CN118021307A - Micro-action-based cognitive level assessment method, electronic device and readable medium - Google Patents
Micro-action-based cognitive level assessment method, electronic device and readable medium Download PDFInfo
- Publication number
- CN118021307A CN118021307A CN202410435275.1A CN202410435275A CN118021307A CN 118021307 A CN118021307 A CN 118021307A CN 202410435275 A CN202410435275 A CN 202410435275A CN 118021307 A CN118021307 A CN 118021307A
- Authority
- CN
- China
- Prior art keywords
- stimulation
- micro
- preset
- sequence
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000001149 cognitive effect Effects 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000000638 stimulation Effects 0.000 claims abstract description 220
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000011156 evaluation Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 10
- 230000003183 myoelectrical effect Effects 0.000 claims description 39
- 230000000007 visual effect Effects 0.000 claims description 17
- 239000000463 material Substances 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 5
- VLARLSIGSPVYHX-UHFFFAOYSA-N (2,5-dioxopyrrolidin-1-yl) 6-(2,5-dioxopyrrol-1-yl)hexanoate Chemical compound O=C1CCC(=O)N1OC(=O)CCCCCN1C(=O)C=CC1=O VLARLSIGSPVYHX-UHFFFAOYSA-N 0.000 claims description 3
- 230000005857 detection of stimulus Effects 0.000 description 14
- 230000033001 locomotion Effects 0.000 description 13
- 210000003205 muscle Anatomy 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 6
- 238000005481 NMR spectroscopy Methods 0.000 description 4
- 208000027626 Neurocognitive disease Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 210000004556 brain Anatomy 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000007917 intracranial administration Methods 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 150000002739 metals Chemical class 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000035807 sensation Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 208000024827 Alzheimer disease Diseases 0.000 description 2
- 208000018737 Parkinson disease Diseases 0.000 description 2
- 201000004810 Vascular dementia Diseases 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 208000029028 brain injury Diseases 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003557 neuropsychological effect Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000014644 Brain disease Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000028698 Cognitive impairment Diseases 0.000 description 1
- 241001112258 Moca Species 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 201000011529 cardiovascular cancer Diseases 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 208000010877 cognitive disease Diseases 0.000 description 1
- 230000003920 cognitive function Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000003412 degenerative effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007659 motor function Effects 0.000 description 1
- 230000009461 neurocognitive dysfunction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009023 proprioceptive sensation Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 210000001044 sensory neuron Anatomy 0.000 description 1
- 230000021317 sensory perception Effects 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application discloses a cognitive level assessment method based on micro-actions, which comprises the following steps: acquiring a micro-action data sequence of an evaluated object in a preset stimulation mode; the type of each micro-action data comprises myoelectricity data and touch data; determining a stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode, and determining a stimulation detection result sequence corresponding to the micro-action data sequence based on a stimulation detection model; the stimulation detection model is obtained by training an initial detection model in advance by utilizing a micro-action data sequence of a healthy tested object in a preset stimulation mode; determining a cognitive level evaluation result of the evaluated object according to the stimulation reference result sequence and the stimulation detection result sequence; the stimulation reference results and the stimulation detection results each include information for characterizing whether a stimulus is received and information for characterizing the type of stimulus. The application also discloses an electronic device and a computer readable medium.
Description
Technical Field
The application relates to the technical field of cognitive assessment, in particular to a cognitive level assessment method based on micro-actions, electronic equipment and a computer readable medium.
Background
The neuro-cognitive disorder is a syndrome with acquired cognitive function impairment as a core and obvious decline of daily life ability, learning ability, working ability and social interaction ability of patients, and the elderly are found to be the fourth disease which threatens the health of the elderly after cerebral apoplexy, cardiovascular diseases and cancers, and the elderly people with neuro-cognitive disorder in China are the first global. Neurocognitive disorders are often associated with degenerative brain diseases, the most common causes of which include Alzheimer's Disease (AD), vascular dementia (VaD) and Parkinson's Disease (PD). Neurocognitive disorders usually occur in the early stages of these three diseases. Neurocognitive dysfunction can be effectively identified by cognitive level assessment.
Accurate assessment of cognitive levels is an important and difficult point of modern neuroscience. Accurate diagnosis of cognitive levels not only affects the treatment decisions of the clinician and family members on the patient, but also reflects the degree of awareness of people regarding the ethical issues of such diseases. The problems of narrow audience area, low accuracy and the like of the traditional cognitive level assessment method generally exist, and a novel method which is wide in audience area and capable of accurately detecting the cognitive level of a patient is needed to be searched.
Disclosure of Invention
The present application aims to solve one of the technical problems in the related art to a certain extent. To this end, the application provides a micro-action based cognitive level assessment method, an electronic device and a computer readable medium.
As a first aspect of the present application, there is provided a micro-action based cognitive level assessment method, wherein the method comprises:
acquiring a micro-action data sequence of an evaluated object in a preset stimulation mode; the micro-action data comprises myoelectricity data and touch data;
Determining a stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode, and determining a stimulation detection result sequence corresponding to the micro-action data sequence based on a stimulation detection model; the stimulation detection model is obtained by training an initial detection model in advance by utilizing a micro-action data sequence of a healthy tested object in a preset stimulation mode;
determining a cognitive level evaluation result of the evaluated object according to the stimulation reference result sequence and the stimulation detection result sequence; wherein the stimulation reference result and the stimulation detection result each comprise information for representing whether a stimulation is received or not and information for representing a stimulation type.
