non-volatile memory, media and memory devices, including CD ROM and DVD-ROM disks. The processor and memory may be supplemented by or integrated with special purpose logic circuitry.

To provide for interaction with a user, embodiments of the subject matter described herein provide a display device for displaying information to a user and a keyboard and pointing device such as a mouse, stylus, touch screen or trackball, whereby the user capable of providing input to the computer. Other types of devices may also be used to provide interaction with the user. For example, the feedback provided to the user (ie, output) may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback. ) may be; Input from the user may be received in any form, including acoustic, voice, or tactile input. In addition, the computer may transmit documents to and receive documents from a device used by a user; For example, the user may interact with the user by sending web pages to the web browser on the user's client device in response to requests received from the web browser.

In some examples, a system, method, or act herein includes a back end component, eg, a data server, or includes a middleware component, eg, an application server, or a front end component, eg, a user to be implemented on a client computer having a graphical user interface or web browser capable of interacting with implementations of the subject matter described herein, or a computing system comprising any combination of one or more such back-end, middleware, or front-end components. can The components of the system may be interconnected by any form or medium of digital data communication, such as a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), an inter-network (eg, the Internet), and a peer-to-peer network. - include peer networks (eg, ad hoc peer-to-peer networks).

An example computing system may include clients and servers. Clients and servers are typically remote from each other and typically interact through a communications network. The relationship of client and server arises by virtue of computer programs running on their respective computers and having a client-server relationship with each other. In some embodiments, the server sends data to the client device (eg, for purposes of displaying data to and receiving user input from a user interacting with the client device). Data generated at the client device (eg, a result of a user interaction) may be received from the client device to a server.

conclusion

Although this specification contains many specific implementation details, these should not be construed as limitations on the scope of any inventions or of what may be claimed, but rather features specific to particular embodiments of the systems and methods described herein. should be construed as their explanations. Certain features that are described herein in the context of separate embodiments may also be implemented in combination in a single embodiment. Alternatively, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination. Moreover, although features have been described above as functioning in particular combinations and even initially claimed as such, one or more features from a claimed combination may in some cases be eliminated from the combination, and the claimed combination may be It may relate to a subcombination or a variation of a subcombination.

Similarly, although acts are depicted in a particular order in the figures, this does not indicate that such acts must be performed in the particular order or sequential order shown, or that all illustrated acts must be performed in order to achieve desirable results. It should not be construed as demanding. In some cases, the actions recited in the claims may be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or sequential order to achieve desirable results.

In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the above-described embodiments should not be construed as requiring such separation in all embodiments, and that the described program components and systems are generally integrated together in a single software product or that multiple It should be understood that they may be packaged into software products of

The embodiments described above may be implemented in any of a variety of ways. For example, some embodiments may be implemented using hardware, software, or a combination thereof. When any aspect of an embodiment is implemented at least in part in software, the software code may execute on any suitable processor or collection of processors, whether provided on a single computer or distributed among multiple computers.

The embodiments described above may be implemented in any of a variety of ways. For example, some embodiments may be implemented using hardware, software, or a combination thereof. When any aspect of an embodiment is implemented at least in part in software, the software code may execute on any suitable processor or collection of processors, whether provided on a single computer or distributed among multiple computers.

In this regard, various aspects of the present invention are directed to one or more program-encoded computer-readable storage media (or circuitry in multiple computer-readable storage media (eg, computer memory, compact disks, optical disks, magnetic tapes, flash memories, Field Programmable Gate Arrays) or other semiconductor devices. configurations, other tangible computer storage media or non-transitory media). A computer readable medium or media may be transportable, such that a program or programs stored thereon can be loaded onto one or more different computers or other processors to implement various aspects of the subject technology as discussed above. can

The terms “program” or “software” as previously discussed refer to any type of computer code or set of computer-executable instructions that can be used to program a computer or other processor to implement various aspects of the present technology. is used herein in a generic sense for Additionally, in accordance with an aspect of this embodiment, one or more computer programs that, when executed, do not need to reside on a single computer or processor for performing the methods of the present technology, and do not need to reside on a number of different It should be appreciated that it may be distributed in a modular fashion between computers or processors.

Computer-executable instructions may be in many forms, such as program modules, being executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Typically, the functionality of the program modules may be combined or distributed as desired in various embodiments.

Also, the techniques described herein may be embodied as a method, wherein at least one example of the method is provided. The acts performed as part of the method may be ordered in any suitable manner. Accordingly, embodiments may be constructed wherein the operations are performed in an order different from that illustrated, which embodiments may include performing some operations concurrently, although shown as sequential operations in the exemplary embodiments. can

All definitions, as defined and used herein, should be understood to take precedence over dictionary definitions, definitions in documents incorporated by reference, and/or the ordinary meanings of the defined terms. .

As used herein in the specification and in the claims, the indefinite articles "a" and "an" should be understood to mean "at least one" unless expressly indicated otherwise.

