WO2023135444A1

WO2023135444A1 - Medication therapy analysis system, methods for determining medication therapy plan recommendations, and related methods and systems

Info

Publication number: WO2023135444A1
Application number: PCT/IB2022/050209
Authority: WO
Inventors: Keisuke TENDA
Original assignee: Mitsui & Co.
Priority date: 2022-01-12
Filing date: 2022-01-12
Publication date: 2023-07-20

Abstract

Methods of analyzing health event data include receiving health event data indicating the occurrence of absence of a seizure event, providing the health event data to a medication therapy analysis system, receiving an indication of a medication therapy plan recommendation, the medication therapy plan recommendation being based at least partially on the health event data, and providing the indication of the medication therapy plan recommendation to a user.

Description

MEDICATION THERAPY ANALYSIS SYSTEM, METHODS FOR DETERMINING MEDICATION THERAPY PLAN RECOMMENDATIONS, AND RELATED METHODS AND SYSTEMS

TECHNICAL FIELD

This disclosure relates generally to a medication therapy analysis system for determining recommendations for medication dosage adjustment based on medication concentration levels and behavioral and environmental triggers.

BACKGROUND

Therapeutic drug monitoring (TDM) often involves measuring a concentration of specific drugs in a patient’s bloodstream to ensure that a blood medication concentration level is appropriate for the individual patient. TDM is important because certain drugs exhibit pronounced intra- or inter-individual variability in pharmacokinetics and pharmacodynamics. Conventional TDM is performed by drawing blood samples immediately before an administration of a dosage of the drug whereupon the samples are shipped to an external laboratory, if the drug administrator does not have its own testing facility. Several days or weeks later, when the lab results are available, a provider must provide drug dosage recommendations to the patient. Therefore, conventional TDM often does not achieve successful therapeutic outcomes due to limited and insufficient data with delayed results. Additionally, conventional TDM methods are limited due to laboratory variability in reporting the blood drug level, the requirement of specialized equipment with skilled staff for TDM, and limited time for providers to completely and accurately analyze the results.

DISCLOSURE

The various embodiments described below provide benefits and/or solve one or more of the foregoing or other problems in the art with systems and methods for determining medication recommendations for a user. Some embodiments of the present disclosure include a method of receiving health event data indicating the occurrence or absence of a seizure event, providing the health event data to a medication therapy analysis system, receiving an indication of a medication therapy plan recommendation, the medication therapy plan recommendation being based at least partially on the health event data, and providing the indication of the medication therapy plan recommendation to a user.

Some embodiments of the present disclosure include a medication therapy analysis system. The system may include at least one processor and at least one non- transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the medication therapy analysis system to receive health event data from a mobile device, the health event data indicating a health event of a user receiving a medication therapy, determine a medication level of the user at the time of the health event based at least partially on the health event data, responsive to determining that the medication level is within a target range, determine an adjusted target range, responsive to determining that the medication level is not within the target range, determine and provide at least one of the following recommendations to the mobile device: a recommendation to increase or decrease a dosage of a medication of the medication therapy, a recommendation for a lifestyle behavior change, and a recommendation to change to a different type of medication for the medication therapy.

One or more embodiments of the present disclosure include a non-transitory computer-readable medium storing instructions thereon that, when executed by at least one processor, cause the at least one processor to perform steps including receiving health event data from one or more devices, at least a portion of the health event data indicating the occurrence or absence of a seizure event of a user, providing the health event data to a medication therapy analysis system on a cloud computing platform, receiving at least one recommendation regarding medication therapy from the medication therapy analysis system, and generating and providing the indication of the at least one recommendation on a user interface for display to the user.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

Various embodiments will be described and explained with additional specificity and detail through the use of the accompanying drawings in which:

FIG. 1 illustrates a schematic diagram of an environment in which a medication therapy analysis system may operate according to one or more embodiments of the present disclosure.

FIG. 2 is a flowchart illustrating a method of managing medication therapy of a user. FIG. 3 is a flowchart illustrating a schematic representation of a process that may be utilized to determine a medication therapy plan recommendation for a user.

FIGS. 4A-4C illustrate an example initialization of target drug levels in accordance with various embodiments of this disclosure.

FIG. 5 is schematic representation of an environment illustrating inputs and outputs of a medication therapy analysis system and an application.

FIGS. 6A-6Q illustrate a collection of user interfaces including features of an application according to one or more embodiments of the present disclosure.

FIG. 7 is a block diagram of an exemplary computing device that may be utilized as a client device and/or a medication therapy analysis system that may be configured to perform one or more of the processes described above.

MODE(S) FOR CARRYING OUT THE INVENTION

The illustrations presented herein are not actual views of any particular medication therapy analysis system, or any component thereof, but are merely idealized representations, which are employed to describe the present disclosure.

As used herein, the singular forms following “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise.

As used herein, the term “may” with respect to a material, structure, feature, function, or method act indicates that such is contemplated for use in implementation of an embodiment of the disclosure, and such term is used in preference to the more restrictive term “is” so as to avoid any implication that other compatible materials, structures, features, functions, and methods usable in combination therewith should or must be excluded.

As used herein, any relational term, such as “first,” “second,” etc., is used for clarity and convenience in understanding the disclosure and accompanying drawings, and does not connote or depend on any specific preference or order, except where the context clearly indicates otherwise.

As used herein, the term “substantially” in reference to a given parameter, property, act, or condition means and includes to a degree that one skilled in the art would understand that the given parameter, property, or condition is met with a small degree of variance, such as within acceptable manufacturing tolerances. By way of example, depending on the particular parameter, property, or condition that is substantially met, the parameter, property, or condition may be at least 90.0% met, at least 95.0% met, at least 99.0% met, or even at least 99.9% met.

As used herein, the term “about” used in reference to a given parameter is inclusive of the stated value and has the meaning dictated by the context (e.g., it includes the degree of error associated with measurement of the given parameter, as well as variations resulting from manufacturing tolerances, etc.).

For the purposes of this disclosure, the terms “drug” and “medication” may be synonymous. Furthermore, “drug level” and “medication concentration level” may be synonymous, both meaning the concentration or amount of a particular drug or medication in one or more of blood of a user, hair, dried blood spots, urine, sweat, saliva, tears, interstitial fluids and tissue biopsies of the user.

“Health event data” refers to data collected by a client device regarding a health event, such as a seizure, seizure aura, side effects of a seizure or a medication, etc. The data collected may include a time and date of the event, behavioral and environmental triggers related to the event, and medication concentration levels before, during, and/or after the event.

“Medication therapy plan” refers to a treatment plan for a user who takes regular doses of medication or drugs to prevent or treat a regularly occurring condition. The medication therapy plan may include dosage amount, dosage timing, diet and exercise recommendations, stress management exercises, etc.

One or more embodiments of the present disclosure include a medication therapy analysis system that receives health event (e.g., seizure or side effects) data related to a user via a client device (e.g., a smartphone) and, after analyzing the health event data, provides a recommendation to the user to adjust a medication or a lifestyle behavior. For example, a user may, daily, record any seizures or side effects that the user experiences in an application on the client device. The user may also take point-of-care measurements of medical concentration levels (e.g., blood medication concentration levels) directly after a seizure and/or at predetermined durations (e.g., on a weekly basis). The client device may then provide the user-recorded data, as well as the medication concentration levels, to the medication therapy analysis system, which analyzes the data and provides recommendations to the client device based on the analysis. In one or more embodiments, the client device may then display the recommendations received from the medication therapy analysis system for the user’s viewing.

Because the medication therapy analysis system of the present disclosure enables a user to easily record health event data and provide the health event data to the medication therapy analysis system, which provides fast and reliable recommendations for a treatment plan adjustment, the medication therapy analysis system is advantageous over conventional medication therapy plan systems. For instance, because the medication therapy analysis system enables a user to receive therapy recommendations while working with a single system instead of multiple providers and/or laboratories (e.g., for testing medication concentration levels), the medication therapy analysis system reduces required processing power, memory, and communication resources needed to facilitate providing therapy recommendations to a user. Accordingly, the medication therapy analysis system results in less data transfer and data bandwidth usage for a computer/communication system. In other words, the medication therapy analysis system results in less required processing power and communication bandwidth in comparison to conventional systems. As a result, the medication therapy analysis system of the present disclosure, in comparison to conventional systems, may be a more appropriate system for mobile devices. Additionally, in view of the foregoing, the medication therapy analysis system may result in a more user-friendly, consistent, attractive, and persuasive method for determining medication adjustment recommendations in comparison to conventional medication therapy analysis systems.