Optionally, the determining the cognitive level evaluation result of the evaluated object according to the stimulation reference result sequence and the stimulation detection result sequence includes:
Calculating the matching degree between the stimulation reference result sequence and the stimulation detection result sequence;
under the condition that the matching degree is smaller than a first preset threshold value, determining that the cognitive level evaluation result of the evaluated object is a plant state VS level;
determining that the cognitive level evaluation result of the evaluated object is the minimum consciousness state MCS level under the condition that the matching degree is not smaller than the first preset threshold value and smaller than a second preset threshold value;
And under the condition that the matching degree is not smaller than the second preset threshold value, determining that the cognitive level evaluation result of the evaluated object is the EMCS level which is out of the minimum consciousness state.
Optionally, the step of calculating the matching degree between the stimulation reference result sequence and the stimulation detection result sequence includes:
And judging that the stimulation reference result is matched with the stimulation reference result under the condition that the information used for representing whether the stimulation is received in the stimulation reference result is matched with the information used for representing whether the stimulation is received in the stimulation detection result and the information used for representing the stimulation type in the stimulation reference result is matched with the information used for representing the stimulation type in the stimulation detection result.
Optionally, the preset stimulation mode includes a correspondence between different preset stimulation states and time, the different preset stimulation states include a non-stimulation state and a stimulation state, and the stimulation state includes multiple pain stimulation types, multiple visual stimulation types and multiple auditory stimulation types;
The determining the stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode comprises the following steps:
Inquiring the preset stimulation mode according to the data acquisition time corresponding to each micro-action data, and determining the preset stimulation state corresponding to each micro-action data;
And determining a stimulation reference result corresponding to each micro-action data according to the preset stimulation state corresponding to each micro-action data, and obtaining the stimulation reference result sequence.
Optionally, the acquiring the micro-motion data sequence of the evaluated object under the preset stimulation mode includes:
Acquiring an initial myoelectric signal of an evaluated object in a preset stimulation mode through a preset myoelectric arm ring; the touch video of the hand of the evaluated object in contact with the flexible material layer in a preset stimulation mode is acquired through a preset touch sensor;
Preprocessing the initial myoelectric signal to obtain myoelectric data; preprocessing the touch video to obtain the touch data;
and determining the micro-motion data sequence according to the myoelectricity data and the touch data.
Optionally, the preprocessing the initial myoelectric signal to obtain the myoelectric data includes:
performing high-pass filtering and signal enhancement processing on the initial electromyographic signals to obtain enhanced electromyographic signals;
dividing the enhanced electromyographic signals into a plurality of signal windows according to preset dividing step length and signal window length; wherein each of the signal windows serves as one of the myoelectric data.
Optionally, the preprocessing the touch video to obtain the touch data includes:
performing filtering processing and denoising processing on each video frame of the touch video to obtain an enhanced touch video;
And adjusting the image size of each video frame of the enhanced touch video according to the preset standard image size to obtain the touch data.
Optionally, the step of determining the stimulation detection result sequence corresponding to the micro-action data sequence based on the stimulation detection model includes:
Inputting the micro-action data sequence into the stimulation detection model so that the stimulation detection model can extract a characteristic sequence according to the micro-action data sequence and determine each stimulation detection result according to the characteristic sequence;
And obtaining the stimulation detection result sequence output by the stimulation detection model.
As a second aspect of the present application, there is provided an electronic apparatus, wherein the electronic apparatus includes:
One or more processors;
a memory having one or more computer programs stored thereon, which when executed by the one or more processors cause the one or more processors to implement the micro-action based cognitive level assessment method of the first aspect of the present application.
As a third aspect of the present application, there is provided a computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the micro-action based cognitive level assessment method according to the first aspect of the present application.
In the cognitive level evaluation method based on micro-actions, which is provided by the embodiment of the application, a micro-action data sequence of an object to be evaluated in a preset stimulation mode is obtained by providing the preset stimulation mode; the types of micro-action data comprise myoelectricity data and touch data, so that hand muscle movements of an estimated object can be comprehensively reflected; training an initial detection model by taking a micro-action data sequence of a healthy tested object in a preset stimulation mode as training data to obtain a stimulation detection model, determining a stimulation detection result sequence corresponding to the micro-action data sequence based on the stimulation detection model, and determining a stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode; the stimulation reference result and the stimulation detection result both comprise information for representing whether to receive stimulation and information for representing the stimulation type, and according to the stimulation reference result sequence and the stimulation detection result sequence, the hand muscle movement of a healthy subject in a preset stimulation mode can be referred to, and the hand muscle movement of the subject to be evaluated in the same stimulation mode can be identified and evaluated, so that the cognitive level evaluation result of the subject to be evaluated can be determined. The method can avoid subjectivity of manual evaluation by using a cognitive scale, is suitable for patients with intracranial implanted metals, sensitively, accurately and rapidly obtains the evaluation result of the cognitive level of the evaluated object, and can also provide accurate data support for subsequent identification of etiology so as to provide cognitive rehabilitation treatment.