The phrase “and/or”, as used herein in the specification and in the claims, means elements that are so conjoined, i.e., exist conjunctively in some cases and conjunctively in other cases. should be understood to mean "either or both" of the elements present disjunctively in Multiple elements listed using “and/or” should be construed in the same way, ie as one or more of the elements so covalently connected. Other elements than those specifically identified by the "and/or" clause may optionally be present, whether related or unrelated to those elements specifically identified. Thus, by way of non-limiting example, reference to "A and/or B", when used in conjunction with an open-ended language such as "comprising," in one embodiment, only A ( optionally including elements other than B); In another embodiment, only B (optionally including elements other than A); In another embodiment, both A and B (optionally including other elements); and the like may be referred to.

As used herein in the specification and in the claims, “or” should be understood to have the same meaning as “and/or” as previously defined. For example, when separating items in a list, "or" or "and/or" should be construed as inclusive, i.e., multiple elements or lists of elements and, optionally, no additional enumerations. The inclusion of at least one of the non-existent items should, of course, be construed as including more than one of them. There are only a number of terms expressly indicated otherwise, such as "only one of" or "exactly one of" or, when used in the claims, "consisting of" shall refer to including exactly one element of the elements or list of elements of Generally, the term “or,” as used herein, is exclusive when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.” It should only be construed as indicating an exclusive alternative (ie one or the other, not both). “Consisting essentially of” when used in the claims should have its ordinary meaning as used in the field of patent law.

As used herein in the specification and claims, the phrase "at least one" in a reference to a list of one or more elements means at least one element selected from any one or more of the elements in the list of elements. Although it should be understood that at least one of each element specifically recited in the list of elements is not necessarily included and does not exclude any combinations of elements in the list of elements. This definition also defines that within the list of elements to which the phrase "at least one" refers, elements other than those specifically identified may optionally be present, whether related or unrelated to those elements specifically identified. allow that Thus, by way of non-limiting example, “at least one of A and B” (or equivalently, “at least one of A or B,” or equivalently, “at least one of A and/or B”) is, in one embodiment, “at least one of A and/or B”. In an example, where B is absent (and optionally includes elements other than B), it can refer to at least one A, optionally including more than one A; In other embodiments, when A is absent (and optionally includes elements other than A), it can refer to at least one B, optionally including more than one B; in yet another embodiment, at least one A, optionally comprising more than one A, and at least one B, optionally comprising more than one B, (and optionally including other elements), and ; and so forth.

In the claims as well as in the above specification, "comprising", "including", "carrying", "having", "containing", "accompanying All transitional phrases such as "involving", "holding", "composed of", and the like are open-ended, i.e., "of should be understood to mean "including but not limited to". Only the transitional phrases "consisting of" and "consisting essentially of" are, respectively, closed or semi-closed ( semi-closed) transitional phrases.

Claims (108)