Furthermore, because the medication therapy analysis system of the present disclosure enables a user to quickly and efficiently test medication concentration levels, correlate the medication concentration levels with possible triggers, and receive realtime recommendations for adjustment to a medication therapy plan, the medication therapy analysis system of the present disclosure may provide greater access (e.g., access to the public) for therapeutic drug monitoring and determining medication adjustments. As a result of the improvements described in the present disclosure, a user may not need to visit their provider as often nor does the provider need to take time to personally analyze daily journals of the user, resulting in significant time and cost savings to both the user and the provider.

FIG. 1 illustrates a schematic diagram of an environment 100 in which a medication therapy analysis system may operate according to one or more embodiments of the present disclosure. As illustrated, the environment 100 includes a client device 104, at least one server 110 including a medication therapy analysis system 112, a network 108, and one or more medical device(s) 114. As used herein, the term “medication therapy analysis system” refers to a system that receives and analyzes data related to a medication therapy (e.g., medication prescriptions, antiepileptic/anti-seizure drugs) for a user receiving a particular medication therapy (e.g., a person with epilepsy taking antiepileptic/anti-seizure drugs). The data may include information such as, for example, medical concentration level (e.g., blood medication concentration level), health and lifestyle information, seizure events, etc. related to the user. In some embodiments, one or more functions of the medication therapy analysis system 112 may be substantially performed by a healthcare provider (e.g., a physician, nurse, etc.). In some embodiments, one or more functions of the medication therapy analysis system 112 may be performed by a computing device, such as computing device 702, described more fully below with reference to FIG. 7. In some embodiments, as is described in greater detail below, the medication therapy analysis system 112 may analyze medical concentration levels (e.g., blood medication concentration levels) of a user and other behavioral/environmental factors to determine a recommendation for the user to increase or decrease medication, change a lifestyle behavior, or change a medication type. For instance, the medication therapy analysis system 112 may determine that the user had a seizure while the medication concentration level was too low and may recommend that the dosage for the antiepileptic drug be increased.

In some embodiments, the client device 104 may include an application 106 for recording health and lifestyle data and for facilitating communication between the user 102 and/or client device 104 and medical device(s) 114 and/or the medication therapy analysis system 112. In particular, the client device 104 may execute one or more applications (e.g., application 106) for performing the functions of the various embodiments and processes described herein. For example, in some instances, the application 106 may be a health and lifestyle recording application that allows a user to track and keep records regarding health events and side effects of medication. For example, a user (e.g., user 102) with epilepsy may record in the application 106 each time the user 102 has a seizure along with any possible behavioral triggers that might have caused the seizure. The application 106 may also remind the user 102 (e.g., with push notifications) to measure medication concentration levels (e.g., blood medication concentration levels) after a seizure has occurred. The user 102 may also record symptoms and side effects in the application 106. The application 106 may include data protection measures such as encryption and password or passcode protection to access sensitive information in the application. The application 106 may also include data sharing and remote access to server(s) 110. The data input by the user 102 may be stored at the server(s) 110, and the application 106, as part of the client device 104, may retrieve the stored data anytime the user logs into the application or any other time.

The medication therapy analysis system 112, the client device 104, and/or the medical device(s) 114 may communicate via the network 108. In one or more embodiments, the network 108 includes a combination of cellular or mobile telecommunications networks, a public switched telephone network (PSTN), and/or the Internet or World Wide Web and facilitates the transmission of messages between the client device 104 and the medication therapy analysis system 112. The network 108, however, may include various other types of networks that use various communication technologies and protocols, such as wireless local network (WLAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), other telecommunication networks, or a combination of two or more of the foregoing networks. Although FIG. 1 illustrates a particular arrangement of the client device 104, the server(s) 110, the medical device(s) 114, and the network 108, various additional arrangements are possible. For example, the server(s) 110 and, accordingly, the medication therapy analysis system 112, may directly communication with the client device 104, bypassing the network.

The medical device(s) 114 may also directly communicate with client device 104, bypassing the network 108. The user 102 may also interface directly with medical device(s) 114 (not shown). The medical device(s) 114 may be a point-of-care testing (POCT) device and may also be, without limitation, a medication level monitoring and me asuring/te sting device (e.g., a blood medication level monitoring and me asuring/te sting device), a wearable electromyography (EMG) device, a seizure prediction and/or detection device, a smart watch, a pedometer, a heart rate monitor, a wearable activity tracker, a fitness tracker, a wearable computer, etc. The medical device(s) 114 may automatically communicate information about a health event to the client device 104 and/or the client device 104 may request information from the medical device(s) 114. For example, the medical device(s) 114 could be a seizure detection device which, responsive to detecting a seizure, automatically provides the seizure event information to client device 104, which is then stored using the application 106. Alternatively, the medical device(s) 114 could be a medication concentration measurement device (e.g., a blood medication concentration measurement device). After the user 102 has a health event (e.g., a seizure), the user 102 may request, via the application 106, that the medication concentration measurement device measure the medication concentration. In this instance, the client device 104 may send a request to the medication concentration measurement device which then measures the medication level. The medication concentration measurement device may then provide the results of the measurement to client device 104. The medication concentration measurement, along with other information such as date and time, may then be recorded and stored in memory. In some embodiments, the medical device(s) 114 may measure a medication concentration using hair, dried blood spots, urine, sweat, saliva, tears, interstitial fluids, and tissue biopsies.

The client device 104 may be any one or more of various types of computing devices. For example, the client device 104 may include a mobile device such as a mobile telephone, a smartphone, a PDA, a tablet, a laptop, a smart speaker (e.g., AMAZON ECHO, GOOGLE HOME, APPLE HOMEPOD, etc.) or a non-mobile device such as a desktop computer or another type of computing device. Additional details with respect to the client device 104 are discussed below with respect to FIG. 7.

As illustrated in FIG. 1, a user 102 may interface with the client device 104, for example, to communicate with the server(s) 110 and to utilize the medication therapy analysis system 112 in order to receive recommendations from the medication therapy analysis system 112 and/or from a provider, as how to alter medication or lifestyle behavior to avoid or reduce future health events, such as seizures. The user 102 may be an individual (i.e., human user), a business, a group or any other entity. More specifically, in some embodiments, the user 102 may be a patient receiving treatment under a medication therapy plan. The user 102 may also be a friend and/or relative of the patient, a medical provider of the patient, an insurance company, a pharmaceutical company, a research firm, or any other entity. Although FIG. 1 illustrates only one user 102 associated with the client device 104, the environment 100 may include any number of a plurality of users that each interact with the environment 100 using a corresponding client device. For instance, the medication therapy analysis system 112 may service multiple client devices 104 and users 102.

In some embodiments, the medication therapy analysis system 112 may include one or more systems, servers, and/or other devices for analyzing and determining recommendations for the user 102. The medication therapy analysis system 112 may include and/or have access to one or more databases. For example, in some embodiments, the medication therapy analysis system 112 may be implemented by a plurality of server devices that store, within the one or more databases, user health information and/or facilitate querying any of the foregoing information and content to provide recommendations to the user 102 regarding a medication therapy plan. As discussed in greater detail below, in some embodiments, medication therapy analysis system 112 may keep track of a target range for medication concentration levels (e.g., blood medication concentration levels) in the user 102 and may adjust the target range depending on the health event data that the medication therapy analysis system 112 receives from the client device 104.