Drawings
The application is further described below with reference to the accompanying drawings:
FIG. 1 is a flow chart of one implementation of a micro-action based cognitive level assessment method provided by an embodiment of the present application;
FIG. 2 is a flow chart of another implementation of a micro-action based cognitive level assessment method provided by an embodiment of the present application;
FIG. 3 is a flow chart of another implementation of a micro-action based cognitive level assessment method provided by an embodiment of the present application;
FIG. 4 is a flow chart of another implementation of a micro-action based cognitive level assessment method provided by an embodiment of the present application;
FIG. 5a is a schematic diagram of an evaluation scenario provided by an embodiment of the present application;
FIG. 5b is a schematic diagram of a tactile sensor;
FIG. 6 is a block diagram of an embodiment of an electronic device provided by an embodiment of the present application;
FIG. 7 is a block diagram of a computer readable medium according to an embodiment of the present application.
Description of the reference numerals
101: Processor 102: memory device
103: I/O interface 104: bus line
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The examples in the embodiments are intended to illustrate the present application and are not to be construed as limiting the present application.
Reference in the specification to "one embodiment" or "an example" means that a particular feature, structure, or characteristic described in connection with the embodiment itself can be included in at least one embodiment of the disclosure. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment.
The traditional cognitive level assessment means generally have the problems of narrow audience surface, low accuracy and the like. One current common means of cognitive level assessment is a cognitive scale, such as the montreal cognitive assessment scale (montreal cognitive assessment, moCA), the simple mental state examination scale (min-MENTALSTATE EXAMINATSION, MMSE), and the like. Most of the cognitive scales are other evaluation scales, namely, the cognitive scales are needed to be used by professional medical evaluators, so that the requirements on knowledge storage and medical experience of the medical evaluators are very high, and the cognitive scales have the defects that the number of the medical evaluators is limited, the number of cognitive impairment patients is in an ascending trend, the patients are easy to stress at the positions of the patients and the medical evaluators, and the like, so that some conscious patients are easy to misdiagnose as unconscious patients, the labor cost is high, and the like. In addition, there are other cognitive level assessment means such as electroencephalogram (electroencephalogram, EEG) and nuclear magnetic resonance technology (Nuclear magnetic resonance, NMR), but these cognitive level assessment means have drawbacks such as narrow audience surface due to serious deformation of the skull, limited acquisition of signals by intracranial implantation of metals, EEG, NMR and the like after serious brain injury or after bone flap decompression surgery. Thus, there is a need to find new means for detecting cognitive levels in patients that are widely available and accurate.
In view of this, the inventors of the present application have proposed that conventional cognitive level assessment means are generally lack of objectivity to the assessment performer by visual assessment, relying on subjective experience, and meanwhile, since the patient usually has serious brain injury, the motor function is often damaged, so that only weak and transient behavioral response may occur to external stimulus, and visual observation is easy to ignore. The micro-motions are small-amplitude and short-lived motions which cannot be perceived by naked eyes of a person, real psychological activities of the person can be reflected, hidden hand muscle motions which cannot be observed by naked eyes can be identified by acquiring micro-motion data such as myoelectricity data and touch data of an estimated object in a preset stimulation mode, and the cognitive level of the patient can be accurately estimated based on the stimulation mode of the preset neuropsychological paradigm.
As shown in fig. 1, an embodiment of the present application provides a method for evaluating cognitive level based on micro-actions, where the method may include:
in step S110, a micro-motion data sequence of the evaluated object in a preset stimulation mode is obtained; the micro-action data comprises myoelectricity data and touch data;
In step S120, a stimulation reference result sequence corresponding to the micro-action data sequence is determined according to the preset stimulation mode, and a stimulation detection result sequence corresponding to the micro-action data sequence is determined based on a stimulation detection model; the stimulation detection model is obtained by training an initial detection model in advance by utilizing a micro-action data sequence of a healthy tested object in a preset stimulation mode;
In step S130, determining a cognitive level evaluation result of the evaluated object according to the stimulation reference result sequence and the stimulation detection result sequence; wherein the stimulation reference result and the stimulation detection result each comprise information for representing whether a stimulation is received or not and information for representing a stimulation type.
The stimulus detection model and the initial detection model may include any supervised learning method, and the training is performed on the initial detection model to obtain a trained stimulus detection model by acquiring a large number of micro-motion data sequences of a large number of healthy subjects in a preset stimulus mode in advance and labeling the large number of micro-motion data sequences with respect to target stimulus detection results respectively.
In the cognitive level evaluation method based on micro-actions, which is provided by the embodiment of the application, a micro-action data sequence of an object to be evaluated in a preset stimulation mode is obtained by providing the preset stimulation mode; the types of micro-action data comprise myoelectricity data and touch data, so that hand muscle movements of an estimated object can be comprehensively reflected; training an initial detection model by taking a micro-action data sequence of a healthy tested object in a preset stimulation mode as training data to obtain a stimulation detection model, determining a stimulation detection result sequence corresponding to the micro-action data sequence based on the stimulation detection model, and determining a stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode; the stimulation reference result and the stimulation detection result both comprise information for representing whether to receive stimulation and information for representing the stimulation type, and according to the stimulation reference result sequence and the stimulation detection result sequence, the manual muscle movement of a healthy subject in a preset stimulation mode can be referred to, and the manual muscle movement of the assessed subject in the same stimulation mode can be identified and assessed, so that the cognitive level assessment result of the assessed subject is determined. The method can avoid subjectivity of manual evaluation by using a cognitive scale, is suitable for patients with intracranial implanted metals, sensitively, accurately and rapidly obtains the evaluation result of the cognitive level of the evaluated object, and can also provide accurate data support for subsequent identification of etiology so as to provide cognitive rehabilitation treatment.