A method for generating a quantifier of an individual's cognitive skills using a response classifier, comprising:
using the at least one processing unit to render the task with interference in the user interface;
measuring, using the at least one processing unit, data indicative of two or more different types of responses to the task or to the interference;
receiving, using the at least one processing unit, data representing a first response of the individual to the task and a second response of the individual to the interference;
analyzing, using the at least one processing unit, the data representative of the first response and the second response to calculate at least one response profile representative of performance of the individual;
determining, using the at least one processing unit, a decision boundary metric from the at least one response profile, wherein the decision boundary metric is at least one of the two or more different types of responses to the interference. comprising a quantitative measure of the individual's tendency to provide a type of response of ;
executing, using the at least one processing unit, a response classifier based at least in part on the decision boundary metric to generate a classifier output indicative of cognitive response capabilities of the individual; ; and
applying at least one adaptive procedure to modify the task and/or the interference such that analysis of the data representative of the first response and/or the second response indicates a modification of the at least one response profile;
including,
the task or the interference comprises a response deadline procedure with a response deadline;
wherein the at least one adaptive procedure modifies the response deadline to modify the performance characteristic of the individual to an impulsive response profile or a conservative response profile;
How to implement a computer. The method of claim 1 , wherein the processing unit is further configured to control at least one actuating component to effectuate one or more of an auditory stimulus, a tactile stimulus, and a vibratory stimulus, wherein the task and/or the interference comprises: and at least one of the auditory stimulus, the tactile stimulus, and the vibratory stimulus. The method of claim 1 , wherein calculating the at least one response profile comprises generating at least one response profile that is an impulsive response profile or a conservative response profile. 2. The user interface of claim 1, wherein the processing unit is configured to control the user interface to modify at least one of a length of time of a response window associated with a response deadline procedure or a time-varying characteristic of an aspect of the interference or task rendered in the user interface. A computer-implemented method. 2. The processing unit of claim 1, wherein the processing unit is further configured to: bias sensitivity derived from the data representative of the first response and the second response, non-decision time sensitivity for parallel tasks, and confidence accumulation for parallel task requests. and calculate as the classifier output parameters indicative of one or more of sensitivity, compensation rate sensitivity, or response window estimation efficiency. The method of claim 1 , wherein the processing unit is configured to control the user interface to render the task as a continuous visual-kinesis tracking task. The method of claim 1 , wherein the processing unit is configured to control a user interface to render the interference as a target discriminative interference. 2. The method of claim 1, wherein rendering the task with the interference comprises:
rendering the task in the presence of the interference such that the interference diverts the individual's attention from the task, wherein the interference is selected from the group consisting of a distraction and a distraction. . The computer-implemented method of claim 1 , wherein the response classifier is trained based at least in part on feedback data from a computational model of human decision-making. 10. The method of claim 9, wherein the computational model of human decision-making is a drift-diffusion model. 2. The method of claim 1, wherein the response classifier is trained using a plurality of training data sets, each training data set corresponding to a previously classified one of the plurality of individuals, and each training data set corresponding to the task. data indicative of the first response of the classified individual to the interference, data indicative of the second response of the classified individual to the interference, and (i) performance of the classified individual in one or more of a cognitive test or a behavioral test. and (ii) data indicative of a diagnosis of the state or progression of a cognitive disease, disease, or executive dysfunction of the classified individual. The computer-implemented method of claim 1 , wherein the classifier output includes an indication of a degree of impulsivity or conservatism of the individual's cognitive response ability. The computer implemented method of claim 1 , wherein the classifier output is sent to and/or displayed in the user interface. The method of claim 1 , wherein the classifier output comprises a measure of the individual's attention deficit or impulsivity. The computer implemented method of claim 1 , further comprising using the classifier output for cognitive monitoring of one or more of a cognitive disease, disorder, or executive dysfunction. 2. The method of claim 1, wherein receiving the data representative of the first response and the second response comprises using one or more sensor components to receive the data representative of the first response and the second response. A computer-implemented method comprising: The method of claim 1 , wherein altering one or more of the amount, concentration, or dose titration of the agent, drug, or biological agent is to reduce the likelihood that the individual will experience adverse effects in response to administration of the agent, drug, or biological agent. one or more of identifying, identifying a change in the individual's cognitive response ability, recommending a treatment plan, or recommending or determining the degree of effectiveness of at least one of behavioral therapy, counseling, or physical exercise. and using the classifier output to A device for generating a quantifier of an individual's cognitive ability using a response classifier, comprising:
A device comprising means for performing a method according to claim 1 . 18. A system comprising one or more physiological components and an apparatus configured to perform the method of any one of claims 1-17, comprising:
Upon execution of processor-executable instructions by the processing unit, the processing unit:
receive data indicative of one or more measurements of the one or more physiological components; and
and execute the response classifier based, at least in part, on the data indicative of the one or more measurements of the one or more physiological components and the calculated values of the decision boundary metric to generate the classifier output. . At least one non-transitory computer-readable medium for storing one or more computer-executable instructions that, when executed, cause a processing unit to execute the method of any one of claims 1-17. A method for generating a quantifier of an individual's cognitive ability, comprising:
rendering, using the at least one processing unit, the task with the interference in the user interface;
measuring, using the at least one processing unit, data indicative of two or more different types of responses to the task or to the interference;
receiving, using the at least one processing unit, data representing a first response of the individual to the task and a second response of the individual to the interference;
analyzing, using the at least one processing unit, the data representative of the first response and the second response to calculate at least one response profile representing performance of the individual;
determining, using the at least one processing unit, a first decision boundary metric based, at least in part, on the at least one response profile, wherein the first decision boundary metric comprises the two or more different types of interference for the interference. comprising a quantitative measure of the individual's propensity to provide a response of at least one type of response; and
Based at least in part on the determined first decision boundary metric, using the at least one processing unit, the first response and/or the second response are modified, thereby indicating a modification of the cognitive response ability of the individual. applying at least one adaptive procedure to adjust the task and/or the interference to derive a modification in the determined first decision boundary metric.
including,
the task or the interference comprises a response deadline procedure with a response deadline;
wherein the at least one adaptive procedure modifies the response deadline to modify the performance characteristic of the individual to an impulsive response profile or a conservative response profile;
How to implement a computer. The method of claim 21 , wherein calculating the at least one response profile comprises generating at least one response profile that is an impulsive response profile or a conservative response profile. 22. The method of claim 21, wherein the analysis of the data representative of the first response and/or the second response indicates a modification of the at least one response profile. and applying an adaptive procedure. 22. The method of claim 21, further comprising controlling the user interface to modify at least one of a length of time of a response window associated with a response deadline procedure or a time-varying characteristic of an aspect of the interference or task rendered in the user interface. , a computer-implemented method. A device for generating a quantifier of an individual's cognitive ability using a response classifier, comprising:
Device comprising means for performing a method according to any one of claims 21 to 24. 25. A system comprising one or more physiological components and an apparatus configured to perform the method of any one of claims 21-24, comprising:
Upon execution of processor-executable instructions by the processing unit, the processing unit:
receive data indicative of one or more measurements of the one or more physiological components; and
and adjust the task and/or the interference based at least in part on the data indicative of the determined first decision boundary metric and the one or more measurements of the one or more physiological components. At least one non-transitory computer-readable medium for storing one or more computer-executable instructions that, when executed, cause a processing unit to execute the method of any one of claims 21-24. delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete delete

Images