FIG. 2 is a flowchart illustrating a method 200 of managing medication therapy of a user. The method 200 may include receiving health event data indicating an occurrence or an absence of a seizure event, as shown in act 202 of FIG. 2. In some embodiments, a client device (e.g., the client device 104) may receive health event data as an input from a user (e.g., user 102) (e.g., user interaction). In other embodiments, the client device 104 may receive health event data from a medical device (e.g., medical device(s) 114). As an example, the input from the user 102 may include recording in the application 106 any symptoms, side effects, seizures, auras, behavioral/environmental triggers, etc. related to the user’s medication therapy. The inputs received by the client device 104 and recorded using the application for recording health and lifestyle data (e.g., application 106) may include a mood of the user 102, diet of the user 102, adherence to medication therapy plan (e.g., taking medication), alcohol consumed by the user 102, sleeping patterns of the user 102, stress levels of the user 102, caffeine intake of the user 102, other drug use of the user 102, exercise patterns of the user 102, time of day when seizure occurred, illness of the user 102, menstruation of the user 102, blood sugar levels of the user 102, travel patterns of the user 102, weather patterns, etc. The user 102 may also record an absence of symptoms, side effects, seizures, and auras. The health event data received from the medical device(s) 114 may include medication concentration measurements (e.g., blood medication concentration measurements), blood sugar (glucose) levels, heartrate/pulse, accelerometer data, gyroscope data, electrocardiogram (EKG/ECG) data, electromyography (EMG) data, blood pressure data, blood oxygen levels, sleeping patterns, body temperature, exercise data, etc.

The method 200 may further include providing the health event data collected to a medication therapy analysis system, such as medication therapy analysis system 112, as shown in act 204 of FIG. 2. The client device 104 may send a communication containing the health event data (e.g., a data package) via the network 108 to the medication therapy analysis system 112. Responsive to receiving the health event data, the medication therapy analysis system 112 may analyze the health event data to determine a medication therapy plan recommendation, as is described in greater detail below in regard to FIG. 3. In other embodiments, a provider (e.g., a medical professional) may analyze the health event data to determine a medication therapy plan recommendation.

The method 200 also includes receiving an indication of a medication therapy plan recommendation, as shown in act 206 of FIG. 2. In some embodiments, the client device 104 receives the indication from the medication therapy analysis system 112, and in other embodiments, the client device 104 receives the indication from a provider, including from a device belonging to the provider. The indication of a medication therapy plan recommendation may include a dosage determination and a recommendation for the user 102 to increase or decrease a dosage of medication, change a type of medication, or maintain the current medication dosage without change. The indication may also include recommendations to alter lifestyle behaviors and/or environment, in connection with the medication dosage determination.

Additionally, the method includes providing the received indication of medication therapy plan recommendation to the user, as shown in act 208 of FIG. 2. In some embodiments, the client device 104 may provide the indication via a graphical user interface (GUI) of the application 106 on a display of the device. In additional embodiments, the client device 104 may provide the indication via an alarm protocol of the client device. In further embodiments, the client device 104 may provide the indication audibly, via vibrations, and/or via haptic methods. Displaying the indication is described in greater detail below in regard to FIGS. 6A-6Q. FIG. 3 is a flowchart illustrating a schematic representation of a process 300 (e.g., one or more algorithms) that may be utilized to determine a medication therapy plan recommendation for a user (e.g., a user 102). In one or more embodiments, the process 300 may be performed by a medication therapy analysis system such as medication therapy analysis system 112 responsive to receiving health event data from client device 104, as described above in regard to FIG. 2. In some embodiments, the process 300 may be implemented using machine learning to learn and improve its effectiveness, as described in further detail below.

In some embodiments, process 300 may begin by deciding whether or not a health event has occurred, as shown in act 302 of FIG. 3. For example, the medication therapy analysis system 112 may analyze the received health event data to determine whether a health event is indicated in the health event data. In one or more embodiments, a health event may be indicated by listing the health event, heart rate, sleep rate, blood levels, etc.

Responsive to a determination that a health event has not occurred, the process 300 may include determining whether a predetermined period of time has passed since a previous health event has occurred, as shown in act 304 of FIG. 3. In one or more embodiments, the period of time may include one month, one week, one day, twelve hours, etc. Responsive to determining that the period of time has passed with no occurrence of a health event, then process 300 includes adjusting and individualizing target drug levels of the user, as shown in act 318 of FIG. 3.

As is described in greater detail herein, and with reference to act 318, the medication therapy analysis system 112 may maintain current target ranges for medication concentration levels (e.g., blood drug levels) of the user. The target ranges may be first developed and determined in an initialization period as described more fully with reference to FIGS. 4A-4C. Once the target ranges are determined, further adjustment may be performed to individualize the treatment of the user 102. The target ranges may include a lower range of medication concentration levels, a range of appropriate medication concentration levels, and a higher range of medication concentration levels. If no event (seizure, aura, or side effect) has occurred for the predetermined period of time, the data regarding the lack of an event from the client device 104 may be analyzed to determine whether the target drug levels of act 318 should be adjusted or not. For example, if no event has occurred for one week, the “appropriate” range (e.g., upper and lower limits) may be broadened to allow for greater variability in the medication concentration level of the user 102.

Responsive to a determination that a health event has occurred, the process 300 includes determining which type of event occurred, as shown in act 306. The two primary types of health events in this exemplary process 300 include 1) seizures or auras and 2) side effects from medication. For the purposes of the discussion regarding FIG. 3, differentiation of seizures and seizure auras will not be made, however, it is understood that separate processes may result from such differentiation. Furthermore, this disclosure is not limited to seizures or epilepsy but the methods described herein may be used for determining recommendations related to other types of health events and conditions including, but not limited to, migraines, narcolepsy, Tourette’s syndrome, convulsive syncope, vertigo, abnormal heart rhythms (arrhythmias), diabetes, etc. Examples of typical side effects from antiepileptic and antiarrhythmic medications may include dizziness, drowsiness, mental slowing, weight gain or loss, metabolic acidosis, nephrolithiasis, angle closure glaucoma, skin rash, hepatotoxicity, colitis, movement and behavioral disorders, tiredness, nausea, shortness of breath, chest pain, headache, swelling of mouth, lips, or tongue, hair loss, unwanted hair growth, agitation, uncontrollable shaking, headache, etc. Again, the type of health event may be determined from the health event data.

Responsive to a determination that a seizure or seizure aura has occurred, the process 300 includes analyzing the health event data to determine whether the medication concentration level is with a target range, as shown in acts 308, 310, and/or 312. In some embodiments, the medication therapy analysis system 112 may analyze the health event data to determine which range the medication concentration level falls into, if any. If the medication concentration level falls within the lower range, process 300 may proceed to act 308. If the medication concentration level falls within an appropriate range, process 300 may proceed to act 310. If the medication concentration level falls within a higher range, process 300 proceeds to act 312.

Responsive to determining that the blood medication concentration level is within a lower range, as indicated by act 308, process 300 may include act 320 including analyzing the health event data and determining whether the user 102 has adhered to the medication therapy plan or if the user 102 has deviated from the plan by failing to take medication as previously directed by a provider or the medication therapy analysis system 112. Information recorded by the client device 104 in the application 106 regarding timing, dosage, and previous recommendations, either from a provider or the medication therapy analysis system 112, may be inputs to this analysis. If the medication therapy analysis system 112 determines that user 102 was compliant and did substantially adhere to the previous medication therapy plan and recommendation for dosage, then the medication therapy analysis system 112 may provide a recommendation to client device 104 that the user 102 increase the dosage of the medication to better prevent or reduce seizures in the future, as shown in act 328. If the medication therapy analysis system 112 determines that the user 102 was not compliant and did not adhere to the medication therapy plan or recommendation for dosage, then the medication therapy analysis system 112 provides a recommendation to the client device 104 that the user 102 adhere to the medication therapy plan, as shown in act 330. The medication therapy analysis system 112 may also provide instructions to client device 104 that the user 102 seek advice from a provider to develop a plan to more successfully take the medication as directed.