The inventors of the present application propose that the more the cognitive level of the subject to be evaluated deviates from the cognitive level of a healthy subject, the more the stimulus detection result sequence will deviate from the stimulus reference result sequence, and therefore, by calculating the degree of matching between the stimulus reference result sequence and the stimulus detection result sequence, the degree of deviation of the cognitive level of the subject to be evaluated from the cognitive level of a healthy subject can be reflected using the degree of matching.
Accordingly, in some embodiments, as shown in fig. 2, the determining the cognitive level evaluation result (i.e. related to step S130) of the evaluated object according to the stimulus reference result sequence and the stimulus detection result sequence may include:
In step S210, a degree of matching between the stimulation reference result sequence and the stimulation detection result sequence is calculated;
in step S220, determining that the cognitive level evaluation result of the evaluated object is a plant state VS level when the matching degree is smaller than a first preset threshold;
In step S230, determining that the cognitive level evaluation result of the evaluated object is the minimum consciousness state MCS level, if the matching degree is not less than the first preset threshold and is less than the second preset threshold;
in step S240, if the matching degree is not less than the second preset threshold, it is determined that the cognitive level evaluation result of the evaluated object is the EMCS level deviating from the minimum consciousness state.
It can be understood that the number of the stimulus reference results in the stimulus reference result sequence and the stimulus detection results in the stimulus detection result sequence are consistent and correspond to each other, and the matching degree between the stimulus reference result sequence and the stimulus detection result sequence can be calculated by corresponding the stimulus reference results and the stimulus detection results one by one, for example, by the following means: degree of matching= (number of successful matches of stimulation reference results to stimulation detection results/total number of stimulation reference results) ×100%.
The first preset threshold and the second preset threshold are not particularly limited, and can be obtained through a large amount of clinical test data statistics, or can be set according to clinical experience of medical evaluation personnel (for example, 5% and 10% respectively).
The stimulation reference result and the stimulation detection result both comprise information for representing whether the stimulation is received or not and information for representing the stimulation type, and when the stimulation reference result is matched with the stimulation detection result, the information for representing whether the stimulation is received or not and the information for representing the stimulation type are matched.
Accordingly, in some embodiments, in the step of calculating the matching degree between the stimulation reference result sequence and the stimulation detection result sequence (i.e. in step S210), it may include: and judging that the stimulation reference result is matched with the stimulation reference result under the condition that the information used for representing whether the stimulation is received in the stimulation reference result is matched with the information used for representing whether the stimulation is received in the stimulation detection result and the information used for representing the stimulation type in the stimulation reference result is matched with the information used for representing the stimulation type in the stimulation detection result.
The inventor of the present application proposes that, in the conventional cognitive level evaluation means, for an object to be evaluated, a single-vision or single-hearing stimulation mode is generally adopted, so that the hand-brain sensing environment is insufficient, and the sufficient hand-brain sensing environment can be provided by providing a stimulation mode of a preset neuropsychological paradigm, so that the acquired micro-motion data can fully reflect the hand-brain sensing condition of the object to be evaluated.
Accordingly, in some embodiments, the preset stimulation patterns include correspondence between different preset stimulation states and time, the different preset stimulation states including a no-stimulation state and a stimulated state, the stimulated state including multiple pain stimulation types, multiple visual stimulation types, and multiple auditory stimulation types;
as shown in fig. 3, the determining, according to the preset stimulation manner, a stimulation reference result sequence corresponding to the micro-action data sequence (i.e. referred to in step S120) may include:
in step S310, according to the data acquisition time corresponding to each micro-action data, inquiring the preset stimulation mode, and determining the preset stimulation state corresponding to each micro-action data;
In step S320, according to the preset stimulation state corresponding to each micro-motion data, a stimulation reference result corresponding to each micro-motion data is determined, and the stimulation reference result sequence is obtained.
Wherein, the non-stimulated state refers to a resting state. The pain stimulus state may be provided by performing operations such as pinching and pressing on the subject to be evaluated by a preset pain stimulus device, that is, pinching and pressing may be performed on different pain stimulus types, and may, of course, be provided by an operator evaluating the cognitive level, which is not particularly limited in the embodiment of the present application. The plurality of visual stimulus types and the plurality of auditory stimulus types may then be provided by an electronic device, a display, and a noise reduction headset.
When different visual pattern materials such as "please open hands", "please open doors" are displayed to an evaluated object, stimulus states of different visual stimulus types are provided, and when auditory pattern materials such as "please open hands", "please open doors" are played to the evaluated object, stimulus states of different auditory stimulus types are provided by using the electronic device and the noise reduction earphone. Of course, the instructions of "please open the hand", "please hold the fist", "please hold the hand", etc., are only executed by the subject to be evaluated, and belong to the passive exercise instructions, the instructions of "please catch the ball", "please open the door", "please turn the steering wheel", etc., and the subject to be evaluated also needs to think, and belong to the active exercise instructions.
When providing the stimulated states of different visual stimulus types and different auditory stimulus types, the duration and interval duration of each visual pattern material, the speech rate of each auditory pattern material, the duration and interval duration, and the like are not particularly limited, and may be set as follows: when the visual pattern materials such as "please open the hand", "please make a fist", "please hold the hand" are displayed, each visual pattern material lasts for 10 seconds, 10 seconds at intervals, and 5 times, and when the audible pattern materials such as "please catch the ball", "please open the door", "please turn the steering wheel", "please retract the hand" are played, each audible pattern material has a speech rate of 3 seconds, 10 seconds at intervals, 10 seconds, and 5 times at intervals.
The hand brain perception refers to the generation of various sensory information (sensation, proprioception and compound sensation) under the stimulation of the external environment, and the information is transmitted to a specific central brain region through corresponding transmission channels, analyzed, integrated and processed, then the processed information is transmitted to an external Zhou Xiaoying device such as musculoskeletal device, and the processed information is displayed through the movement modes of hand muscles and bones. In the afferent of multi-channel sensory perception, multi-modal sensations and perception are generated. The hand-brain sensing environment refers to a visual environment visualized or masked by means of a stimulating tool or accessible rehabilitation regimen, auditory environment, analysis of sensory environment and signals by a large number of different types of sensory neurons in the brain, followed by selective performance of hand-sensory and motor tasks. By providing a stimulated state with multiple pain stimulus types, multiple visual stimulus types, and multiple auditory stimulus types, multiple pain stimulus types, multiple visual stimulus types, and multiple auditory stimulus types.
The preset stimulation mode comprises corresponding relations between different preset stimulation states and time, namely rules for providing different preset stimulation states according to time are preset, the micro-motion corresponds to data acquisition time, and according to the data acquisition time and the corresponding relations, the specific type of stimulation under which each micro-motion data is acquired and processed can be determined one by one, so that a stimulation reference result corresponding to each micro-motion data is determined.
In some embodiments, as shown in fig. 4, the acquiring the micro-action data sequence of the subject under the preset stimulus mode (i.e. step S110) may include:
in step S410, acquiring an initial myoelectric signal of the evaluated object in a preset stimulation mode through a preset myoelectric arm ring; the touch video of the hand of the evaluated object in contact with the flexible material layer in a preset stimulation mode is acquired through a preset touch sensor;
In step S420, the initial myoelectric signal is preprocessed to obtain the myoelectric data; preprocessing the touch video to obtain the touch data;
In step S430, the micro-motion data sequence is determined according to each myoelectricity data and each touch data.
As shown in fig. 5a, a display connected to an electronic device is used to display visual pattern materials to an object to be evaluated to provide stimulated states of different visual stimulus types, a noise reduction earphone connected to the electronic device is used to play auditory pattern materials to the object to be evaluated to provide stimulated states of different auditory stimulus types, an electromyographic arm ring is placed on an arm of the object to be evaluated to collect initial electromyographic signals, and a hand of the object to be evaluated is placed on a touch sensor to collect touch videos.
The myoelectric arm ring is not particularly limited in the embodiment of the application, for example, the myoelectric arm ring can be a gForce myoelectric arm ring designed and manufactured by OYMotion company, 8 high-sensitivity myoelectric sensors are embedded on the myoelectric arm ring, each myoelectric sensor is provided with three stainless steel dry electrodes, a reference electrode is arranged in the middle, a pair of differential pairs are arranged on two sides, and in addition, 9-axis IMU motion sensors are also embedded on the gForce myoelectric arm ring. And the gForce myoelectric arm ring is in communication connection with the electronic equipment through the Bluetooth module, and when the gForce myoelectric arm ring is used, a button on the gForce myoelectric arm ring is pressed for a long time until a green indicator lamp is lighted, so that the arm ring is ready for Bluetooth connection.
The embodiment of the application is not particularly limited, and for example, as shown in fig. 5b, the touch sensor may be composed of a uniform reflection film, a high-density tracking array (i.e., a uniform reflection layer), a 00-30 flexible silica gel layer (i.e., a flexible sensing layer), a transparent high-strength acrylic substrate (i.e., a transparent supporting substrate), an annular LED adjustable light field (i.e., a light source), a modularized adjustable bracket, a lightweight optimization device base, a high-definition camera (i.e., a camera) and the like. After the touch sensor is connected with the electronic equipment, the touch sensor captures three-dimensional deformation of the flexible sensing layer in contact with the target object by using a camera, and rebuilds the morphology and force distribution information of the contact surface by using imaging differences under illumination in different directions, so that the touch sensor has the advantages of high sensing density, stability, reliability, mature algorithm, low cost, easiness in integration and miniaturization and the like.
The initial electromyographic signals acquired by the electromyographic arm ring may contain noise and electrode motion artifacts. Electrode motion artifacts may result from skin deformation under surface electrode areas or perturbation of electrode charge layers. In addition, the initial electromyographic signals are continuously acquired, and data segmentation is also needed. Accordingly, in some embodiments, the preprocessing the initial myoelectric signal to obtain the myoelectric data (i.e. related to step S420) may include:
performing high-pass filtering and signal enhancement processing on the initial electromyographic signals to obtain enhanced electromyographic signals;
dividing the enhanced electromyographic signals into a plurality of signal windows according to preset dividing step length and signal window length; wherein each of the signal windows serves as one of the myoelectric data.