Responsive to determining that the medication concentration level is within an appropriate range, as indicated by act 310, process 300 may include determining whether there are any behavioral or environmental triggers that may have contributed to the occurrence of the seizure, as shown in act 322. Possible triggers may include stress, mood, diet (e.g., alcohol consumption, caffeine consumption), lack of sleep, exercise patterns of the user 102, blood sugar level of the user 102, weather patterns, time of day, dehydration, menstruation, flashing lights, other medications, etc. The medication therapy analysis system 112 may analyze the health event data received from the client device 104 to determine whether the user 102's behavior or external circumstances may have caused the seizure. This analysis may include determining patterns between particular behaviors or circumstances that may correspond to an increased likelihood of seizures, despite the appropriate or normal medication concentration levels. Responsive to determining that triggers may have contributed to the cause of the seizure, the triggers are analyzed at act 332. Additionally, different combinations of triggers may be analyzed at act 332 to determine whether there is a correlation between different possible triggers and whether certain behaviors combine to increase the likelihood of a seizure. The results of this analysis regarding possible triggers may be provided to the client device 104, along with recommendations for lifestyle behavior change of the user 102. Recommended lifestyle behavioral changes may include improving amount and quality of sleep, taking steps to decrease stress and improve mood, decreasing alcohol or other substance (e.g., caffeine, sugar, etc.) consumption, increasing amount and quality of exercise, etc. If there are no recognizable triggers and the medication concentration level was within the appropriate range, as determined from the health event data, this may be an indication that the target drug levels determined in act 318 do not reflect the correct ranges for the user 102. Therefore, to further individualize the target drug levels of act 318, the seizure event and the medication concentration level information is provided so that the target ranges may be adjusted accordingly at act 318. In this instance, the lower limit for the appropriate range may be raised so that future dosage recommendations reflect the individualized needs and pharmacokinetics of the user 102. Accordingly, the information determined at act 322 is used to individualize an appropriate range for future dosage recommendations.

Responsive to determining that the medication concentration level is within a higher range, as indicated by act 312, process 300 may include analyzing the health event data and determining whether there are any behavioral or environmental triggers that may have contributed to the occurrence of the seizure, as shown in act 324. The analysis performed during act 324 may be similar or the same as act 322. Furthermore, if behavioral/environmental triggers appear to have contributed to the occurrence of a seizure, process 300 may include analyzing the triggers, as shown in act 332, and providing a recommendation to the client device 104 that the user 102 consider making lifestyle behavior changes. If, after analysis, behavioral triggers do not appear to be a cause for the seizure, this may be an indication that the type of medication that the user 102 is taking is not effective for the user 102 because the medication concentration level is already in a higher range and no behavioral triggers appear to explain the occurrence of a seizure. Therefore, the medication therapy analysis system 112 may provide, to the client device 104, a recommendation to consider changing the type of medication. Additionally, the medication therapy analysis system 112 may provide, to the client device 104, a recommendation to consult with a provider to change the type of medication.

Responsive to determining that the health event is a side effect(s), process 300 may include analyzing the health event data to determine whether the medication concentration level is within a target range. It is unlikely for side effects to occur when the medication concentration level is within a lower range and as such, this result and analysis is not shown in FIG. 3. Additionally, because the absence of seizures is generally viewed by healthcare professionals as more important than limiting side effects, excessive doses tend to be prescribed by providers and low medication concentration levels are rarely expected when side effects are occurring. However, if the medication concentration level is found to be within a lower range after determining that side effects are occurring, the medication therapy analysis system 112 may provide a recommendation to the client device 104 to change the type of medication that the user 102 is taking, as may be indicated by act 334.

Responsive to determining that the medication concentration level is within an appropriate range while side effects have occurred, as indicated by act 314, medication therapy analysis system 112 may determine that the target drug levels determined in act 318 do not reflect the correct target ranges for the user 102 because side effects occurred despite the medication concentration level being within an appropriate range according to the individualized target drug levels. Therefore, to further individualize the target drug levels, the side effects event and the medication concentration level information is analyzed at act 318 so that the target ranges may be adjusted accordingly. In this instance, the upper limit for the appropriate range may be lowered so that future dosage recommendations are lower and more accurate for the given user 102. The medication therapy analysis system 112 or a provider may determine that side effects in the absence of seizures is preferable than the occurrence of seizures without side effects and as such, may provide no recommendation for a change in dosage, lifestyle behavior, or type of medication to the client device 104 or the user 102.

Responsive to determining that the medication concentration level is within a higher range at act 316, process 300 may include determining the occurrence of a seizure, as shown in act 326. If a seizure has occurred along with side effects and the medication concentration level is found to be within a higher target range, then medication therapy analysis system 112 may determine that the medication may be inadequate for the user 102 and may provide a recommendation to the client device 104 to change the type of medication, as illustrated by act 334. If a seizure has not occurred, this may be an indication that the dosage of the medication is too high and a recommendation may be provided to the client device 104 for the user 102 to consider decreasing the dosage of the medication, as shown in act 336. The recommendation may also include instructions to consult with a provider to determine more details regarding the decrease in dosage.

Following any of acts 328, 330, 332, 334, or 336, process 300 may repeat and proceed to act 302 where another event/non-event may be analyzed by the medication therapy analysis system 112.

As noted above, in some embodiments, the process 300 may be implemented using machine learning to improve its effectiveness. For instance, one or more processes such as the process 300, may include machine learning and/or deep learning techniques that include providing training corpora to a matching learning algorithm or neural network to train a machine to aid or perform the processes described herein. In some embodiments, the medication therapy analysis system 112 may analyze the health event data utilizing one or more of regression models (e.g., a set of statistical processes for estimating the relationships among variables), classification models, and/or phenomena models. Additionally, the machine-learning models may include a quadratic regression analysis, a logistic regression analysis, a support vector machine, a Gaussian process regression, ensemble models, or any other regression analysis. Furthermore, in yet further embodiments, the machine -learning models may include decision tree learning, regression trees, boosted trees, gradient boosted tree, multilayer perceptron, one-vs-rest, Naive Bayes, k-nearest neighbor, association rule learning, a neural network, deep learning, pattern recognition, or any other type of machine-learning.

For example, the medication therapy analysis system 112 may apply one or more of the above described machine learning techniques to the health event data in conjunction with any subsequent or earlier recommendations sent to the client device 104 and any subsequent or earlier health event data received from the client device 104. In other words, the medication therapy analysis system 112 may apply one or more of the above described machine learning techniques to the feedback loop of a communication session with the client device 104. Furthermore, by applying the one or more machine -learning techniques to the previously provided recommendations and any subsequent or earlier received health event data, the medication therapy analysis system 112 may more accurately update the target drug levels as shown in act 318 and provide more accurate and reliable medical therapy recommendations to the user 102.

As a non-limiting example, the medication therapy analysis system 112 may utilize the feedback loop of the communication session (e.g., providing recommendations and receiving health event data) to train the machine-learning models to update the target drug levels and provide accurate recommendations in the future. In other words, via the machine learning model techniques, the medication therapy analysis system 112 may learn correlations and/or relationships between health events, behavioral/environmental triggers, and medication dosage. For example, as will be understood in the art, for a given set of input values (e.g., the health event data), the medication therapy analysis system 112 is expected to produce the same output values (e.g., a medication, dosage, or lifestyle behavior change recommendation), as would be actually understood by a human operator. In particular, the machine learning models are trained via supervised learning, as in known in the art. After a sufficient number of iterations, the machine learning models become trained machine-learning models. In some embodiments, the machine learning models may be also trained on historical data from previous health event data and/or previous recommendations.

FIGS. 4A-4C illustrate an example initialization of target drug levels determined in act 318 of FIG. 3 in accordance with various embodiments of this disclosure. FIG. 4A includes a plot 400a illustrating measurements of medication concentration levels (e.g., blood medication concentration levels) overtime. The shaded region 402a represents an initial appropriate range of medication concentration levels as statistically determined in clinical trials. Medication concentration measurements such as medication concentration measurement 404 may be taken as a user 102 begins taking a particular medication for a medication therapy plan. Medication concentration measurement 404 may be taken using a point-of-care testing kit or device. Measurements such as blood medication concentration measurement 404 may be taken directly after a seizure or side effect. For example, a user 102 may be prompted by the client device 104 to take a medication concentration measurement after a medical device(s) 114 has detected that a seizure has occurred. In some embodiments, such as where the medication concentration level is measured in blood, the user may use a point-of-care blood medication concentration testing kit or device (such as those described in U.S. Patent Application Publication No. 2020/0393450 Al, the disclosure of which is incorporated herein in its entirety by this reference) and record the results using the application 106. Measurements such as medication concentration measurement 404 may also be taken periodically, without regard to occurrence of seizures or side effects. For example, if the client device 104 determines that the medication concentration has not been measured for a predetermined period of time (e.g., one week), then the client device 104 may prompt user 102 to take a medication concentration measurement. As illustrated in FIG. 4A, the medication concentration level may be gradually increased until the measurements show that the medication concentration level is consistently within the appropriate range 402a.