The high-pass filtering process can improve the quality of the initial electromyographic signals, and perform baseline drift removal and the like on the initial electromyographic signals. The initial electromyographic signal may be high pass filtered using a high pass filter, and it should be noted that the power density of the electrode motion artifact is less than 20Hz, and the turning frequency of the high pass filter should be between 10Hz and 20Hz, but not greater than 20Hz, which would otherwise result in the loss of energy from the initial electromyographic signal.
In the embodiment of the application, the enhanced electromyographic signal can be divided into a plurality of signal windows, and the sum of the signal window length and the data processing time length is limited by the real-time requirement and does not exceed 300ms. According to the difference of the dividing step length, the two dividing modes of the adjacent window (adjacent windowing) and the overlapped window (overlapped windowing) can be divided, wherein the dividing step length of the adjacent window dividing mode is equal to the window length of the signal window, and the dividing step length of the overlapped window dividing mode is smaller than the window length of the signal window.
As described above, the stimulus detection model is obtained by training the initial detection model with the micro-motion data sequence of the healthy subject in the preset stimulus mode in advance, and the principle is the same when obtaining the micro-motion data sequence of the healthy subject in the preset stimulus mode as compared with obtaining the micro-motion data sequence of the evaluated subject in the preset stimulus mode.
The embodiment of the application does not limit the specific use of the adjacent window segmentation mode or the overlapping window segmentation mode, and as an alternative implementation mode, the overlapping window segmentation mode can be used because the smaller the segmentation step length is, the denser the data features are and the performance of the model is improved. Each signal window obtained through data segmentation is a sample, namely myoelectricity data, one myoelectricity data or one touch data is used as micro-action data, and the stimulation detection model can give a stimulation detection result based on the micro-action data.
The touch data collected by the touch sensor also has noise, and needs to be preprocessed. Accordingly, in some embodiments, the preprocessing the touch video to obtain the touch data (i.e. referred to in step S420) may include:
performing filtering processing and denoising processing on each video frame of the touch video to obtain an enhanced touch video;
And adjusting the image size of each video frame of the enhanced touch video according to the preset standard image size to obtain the touch data.
The embodiment of the present application is not particularly limited to the preset standard image size, and for example, a conventionally used image size may be used as the standard image size.
The quality of touch data can be ensured through filtering and denoising, and the consistency and unified analysis of the touch data can be ensured by adjusting the image size of each video frame of the enhanced touch video according to the preset standard image size. In addition, the preprocessing process may include other processes such as frame extraction to de-duplicate a large number of video frames.
In some embodiments, in the step of determining the stimulus detection result sequence corresponding to the micro-action data sequence based on the stimulus detection model (i.e. in step S120), the method may include:
Inputting the micro-action data sequence into the stimulation detection model so that the stimulation detection model can extract a characteristic sequence according to the micro-action data sequence and determine each stimulation detection result according to the characteristic sequence;
And obtaining the stimulation detection result sequence output by the stimulation detection model.
The stimulation detection model may include myoelectric features and touch features according to the feature sequence extracted from the micro-motion data sequence, the myoelectric features may include amplitude features, time domain features, frequency domain features, and the like, the amplitude features refer to whether obvious muscle point peaks exist in myoelectric data, the time domain features refer to frequency changes detected by researching frequency components of signals through fourier transformation or power spectral density analysis, the frequency domain features refer to time domain parameters such as mean values, standard deviations, peaks and the like of the calculated myoelectric data, the frequency domain features are more capable of stably representing an action mode when dynamics changes than the time domain features, and the time domain features are more capable of having higher time resolution than the frequency domain features. The touch features may include shape features, i.e., information of the shape, edges, contours of the identified object, texture features, i.e., information of the texture and characteristics of the object surface, dynamic features, i.e., gestures detected from changes in touch data over time, etc.
Two different sub-models can also be used in the stimulus detection model to extract myoelectric features from myoelectric data and touch features from touch data, respectively. The two different sub-models are not particularly limited in the embodiment of the present application, for example, the sub-model used to extract the touch feature from the touch data may be a convolutional neural network model ((Convolutional Neural Networks, CNN) or a more advanced and complex time sequence model such as a time-shift-based efficient video understanding model (Temporal Shift Module for Efficient Video Understanding, TSM), etc., and the sub-model used to extract the myoelectric feature from the myoelectric data may be a gaussian mixture model, a hidden markov model, an artificial neural network, a support vector machine, etc., classifier model.
As a second aspect of the embodiment of the present application, there is provided an electronic device, wherein, as shown in fig. 6, the electronic device includes:
one or more processors 101;
A memory 102 having one or more computer programs stored thereon, which when executed by the one or more processors 101, cause the one or more processors 101 to implement the micro-action based cognitive level assessment method provided by the first aspect of the embodiments of the present application.
The electronic device may also include one or more I/O interfaces 103 coupled between the processor 101 and the memory 102 configured to enable information interaction of the processor 101 with the memory 102.