The client device 104 may prompt the user 102 to take a measurement of the medication concentration level several times a day for several weeks to reveal the user’s 102 specific pharmacokinetics (PK) and pharmacodynamics (PD). To determine PK and PD, a relationship between dosage amount, time from administration of dose, the user’s 102 metabolic capacity, and an interaction with other drugs may be evaluated. The data collected by the client device 104 about user 102 may be aggregated with data collected by other client devices about other users to develop treatment for sub-groups, including infants, elderly, pregnant women, etc. Machine learning may be used to learn trends and correlations for predicting causes of seizures for particular individuals and for groups of individuals who share common characteristics.

FIG. 4B includes a plot 400b illustrating measurements of medication concentration levels (e.g., medication concentration measurement 404) overtime as well as measurements taken in response to seizures (e.g., seizure 406) and side effects (e.g., side effect 408). As explained above with reference to FIG. 4A, medication concentration levels may be measured immediately after an event, such as a seizure or a severe side effect. An exemplary measurement taken in response to a seizure is represented by seizure 406. An exemplary measurement taken in response to a side effect is represented on plot 400b as side effect 408. Other measurements such as medication concentration measurement 404 are taken periodically if a predetermined time passes without an event such as a seizure or side effects.

FIG. 4C includes a plot 400c illustrating measurements of medication concentration levels and individualized target ranges for medication concentration levels (e.g., target drug levels determined in act 318). The different shaded regions 402b, 410, and 412 shown in FIG. 4C represent individualized target ranges for a single user (e.g., user 102). The appropriate range 402a that originally encompassed a large range of medication concentration levels is reduced responsive to the measurements taken immediately after seizures and side effects, as described in more detail with respect to FIG. 3. For example, as shown in FIG. 4B, if a seizure 406 and the subsequent medication concentration measurement indicates that the seizure occurred while the user 102 was in the appropriate range 402a, then the lower limit of appropriate range 402a will be increased (i.e., the span of the range appropriate range 402a may be reduced by increasing the lower limit of the appropriate range 402a) to appropriate range 402b and the medication concentration levels corresponding to the levels when the seizure occurred will be designated as the lower range 410. As another example, if a side effect 408 and subsequent medication concentration measurement indicate that the side effect occurred while the user 102 was in the appropriate range 402a, then the upper limit of the appropriate range 402a will be reduced, resulting in appropriate range 402b and the medication concentration levels corresponding to the levels when the side effect occurred will be designated higher range 412. As explained with reference to FIG. 3, other behavioral triggers are considered when determining and adjusting the target drug levels of act 318 and the levels may, in some embodiments, only be adjusted when there are no other behavioral or environmental triggers that may explain the seizure or side effects.

FIG. 5 is schematic representation 500 of environment 100 of FIG. 1 illustrating inputs and outputs of the medication therapy analysis system 112 and the application 106. Schematic view 500 includes inputs 502, 504, 506, and 508, application 106, server(s) 110, and decision act 510. A user (e.g., user 102) may record in the application 106 whenever the user takes medication as indicated by input 502, potential seizure triggers as indicated by input 504, and symptoms such as auras, seizures, and side effects as indicated by input 506. When an event occurs, such as a seizure, aura, or side effect, the application 106 may prompt the user 102 to measure medication concentration level as indicated in input 508, upon which the user 102 may record the resulting measurement in the application 106. The application 106 may then provide the inputs and measurement results to server(s) 110 which performs analysis in accordance with various embodiments of this disclosure. Responsive to the completed analysis at server(s) 110, a recommendation or decision act 510 may be provided to the application 106. The recommendation or decision may include instructions to increase or decrease dosage of a medication, a recommendation to adjust lifestyle behavior to avoid identified behavioral and environmental triggers that may be causing or inducing seizures, or to change the type of medication the user 102 is taking because it appears to be ineffective in preventing seizures. FIGS. 6A-6Q illustrate a collection of user interfaces including features of the application 106 according to one or more embodiments of the present disclosure. In particular, the user interfaces show features of the application 106 of the client device 104 and the medication therapy analysis system 112. As will be described in more detail below, the components of the environment 100 as described with regard to FIG. 1 may provide, alone and/or in combination with the other components, one or more graphical user interfaces (“GUIs”). A GUI typically includes one or more display regions and active/activatable regions. As used in this disclosure, a display region is a region of a GUI which displays information to a user. An activatable region is a region of a GUI, such as a button, slider, or a menu, which allows the user to take some action with respect to the GUI (e.g., if manipulated). Some display regions are also activatable regions in that the activatable regions display information and enable some action that may be taken by a user. In a contact-sensitive GUI, contacting a contact-sensitive area associated with an activatable region may activate that region (e.g., selecting a GUI button). Activatable regions may be displayed as GUI elements/objects, for example, buttons, sliders, selectable panes, menus, etc. all of various shapes and sizes. In particular, the components (e.g., the activatable regions of the GUI) may allow a user 102 to interact with a collection of display elements for a variety of purposes. In particular, FIGS. 6A-6G and the description that follows illustrate various examples embodiments of the present disclosure.

For example, FIG. 6A illustrates a client device 602 of a medication therapy analysis system 112 user (e.g., the user 102 of FIG. 1) that may implement one or more of the components or features of the environment 100. The client device 602 may be an example of a client device 104 of FIG. 1. As shown in FIG. 6A, in some embodiments, the client device 602 is a handheld device, such as a mobile phone device (e.g., a smartphone). As used herein, the term “handheld device” refers to a device sized and configured to be held/operated in a single hand of the user 102 and/or worn and operated by one or more hands of the user 102. In additional or alternative examples, however, any other suitable computing device such as, but not limited to, a tablet device, larger wireless device, laptop or desktop computer, a personal digital assistant device, and/or any other suitable computing device may perform one or more of the processes and/or operations described herein. The client device 602 includes a touch screen display 604 that may display user interfaces. Furthermore, the client device 602 receives and/or detects user input via the touch screen display 604. As used herein, a “touch screen display” refers to the display of a touch screen device. In one or more embodiments, a touch screen device may be the client device 602 with at least one surface upon which a user 102 may perform touch gestures (e.g., a laptop, a tablet computer, a personal digital assistant, a media player, a mobile phone, etc.). Additionally or alternatively, the client device 602 may include any other suitable input device, such as a touch pad or those described below with reference to FIG. 7.

FIGS. 6A-6Q show example GUIs for application 106 through which the user 102 may interact with client device 602 to record and store information regarding health events such as seizures. FIGS. 6A-6C show an example of how a user 102 may create an account so that information stored on server(s) 110 may be accessible through different devices in addition to the client device 104 or client device 602.

In reference to FIG. 6A, the client device 602 detects a user interaction inputting a desire to create a new account with application 106. The user 102 may touch button 606 to start the onboarding process of creating a new account within application 106 and medication therapy analysis system 112.

Referring to FIG. 6B, responsive to receiving an input that the user 102 desires to create an account, client device 602 provides textboxes such as textbox 608 on the display to receive input from the user 102 for creating an account with the medication therapy analysis system 112. The textboxes such as textbox 608 may include space to input a user’s name, email address, password, etc. The inputs shown on this screen or others as a part of account creation may also include other personal or health information such as height, weight, medical history, family history, etc. Once the user 102 has input the information as requested by the application 106, the user 102 may tap button 610 to create a new account in the medication therapy analysis system 112.

Referring to FIG. 6C, responsive to account creation, the client device 602 may prompt the user 102 as to whether the user 102 desires to receive reminders and/or notifications such as medication reminders from the client device 602. The user 102 may choose to accept or decline the option of receiving notifications and/or reminders by tapping button 612 for yes or button 614 for no. Referring to FIG. 6D, the client device 602 may prompt the user 102 to log a health event. The user 102 may receive a notification from the client device 602 that an event occurred, as detected and reported by a medical device(s) 114. In this case, the medical device(s) 114 may communicate with the client device 602 to prompt the user 102 to log the detected health event. In other embodiments or scenarios, after a health event occurs, the user 102 may open the application 106 without any prompting or notification from the client device 602 in order to log the event. As shown in FIG. 6D, the client device 602 may prompt the user 102 to choose which type of health event occurred (e.g., a seizure, an aura, or side effects). The user 102 may tap the button that corresponds to the health event that occurred.

FIGS. 6E-6G illustrate GUIs that may be used when a seizure has occurred while FIGS. 6H-6K illustrate a flow of displays that may be presented to the user 102 when side effects have occurred. Referring to FIG. 6E, responsive to receiving an input from the user 102 regarding which type of health event occurred, the client device 602 may further prompt the user 102 for more information regarding the health event. For example, responsive to the user 102 experiencing a health event and input that the health event was a seizure, as described with relation to FIG. 6D, the client device 602 may prompt the user 102 to give further input as to the type of seizure (e.g., convulsive/non- convulsive or aware/non-aware). The choices between options may be represented as radio buttons, such as radio button 616 where the user may only choose one by tapping the most appropriate option.

Furthermore, as illustrated in FIG. 6F, the user may be further prompted to describe any possible triggers that may have contributed to the occurrence of the seizure. For example, responsive to a recent consumption of alcohol by the user 102, the user 102 would tap the button 618 representing the possible trigger for “alcohol.” Other buttons that may be included in the display prompting the user 102 to select possible triggers are “alcohol,” “sleep,” “caffeine,” “stress,” “missed medication,” “menstruation,” “fever,” “dehydration,” “not sure”, or “other.”

Referring to FIG. 6G, the user 102 may also choose to add additional notes regarding the seizure and any possible triggers. The user 102 may type anything into the textbox 620 that may be relevant to the seizure or possible triggers. The medication therapy analysis system 112 may interpret this information using natural language processing (NLP) to provide individualized recommendations to the user 102 regarding possible medication dosage changes and/or lifestyle behavior changes.

Referring to FIG. 6H, the client device 602 may prompt the user 102 to input information regarding side effects that occurred. In some embodiments, the user 102 may experience side effects and open the application 106 on the client device 602 to log the side effects. In other embodiments, the client device 602 may remind the user 102 at a predetermined time (e.g., end of day before going to bed or every day at 9:00 P.M.) to enter information regarding any side effects that may have occurred during the day. The user 102 may forget to log the occurrence of side effects and therefore a reminder is helpful for the medication therapy analysis system 112 to have the most accurate and up-to-date information for recommendation purposes. The client device 602 may present a list 626 of side effects in a similar fashion as the possible triggers shown in FIG. 6F. For example, the client device 602 may present a list 626 of possible side effects on the touch screen display 604 of client device 602 with buttons with which the user 102 may choose which side effects the user 102 experienced. Examples of possible listed side effects may include “confusion,” “dizziness,” “memory changes,” “double vision,” “anxiety,” “depression,” “tiredness,” “sleep issues,” “headache,” or “other.”

FIG. 61 illustrates the GUI when, as an example, the user 102 chooses and taps the “other” option button 622 when prompted to choose which side effects occurred from list 626. The user 102 may choose the “other” option when the listed options of list 626 are not representative of the side effect that the user 102 experienced. As shown in FIG. 61, the “other” option button 622 appears darker to represent being selected by the user 102 responsive to the user 102 tapping the “other” option button 622. The “submit” button also changes in appearance and becomes darker in response to the user 102 choosing a side effect and tapping one of the side effects buttons, such as the “other” option button 622. The darker appearance suggests to the user 102 that the “submit” button 624 is now active and may be tapped. Once the user 102 chooses to submit, the user may then see the GUI shown in FIG. 6G.

Referring to FIG. 6J, the client device 602 may prompt the user 102 to input notes describing the side effect since it was not a part of the pre-populated list 626 of FIG. 6H. The user may type in textbox 628 to describe the experienced side effect(s). The notes input in textbox 628 may be processed using NEP and the medication therapy analysis system 112 may use machine learning to improve its ability to understand the side effect and its impact on the user 102. The medication therapy analysis system 112 may also aggregate inputs from several users who are using the medication therapy analysis system 112 in order to improve its ability to understand the different side effects that may occur and the natural language used to describe them.

Referring to FIG. 6K, the client device 602 may prompt the user 102 to input any other notes that are relevant to the occurrence of the side effects and tap the “submit” button 630 to submit the information to the medication therapy analysis system 112.

Referring to FIG. 6L, the client device 602 may prompt the user 102 to insert a blood sample into a medication concentration measuring device (e.g., a blood medication concentration measuring device (e.g., medical device(s) 114)). As shown in FIG. 6L, the GUI on the client device 602 may instruct the user 102 to prick a finger to draw blood and place the drawn blood into the medical device(s) 114.

Referring to FIG. 6M, the GUI may display to the user 102 that the medical device(s) 114 is calibrating and/or measuring the medication concentration level of the user 102. The GUI may display a graphic that expresses that the medical device(s) 114 is processing the blood sample and that the user 102 should wait until the processing is complete.

Referring to FIG. 6N, the medical device(s) 114 may communicate directly (e.g., wirelessly) with the client device 602 to provide results of the medication concentration measurement. The client device 602 may present on its display results of the medication concentration measurement. The client device 602 may then provide the results via network 108 to the medication therapy analysis system 112 which may analyze the medication concentration level along with health event data collected related to the user 102, through the application 106.

Referring to FIG. 60, the GUI may display an interactive calendar that the user 102 may use to view recorded health and lifestyle entries for past health events. The user 102 may tap particular days in the calendar to see the health events that occurred that day and all the details that the user 102 entered. The historical entries may also be editable so that more information about a health event may be added at a later time.

Responsive to the user 102 tapping a particular day, the recorded health and lifestyle data may appear on the display, as illustrated in FIG. 6P. The details regarding the recorded health and lifestyle data for the health event are reviewable and in some embodiments, are editable. The historical entries may be editable so that more information about a health event may be added and/or changed at a later time.

Referring to FIG. 6Q, a reminder, as described with reference to FIG. 6H, is illustrated on the “home screen” of the client device 602. The reminder may be a push notification that states that the user 102 should remember to record health and lifestyle data for the day. If no health events occurred during the day, including seizures or side effects, then the user may enter a note or input stating that no health event occurred that day. The user can also log possible factors that might normally be considered triggers but did not trigger a seizure during that day. This kind of information may be useful for the medication therapy analysis system 112 to determine with more accuracy which behaviors and environments are actual triggers and which are not.

FIG. 7 is a block diagram of an exemplary computing device 702 that may be utilized as a client device (e.g., client device 104) and/or a medication therapy analysis system (e.g., medication therapy analysis system 112) that may be configured to perform one or more of the processes described above. One will appreciate that one or more computing devices may implement the computing device 702. The computing device 702 can comprise a processor 704, a memory 706, a storage device 708, an I/O interface 710, and a communication interface 712, which may be communicatively coupled by way of communication infrastructure 714. While an exemplary computing device is shown in FIG. 7, the components illustrated in FIG. 7 are not intended to be limiting. Additional or alternative components may be used in other embodiments. Furthermore, in certain embodiments, the computing device 702 may include fewer components than those shown in FIG. 7. Components of the computing device 702 shown in FIG. 7 will now be described in additional detail.

In one or more embodiments, the processor 704 includes hardware for executing instructions, such as those making up a computer program. As an example and not by way of limitation, to execute instructions, the processor 704 may retrieve (or fetch) the instructions from an internal register, an internal cache, the memory 706, or the storage device 708 and decode and execute them. In one or more embodiments, the processor 704 may include one or more internal caches for data, instructions, or addresses. As an example not by way of limitation, the processor 704 may include one or more instruction caches, one or more data caches, and one or more translational lookaside buffers (TLBs). Instructions in the instruction caches may be copies of instructions in the memory 706 or the storage device 708.

The computing device 702 includes memory 706, which is coupled to the processor(s) 704. The memory 706 may be used for storing data, metadata, and programs for execution by the processor(s). The memory 706 may include one or more of volatile and non-volatile memories, such as Random-Access Memory (“RAM”), Read Only Memory (“ROM”), a solid state disk (“SSD”), Flash, Phase Change Memory (“PCM”), or other types of data storage. The memory 706 may be internal or distributed memory.