Wherein the processor 101 is a device having data processing capabilities, including but not limited to a Central Processing Unit (CPU) or the like; memory 102 is a device with data storage capability including, but not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically charged erasable programmable read-only memory (EEPROM), FLASH memory (FLASH); an I/O interface (read/write interface) is connected between the processor and the memory, and can implement information interaction between the processor and the memory, which includes, but is not limited to, a data Bus (Bus), and the like.
In some embodiments, processor 101, memory 102, and I/O interface 103 are connected to each other via bus 104, and thus to other components of the computing device.
As a third aspect of the embodiment of the present application, as shown in fig. 7, there is provided a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the micro-action based cognitive level assessment method provided by the first aspect of the embodiment of the present application.
Those skilled in the art will appreciate that implementing all or part of the processes in the methods of the embodiments described above may be accomplished by computer programs to instruct related hardware. Accordingly, the computer program may be stored in a non-volatile computer readable storage medium, which when executed, performs the method of any of the above embodiments. Any reference to memory, storage, database, or other medium used in embodiments of the application may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The above is only a specific embodiment of the present application, but the scope of the present application is not limited thereto, and it should be understood by those skilled in the art that the present application includes but is not limited to the accompanying drawings and the description of the above specific embodiment. Any modifications which do not depart from the functional and structural principles of the present application are intended to be included within the scope of the appended claims.
Claims (10)
1. A method of micro-action based cognitive level assessment, the method comprising:
acquiring a micro-action data sequence of an evaluated object in a preset stimulation mode; the micro-action data comprises myoelectricity data and touch data;
Determining a stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode, and determining a stimulation detection result sequence corresponding to the micro-action data sequence based on a stimulation detection model; the stimulation detection model is obtained by training an initial detection model in advance by utilizing a micro-action data sequence of a healthy tested object in a preset stimulation mode;
determining a cognitive level evaluation result of the evaluated object according to the stimulation reference result sequence and the stimulation detection result sequence; wherein the stimulation reference result and the stimulation detection result each comprise information for representing whether a stimulation is received or not and information for representing a stimulation type.
2. The method of claim 1, wherein the determining the cognitive level assessment result of the subject based on the stimulation benchmark result sequence and the stimulation test result sequence comprises:
Calculating the matching degree between the stimulation reference result sequence and the stimulation detection result sequence;
under the condition that the matching degree is smaller than a first preset threshold value, determining that the cognitive level evaluation result of the evaluated object is a plant state VS level;
determining that the cognitive level evaluation result of the evaluated object is the minimum consciousness state MCS level under the condition that the matching degree is not smaller than the first preset threshold value and smaller than a second preset threshold value;
And under the condition that the matching degree is not smaller than the second preset threshold value, determining that the cognitive level evaluation result of the evaluated object is the EMCS level which is out of the minimum consciousness state.
3. The method according to claim 2, wherein in the step of calculating the degree of matching between the stimulation reference result sequence and the stimulation test result sequence, it comprises:
And judging that the stimulation reference result is matched with the stimulation reference result under the condition that the information used for representing whether the stimulation is received in the stimulation reference result is matched with the information used for representing whether the stimulation is received in the stimulation detection result and the information used for representing the stimulation type in the stimulation reference result is matched with the information used for representing the stimulation type in the stimulation detection result.
4. A method according to any one of claims 1-3, wherein the preset stimulation patterns comprise correspondence between different preset stimulation states and time, the different preset stimulation states comprising a no-stimulation state and a stimulated state, the stimulated state comprising a plurality of pain stimulation types, a plurality of visual stimulation types, and a plurality of auditory stimulation types;
The determining the stimulation reference result sequence corresponding to the micro-action data sequence according to the preset stimulation mode comprises the following steps:
Inquiring the preset stimulation mode according to the data acquisition time corresponding to each micro-action data, and determining the preset stimulation state corresponding to each micro-action data;
And determining a stimulation reference result corresponding to each micro-action data according to the preset stimulation state corresponding to each micro-action data, and obtaining the stimulation reference result sequence.
5. A method according to any one of claims 1-3, wherein the acquiring of the micro-action data sequence of the subject under evaluation under the preset stimulus regime comprises:
Acquiring an initial myoelectric signal of an evaluated object in a preset stimulation mode through a preset myoelectric arm ring; the touch video of the hand of the evaluated object in contact with the flexible material layer in a preset stimulation mode is acquired through a preset touch sensor;
Preprocessing the initial myoelectric signal to obtain myoelectric data; preprocessing the touch video to obtain the touch data;
and determining the micro-motion data sequence according to the myoelectricity data and the touch data.
6. The method of claim 5, wherein the preprocessing the initial myoelectric signal to obtain the myoelectric data comprises:
performing high-pass filtering and signal enhancement processing on the initial electromyographic signals to obtain enhanced electromyographic signals;
dividing the enhanced electromyographic signals into a plurality of signal windows according to preset dividing step length and signal window length; wherein each of the signal windows serves as one of the myoelectric data.
7. The method of claim 5, wherein the preprocessing the touch video to obtain the touch data comprises:
performing filtering processing and denoising processing on each video frame of the touch video to obtain an enhanced touch video;
And adjusting the image size of each video frame of the enhanced touch video according to the preset standard image size to obtain the touch data.