The computing device 702 includes a storage device 708 that includes storage for storing data or instructions. As an example, and not by way of limitation, storage device 708 can comprise a non-transitory storage medium described above. The storage device 708 may include a hard disk drive (HDD), a floppy disk drive, Flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. The storage device 708 may include removable or non-removable (or fixed) media, where appropriate. The storage device 708 may be internal or external to the computing device 600. In one or more embodiments, the storage device 708 is non-volatile, solid-state memory. In other embodiments, the storage device 708 includes read-only memory (ROM). Where appropriate, this ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or Flash memory or a combination of two or more of these.

The computing device 702 also includes one or more input or output (“I/O”) devices/interfaces 710, which are provided to allow a user to provide input to, receive output from, and otherwise transfer data to and receive data from computing device 702. The I/O devices/interfaces 710 may include a mouse, a keypad or a keyboard, a touch screen, a camera, an optical scanner, network interface, modem, other known I/O devices or a combination of such I/O device/interfaces. The touch screen may be activated with a stylus or a finger.

The I/O devices/interfaces 710 may include one or more devices for presenting output to a user, including, but not limited to, a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., display drivers), one or more audio speakers, and one or more audio drivers. In certain embodiments, the I/O interface 710 is configured to provide graphical data to a display for presentation to a user. The graphical data may be representative of one or more graphical user interfaces and/or any other graphical content as may serve a particular implementation.

The computing device 702 can further include a communication interface 712. The communication interface 712 can include hardware, software, or both. The communication interface 712 can provide one or more interfaces for communication (such as, for example, packet-based communication) between the computing device 702 and one or more other computing devices or networks. As an example, and not by way of limitation, the communication interface 712 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wirebased network or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a Wi-Fi.

Additionally or alternatively, the communication interface 712 may facilitate communications with an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or one or more portions of the Internet or a combination of two or more of these. One or more portions of one or more of these networks may be wired or wireless. As an example, the communication interface 712 may facilitate communications with a wireless PAN (WPAN) (such as, for example, a BLUETOOTH®WPAN), a WI-FI network, a WI-MAX network, a cellular telephone network (such as, for example, a Global System for Mobile Communications (GSM) network), or other suitable wireless network or a combination thereof.

Additionally, the communication interface 712 may facilitate communications various communication protocols. Examples of communication protocols that may be used include, but are not limited to, data transmission media, communications devices, Transmission Control Protocol (“TCP”), Internet Protocol (“IP”), File Transfer Protocol (“FTP”), Telnet, Hypertext Transfer Protocol (“HTTP”), Hypertext Transfer Protocol Secure (“HTTPS”), Session Initiation Protocol (“SIP”), Simple Object Access Protocol (“SOAP”), Extensible Mark-up Language (“XML”) and variations thereof, Simple Mail Transfer Protocol (“SMTP”), Real-Time Transport Protocol (“RTP”), User Datagram Protocol (“UDP”), Global System for Mobile Communications (“GSM”) technologies, Code Division Multiple Access (“CDMA”) technologies, Time Division Multiple Access (“TDMA”) technologies, Short Message Service (“SMS”), Multimedia Message Service (“MMS”), radio frequency (“RF”) signaling technologies, Long Term Evolution (“LTE”) technologies, wireless communication technologies, in-band and out-of-band signaling technologies, and other suitable communications networks and technologies.

The communication infrastructure 714 may include hardware, software, or both that couples components of the computing device 702 to each other. As an example and not by way of limitation, the communication infrastructure 714 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a front-side bus (FSB), a HYPERTRANSPORT (HT) interconnect, an Industry Standard Architecture (ISA) bus, an INFINIBAND interconnect, a low-pin-count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a serial advanced technology attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination thereof.

The foregoing specification is described with reference to specific example embodiments thereof. Various embodiments and aspects of the disclosure are described with reference to details discussed herein, and the accompanying drawings illustrate the various embodiments. The description above and drawings are illustrative and are not to be construed as limiting. Numerous specific details are described to provide a thorough understanding of various embodiments. For instance, while specific example embodiments are discussed above with respect to blood, including blood medication concentration levels, blood drug levels, and blood medication levels, the disclosure is not limited to medication concentration levels in blood but may include medication concentration levels in other substances such as hair, urine, sweat, saliva, tears, interstitial fluids, etc.

The additional or alternative embodiments may be embodied in other specific forms without departing from its spirit or essential characteristics. The described embodiments are to be considered in all respects only as illustrative and not restrictive. The scope of the disclosure is, therefore, indicated by the appended claims rather than by the foregoing description. All changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.

Additional non-limiting example embodiments of the disclosure are set forth below.

Embodiment 1: A method comprising: receiving health event data indicating an occurrence or an absence of a seizure event; providing the health event data to a medication therapy analysis system; receiving an indication of a medication therapy plan recommendation, the medication therapy plan recommendation being based at least partially on the health event data; and providing the indication of the medication therapy plan recommendation to a user.

Embodiment 2: The method of Embodiment 1, wherein receiving the health event data comprises receiving one or more inputs from the user.

Embodiment 3: The method of Embodiment 1 or Embodiment 2, wherein receiving the health event data comprises receiving a communication comprising a data package from one or more devices.

Embodiment 4: The method of any one of Embodiments 1 through 3, wherein the health event data further indicates an occurrence or an absence of a side effect event.

Embodiment 5: The method of any one of Embodiments 1 through 4, wherein the indication of the medication therapy plan recommendation is provided through a device display.

Embodiment 6: The method of any one of Embodiments 1 through 5, wherein the medication therapy plan recommendation comprises a medication dosage determination.

Embodiment 7: A medication therapy analysis system, comprising: at least one processor; and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the medication therapy analysis system to: receive health event data from a mobile device, the health event data indicating a health event of a user receiving a medication therapy; determine a medication level of the user at a time of the health event based at least partially on the health event data; responsive to determining that the medication level is within a target range, determine an adjusted target range; and responsive to determining that the medication level is not within the target range, determine and provide at least one recommendation of the following to the mobile device: a recommendation to increase or decrease a dosage of a medication of the medication therapy; a recommendation for a lifestyle behavior change; and a recommendation to change to a different type of medication for the medication therapy.

Embodiment 8: The medication therapy analysis system of Embodiment 7, wherein determining and providing at least one of recommendations comprises: determining that the medication level is below the target range; responsive to determining that the user is adhering to a plan for the medication therapy, providing a recommendation to the mobile device to increase the dosage of the medication; and responsive to determining that the user is not adhering to the plan for the medication therapy, providing a recommendation to the mobile device to seek instruction from a provider.

Embodiment 9: The medication therapy analysis system of Embodiment 7 or Embodiment 8, further comprising: responsive to determining that the medication level is within the target range, determine that behavioral or environmental triggers are potential causes of the health event and analyze the behavioral or environmental triggers to determine and provide a recommendation for the lifestyle behavior change.

Embodiment 10: The medication therapy analysis system of any one of Embodiments 7 through 9, further comprising: responsive to determining that the medication level is above the target range, determine whether behavioral or environmental triggers are potential causes of the health event; responsive to determining that the behavioral triggers are a potential cause of the health event, analyze the behavioral or environmental triggers to determine and provide a recommendation to the mobile device for a behavioral change; and responsive to determining that the behavioral or environmental triggers are not a probable cause of the health event, determine and provide a recommendation to the mobile device to change to the different type of medication for the medication therapy.

Embodiment 11: The medication therapy analysis system of any one of Embodiments 7 through 10, wherein the medication therapy analysis system comprises a cloud computing platform.

Embodiment 12: The medication therapy analysis system of any one of Embodiments 7 through 11, wherein the medication therapy analysis system comprises a provider device associated with a provider of the user.

Embodiment 13: The medication therapy analysis system of any one of Embodiments 7 through 12, wherein receiving the health event data from the mobile device comprises receiving the health event data via an application of the mobile device.

Embodiment 14: The medication therapy analysis system of Embodiment 13, wherein the application comprises a health and lifestyle data recording application for receiving health related entries from the user. Embodiment 15: The medication therapy analysis system of any one of Embodiments 7 through 14, wherein the health event comprises a side effect.

Embodiment 16: The medication therapy analysis system of any one of Embodiments 7 through 15, wherein the health event comprises a health event the medication therapy is intended to prevent.

Embodiment 17: The medication therapy analysis system of any one of Embodiments 7 through 16, wherein the health event comprises a seizure-related event.

Embodiment 18: A non-transitory computer-readable medium storing instructions thereon that, when executed by at least one processor, cause the at least one processor to perform steps comprising: receiving health event data from one or more devices, at least a portion of the health event data indicating an occurrence or an absence of a seizure event of a user; providing the health event data to a medication therapy analysis system on a cloud computing platform; receiving at least one recommendation regarding medication therapy from the medication therapy analysis system; and generating and providing the indication of the at least one recommendation on a user interface for display to the user.

Embodiment 19: The non-transitory computer- readable medium of

Embodiment 18, wherein the one or more devices comprise at least one of: a blood medication level monitoring device, a wearable electromyography (EMG) device, a seizure prediction and/or detection device, a smart watch, a pedometer, a heart rate monitor, a wearable activity tracker, a fitness tracker, or a wearable computer.

Embodiment 20: The non-transitory computer- readable medium of

Embodiment 18 or Embodiment 19, further comprising instructions thereon that, when executed by the at least one processor cause the at least one processor to further perform a step of receiving an input from the user comprising additional health event data.

Embodiment 21: The non-transitory computer-readable medium of any one of Embodiments 18 through 20, wherein the health event data comprises one or more of: indications of symptoms of the user, medication levels of the user following a health event, indications of user side effects of a medication, and indications of user behavior.

Embodiment 22: The non-transitory computer-readable medium of any one of Embodiments 18 through 21, further comprising instructions thereon that, when executed by the at least one processor cause the at least one processor to further perform steps of: determining a medication concentration level from the health event data; and adjusting a target range for the medication concentration level.

Embodiment 23: The non-transitory computer-readable medium of

Embodiment 22, wherein the target range is adjusted when the health event data indicates the absence of a seizure event of the user and a predetermined period of time has passed since the health event data has indicated the occurrence of a seizure event of the user.

Embodiment 24: The non-transitory computer- readable medium of

Embodiment 22, wherein the target range is updated when the health event data indicates the occurrence of a seizure event of the user and the medication concentration level is within the target range and the health event data does not contain other indicators to explain a cause of the seizure event of the user.

The embodiments of the disclosure described above and illustrated in the accompanying drawing figures do not limit the scope of the disclosure, since these embodiments are merely examples of embodiments of the disclosure, which is defined by the appended claims and their legal equivalents. Any equivalent embodiments are intended to be within the scope of this disclosure. Indeed, various modifications of the present disclosure, in addition to those shown and described herein, such as alternative useful combinations of the content features described, may become apparent to those skilled in the art from the description. Such modifications and embodiments are also intended to fall within the scope of the appended claims and legal equivalents.

Claims

- 33 - CLAIMS What is claimed is:

1. A method comprising: receiving health event data indicating an occurrence or an absence of a seizure event; providing the health event data to a medication therapy analysis system; receiving an indication of a medication therapy plan recommendation, the medication therapy plan recommendation being based at least partially on the health event data; and providing the indication of the medication therapy plan recommendation to a user.

2. The method of claim 1, wherein receiving the health event data comprises receiving one or more inputs from the user.

3. The method of claim 1, wherein receiving the health event data comprises receiving a communication comprising a data package from one or more devices.

4. The method of claim 1, wherein the health event data further indicates an occurrence or an absence of a side effect event.

5. The method of claim 1, wherein the indication of the medication therapy plan recommendation is provided through a device display.

6. The method of claim 1, wherein the medication therapy plan recommendation comprises a medication dosage determination.

- 34 -

7. A medication therapy analysis system, comprising: at least one processor; and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the medication therapy analysis system to: receive health event data from a mobile device, the health event data indicating a health event of a user receiving a medication therapy; determine a medication level of the user at a time of the health event based at least partially on the health event data; responsive to determining that the medication level is within a target range, determine an adjusted target range; and responsive to determining that the medication level is not within the target range, determine and provide at least one recommendation of the following to the mobile device: a recommendation to increase or decrease a dosage of a medication of the medication therapy; a recommendation for a lifestyle behavior change; and a recommendation to change to a different type of medication for the medication therapy.

8. The medication therapy analysis system of claim 7, wherein determining and providing at least one of recommendations comprises: determining that the medication level is below the target range; responsive to determining that the user is adhering to a plan for the medication therapy, providing a recommendation to the mobile device to increase the dosage of the medication; and responsive to determining that the user is not adhering to the plan for the medication therapy, providing a recommendation to the mobile device to seek instruction from a provider.

9. The medication therapy analysis system of claim 7, further comprising: responsive to determining that the medication level is within the target range, determine that behavioral or environmental triggers are potential causes of the health event and analyze the behavioral or environmental triggers to determine and provide a recommendation for the lifestyle behavior change.

10. The medication therapy analysis system of claim 7, further comprising: responsive to determining that the medication level is above the target range, determine whether behavioral or environmental triggers are potential causes of the health event; responsive to determining that the behavioral triggers are a potential cause of the health event, analyze the behavioral or environmental triggers to determine and provide a recommendation to the mobile device for a behavioral change; and responsive to determining that the behavioral or environmental triggers are not a probable cause of the health event, determine and provide a recommendation to the mobile device to change to the different type of medication for the medication therapy.

11. The medication therapy analysis system of claim 7, wherein the medication therapy analysis system comprises a cloud computing platform.

12. The medication therapy analysis system of claim 7, wherein the medication therapy analysis system comprises a provider device associated with a provider of the user.

13. The medication therapy analysis system of claim 7, wherein receiving the health event data from the mobile device comprises receiving the health event data via an application of the mobile device.

14. The medication therapy analysis system of claim 13, wherein the application comprises a health and lifestyle data recording application for receiving health related entries from the user.

15. The medication therapy analysis system of claim 7, wherein the health event comprises a side effect.

16. The medication therapy analysis system of claim 7, wherein the health event comprises a health event the medication therapy is intended to prevent.

17. The medication therapy analysis system of claim 7, wherein the health event comprises a seizure-related event.

18. A non-transitory computer- readable medium storing instructions thereon that, when executed by at least one processor, cause the at least one processor to perform steps comprising: receiving health event data from one or more devices, at least a portion of the health event data indicating an occurrence or an absence of a seizure event of a user; providing the health event data to a medication therapy analysis system on a cloud computing platform; receiving at least one recommendation regarding medication therapy from the medication therapy analysis system; and generating and providing the indication of the at least one recommendation on a user interface for display to the user.

19. The non-transitory computer-readable medium of claim 18, wherein the one or more devices comprise at least one of: a blood medication level monitoring device, a wearable electromyography (EMG) device, a seizure prediction and/or detection device, a smart watch, a pedometer, a heart rate monitor, a wearable activity tracker, a fitness tracker, or a wearable computer.

20. The non-transitory computer-readable medium of claim 18, further comprising instructions thereon that, when executed by the at least one processor cause the at least one processor to further perform a step of receiving an input from the user comprising additional health event data. - 37 -

21. The non-transitory computer-readable medium of claim 18, wherein the health event data comprises one or more of: indications of symptoms of the user, medication levels of the user following a health event, indications of user side effects of a medication, and indications of user behavior.

22. The non-transitory computer-readable medium of claim 18, further comprising instructions thereon that, when executed by the at least one processor cause the at least one processor to further perform steps of: determining a medication concentration level from the health event data; and adjusting a target range for the medication concentration level.

23. The non-transitory computer-readable medium of claim 22, wherein the target range is adjusted when the health event data indicates the absence of a seizure event of the user and a predetermined period of time has passed since the health event data has indicated the occurrence of a seizure event of the user.

24. The non-transitory computer-readable medium of claim 22, wherein the target range is updated when the health event data indicates the occurrence of a seizure event of the user and the medication concentration level is within the target range and the health event data does not contain other indicators to explain a cause of the seizure event of the user.