8. A method according to any one of claims 1-3, wherein in the step of determining a stimulation test result sequence corresponding to the micro-action data sequence based on a stimulation test model, it comprises:
Inputting the micro-action data sequence into the stimulation detection model so that the stimulation detection model can extract a characteristic sequence according to the micro-action data sequence and determine each stimulation detection result according to the characteristic sequence;
And obtaining the stimulation detection result sequence output by the stimulation detection model.
9. An electronic device, the electronic device comprising:
One or more processors;
Memory having one or more computer programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the micro-action based cognitive level assessment method of any of claims 1-8.
10. A computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a micro-action based cognitive level assessment method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410435275.1A CN118021307A (en) | 2024-04-11 | 2024-04-11 | Micro-action-based cognitive level assessment method, electronic device and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410435275.1A CN118021307A (en) | 2024-04-11 | 2024-04-11 | Micro-action-based cognitive level assessment method, electronic device and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118021307A true CN118021307A (en) | 2024-05-14 |
Family
ID=90989920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410435275.1A Pending CN118021307A (en) | 2024-04-11 | 2024-04-11 | Micro-action-based cognitive level assessment method, electronic device and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118021307A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145372A1 (en) * | 2015-03-12 | 2016-09-15 | Akili Interactive Labs, Inc. | Processor implemented systems and methods for measuring congnitive abilities |
| US20190159715A1 (en) * | 2016-08-05 | 2019-05-30 | The Regents Of The University Of California | Methods of cognitive fitness detection and training and systems for practicing the same |
| CN112201343A (en) * | 2020-09-29 | 2021-01-08 | 浙江大学 | Cognitive state recognition system and method based on facial micro-expression |
| CN113712572A (en) * | 2020-11-25 | 2021-11-30 | 北京未名脑脑科技有限公司 | System and method for assessing cognitive function |
| CN116386862A (en) * | 2023-02-10 | 2023-07-04 | 平安科技（深圳）有限公司 | Multi-modal cognitive impairment evaluation method, device, equipment and storage medium |
-
2024
- 2024-04-11 CN CN202410435275.1A patent/CN118021307A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145372A1 (en) * | 2015-03-12 | 2016-09-15 | Akili Interactive Labs, Inc. | Processor implemented systems and methods for measuring congnitive abilities |
| US20190159715A1 (en) * | 2016-08-05 | 2019-05-30 | The Regents Of The University Of California | Methods of cognitive fitness detection and training and systems for practicing the same |
| CN112201343A (en) * | 2020-09-29 | 2021-01-08 | 浙江大学 | Cognitive state recognition system and method based on facial micro-expression |
| CN113712572A (en) * | 2020-11-25 | 2021-11-30 | 北京未名脑脑科技有限公司 | System and method for assessing cognitive function |
| CN116386862A (en) * | 2023-02-10 | 2023-07-04 | 平安科技（深圳）有限公司 | Multi-modal cognitive impairment evaluation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109157231B (en) | Portable multichannel depression tendency evaluation system based on emotional stimulation task | |
| Khare et al. | PDCNNet: An automatic framework for the detection of Parkinson’s disease using EEG signals | |
| KR101703547B1 (en) | Method and apparatus for estimating effective channel of functional near-infrared spectroscopy | |
| JP6124140B2 (en) | Assessment of patient cognitive function | |
| US20160029965A1 (en) | Artifact as a feature in neuro diagnostics | |
| US11116437B2 (en) | Scoring method based on improved signals analysis | |
| US20190343457A1 (en) | Pain assessment method and apparatus for patients unable to self-report pain | |
| WO2016004117A1 (en) | System and signatures for a multi-modal physiological periodic biomarker assessment | |
| JP3581319B2 (en) | Brain activity automatic judgment device | |
| JP2016501056A (en) | System and method for evaluation of neuropathology | |
| Luca et al. | Detecting rare events using extreme value statistics applied to epileptic convulsions in children | |
| Jacob et al. | Towards defining biomarkers to evaluate concussions using virtual reality and a moving platform (BioVRSea) | |
| US20170032098A1 (en) | Stochastic oscillator analysis in neuro diagnositcs | |
| CN115054250B (en) | Mirror image overflow motion detection and analysis method and system | |
| Paisarnsrisomsuk et al. | Deep Sleep: Convolutional neural networks for predictive modeling of human sleep time-signals | |
| CN115299947A (en) | Psychological scale confidence evaluation method and system based on multi-modal physiological data | |
| Kaur et al. | Using virtual reality to examine the neural and physiological anxiety-related responses to balance-demanding target-reaching leaning tasks | |
| Li et al. | Multi-modal emotion recognition based on deep learning of EEG and audio signals | |
| Ahamad | System architecture for brain-computer interface based on machine learning and internet of things | |
| Adem et al. | Classification of Parkinson's disease using EMG signals from different upper limb movements based on multiclass support vector machine | |
| CN116186502B (en) | Multi-mode visual nerve function detection method and system thereof | |
| CN112674760A (en) | Wearable sensor-based Parkinson upper limb movement detection method | |
| Özel et al. | Implementation of Artifact Removal Algorithms in Gait Signals for Diagnosis of Parkinson Disease. | |
| CN113812964B (en) | Proxy measurement and pseudo-multimode frozen gait detection method and device for electroencephalogram characteristics | |
| Chen et al. | An interpretable deep learning optimized wearable daily detection system for Parkinson’s disease |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |