Method and system for using facial biometric data with neurological models

Abstract

Methods and systems for using facial biometric data with neurological models may include obtaining electroencephalogram (EEG) data and facial biometric data of a patient. The EEG data and the facial biometric data may be provided to a first model, to generate first model output data indicating a seizure. The EEG data and the facial biometric data may be provided to a second model, to generate second model output data predicting a seizure. The facial biometric data may be provided to a third model, to generate third model output data indicating an epileptic insight. In response to generating the model output data, the systems and methods may provide the model output data to a user device and / or store the model output data in a memory.

Description

METHOD AND SYSTEM FOR USING FACIAL BIOMETRIC DATA WITH NEUROLOGICALMODELSTECHNICAL FIELD

[0001] The present disclosure relates to systems and methods for using facial biometrics and, in particular, systems and methods for using facial biometric data with neurological models.BACKGROUND OF THE DISCLOSURE

[0002] Epilepsy is considered the world’s most common serious brain disorder, with an estimated 50 million sufferers worldwide and 2.4 million new cases occurring each year.

[0003] Epilepsy is a condition of the brain characterized by epileptic seizures that vary from brief and barely detectable seizures to more conspicuous seizures in which a sufferer vigorously shakes. Epileptic seizures are unprovoked, recurrent and due to unexplained causes.

[0004] Diagnosing epilepsy typically requires detailed study of both clinical observations and electrical and / or other signals in the patient’s brain and / or body. Particularly with respect to studying electrical activity in the patient’s brain (e.g., using electroencephalography to produce an electroencephalogram (EEG)), such study usually requires the patient to be monitored for some period of time. The monitoring of electrical activity in the brain requires the patient to have a number of electrodes placed on the scalp, each of which electrodes is typically connected to a data acquisition unit that samples the signals continuously (e.g., at a high rate) to record the signals for later analysis. Medical personnel monitor the patient to watch for outward signs of epileptic or other events, and review the recorded electrical activity signals to determine whether an event occurred, whether the event was epileptic in nature and, in some cases, the type of epilepsy and / or region(s) of the brain associated with the event. Because the electrodes are wired to the data acquisition unit, and because medical personnel must monitor the patient for outward clinical signs of epileptic or other events, the patient is typically confined to a small area (e.g., a hospital or clinical monitoring room) during the period of monitoring, that is generally short-term in nature due to such restrictions for the patient. Moreover, where the number of electrodes placed on or under the patient’s scalp is significant, the size of the corresponding wire bundle coupling the sensors to the data acquisition unit may be significant, which may generally require the patient to remain generally inactive during the period of monitoring, and may prevent the patient from undertaking normal activities that may be related to the onset of symptoms.

[0005] While advancements in implantable devices that gather EEG, such as the Epi-Minder Minder® system, now provide the ability to gather EEG while having a minimal impact, if any, on thequality of life of the patient in which the device is implanted, the EEG alone may not always capture the complete picture of the patient’s epilepsy status, which in-turn may affect the ability to determine an optimal treatment pathway for the patient, among other things. Complementing the EEG with physiological information of the patient, such as heart rate, movement patterns, etc., may provide additional, relevant information to determine the state of the patient’s epilepsy. However, even with this additional information, it remains difficult to substantiate that a patient-reported health event such as a seizure is accurate, and / or determine the overall well-being of the patient, side-effects from epilepsy medication, long-term clinical impacts of epilepsy-relates treatments, to name but a few.

[0006] Facial biometrics, such as biometrics associated with the eye, mouth, nose, face, etc., of the patient, can be a rich source of information providing insight into the state of health of the patient as it relates to a neurological disease, such as epilepsy, when analyzed alone, or in combination with EEG, to provide. However, capturing facial biometric information of the patient during an appropriate time, such as during a seizure or other health event, may prove challenging. Even if able to capture the facial biometric information of the patient, without having models to satisfactorily analyze the facial biometric information, for example to identify what the relevant facial biometrics are, correlate the relevant facial biometrics with EEG patterns, identify and / or predict a neurological health event, and / or otherwise determine neurological insights for the patient, etc., the facial biometric information may not realize its full potential. Thus, it is desirable to have systems and methods for using facial biometric data with neurological models.

[0007] Any discussion of documents, acts, materials, devices, articles or the like included in the present background is not to be taken as an admission that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present disclosure as it existed before the priority date of each claim of this application.SUMMARY

[0008] In embodiments, a system for identifying a seizure of a patient. The system may include (i) an implant device comprising a sensor array and a processor device, (a) the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient, and provide the EEG data to the processing device; (b) and the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor arrayvia the communication circuitry; (ii) an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (iii) a first model, stored in the memory and configured to be executed by the microprocessor, the first model trained using first model training data, and operable to: (a) receive the facial biometric data and the EEG data; (b) determine one or more feature values of the facial biometric data and the EEG data; and (c) based on the one or more feature values, generate first model output data indicating the seizure of the patient; and (iv) in response to generating the first mode output data, the processor device is configured to one or more of: (a) provide the first model output data to a user device; or (b) store the first model output data in the memory. The system may include additional, fewer, and / or alternate components, including various components descried in the present disclosure. Moreover, the system may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0009] In other embodiments, a system for predicting a seizure of a patient. The system may include (i) an implant device comprising a sensor array and a processor device, (a) the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient, and provide the EEG data to the processing device; and (b) the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor array via the communication circuitry; (ii) an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (iii) a second model, stored in the memory and configured to be executed by the microprocessor, the second model trained using second model training data, and operable to: (a) receive the facial biometric data and the EEG data; (b) determine one or more feature values of the facial biometric data and the EEG data; and (c) based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient; and (iv) in response to generating the second model output data, the processor device is configured to one or more of: (a) provide the second model output data to a user device; or (b) store the second model output data in the memory. The system may include additional, fewer, and / or alternate components, including various components descried in the presentdisclosure. Moreover, the system may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0010] In yet other embodiments, a system for generating an epileptic insight based upon facial biometrics of a patient. The system may include (i) a processor device comprising a processor, a memory, and communication circuitry; (ii) an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient; (iii) a third model, stored in the memory and configured to be executed by the processor, the third model trained using third model training data, and operable to: (a) receive the facial biometric data; (b) determine one or more feature values of the facial biometric data; and (c) based on the one or more feature values, generate third model output data indicating the epileptic insight; and (iv) in response to generating the third mode output data, the processor device is configured to one or more of: (a) provide the third model output data to a user device; or (b) store the third model output data in the memory. The system may include additional, fewer, and / or alternate components, including various components descried in the present disclosure. Moreover, the system may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0011] In still yet other embodiments, a computer-implemented method for identifying a seizure of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, (a) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and (b) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (ii) providing, by the one or more processors, the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating the seizure of the patient; and (iii) in response to generating the first model output data, one or more of: (a) providing, by the one or more processors, the first model output data to a user device; or (b) storing, by the one or more processors, the first model output data in a memory. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0012] In other embodiments, a computer-implemented method for predicting a seizure of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, (a) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and (b) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (ii) providing, by the one or more processors, the facial biometric data and the EEG data to a second model, trainedusing second model training data, to generate second model output data indicating the prediction of the seizure of the patient; and (iii) in response to generating the second model output data, one or more of: (i) providing, by the one or more processors, the second model output data to a user device; or (ii) storing, by the one or more processors, the second model output data in a memory. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0013] In yet other embodiments, a computer-implemented method for generating an epileptic insight based upon facial biometrics of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; (ii) providing, by the one or more processors, the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating the epileptic insight; and (iii) in response to generating the third model output data, one or more of: (a) providing, by the one or more processors, the third model output data to a user device; or (b) storing, by the one or more processors, the third model output data in a memory. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0014] In still yet other embodiments, a computer-implemented method for training a first model to identify a seizure of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, a first training dataset; (ii) receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; (iii) training, by the one or more processors, a first iteration of the first model using the first training dataset using the feature values defined for the first training dataset to generate primary first model output data having associated first error rates; (iv) obtaining, by the one or more processors, a second training dataset; (v) receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and (vi) training, by the one or more processors, a second iteration of the first model using the second training dataset using the feature values defined for the second training dataset to generate secondary first model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0015] In other embodiments, a computer-implemented method for training a second model to predict a seizure of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, a first training dataset; (ii) receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; (iii) training, by the one or more processors, a first iteration of the second model using the first training dataset using thefeature values defined for the first training dataset to generate primary second model output data having associated first error rates; (iv) obtaining, by the one or more processors, a second training dataset; (v) receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and (vi) training, by the one or more processors, a second iteration of the second model using the second training dataset using the feature values defined for the second training dataset to generate secondary second model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0016] In yet other embodiments, a computer-implemented method for training a third model to generate an epileptic insight based upon facial biometrics of a patient. The computer-implemented method may include (i) obtaining, by one or more processors, a first training dataset; (ii) receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; (iii) training, by the one or more processors, a first iteration of the third model using the first training dataset using the feature values defined for the first training dataset to generate primary third model output data having associated first error rates; (iv) obtaining, by the one or more processors, a second training dataset; (v) receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and (vi) training, by the one or more processors, a second iteration of the third model using the second training dataset using the feature values defined for the second training dataset to generate secondary third model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates. The method may include additional, fewer, and / or alternate actions, including actions described in the present disclosure.

[0017] In still yet other embodiments, a first model for identifying a seizure of a patient. The first model may include the first model, stored on one or more memories and configured to be executed by one or more processors, the first model trained using first model training data and operable to: (i) receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; (ii) receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (iii) determine one or more feature values of the EEG data and the facial biometric data; and (iv) based on the one or more feature values, generate first model output data indicating the seizure of the patient. The first model may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0018] In other embodiments, a second model for predicting a seizure of a patient. The second model may include the second model, stored on one or more memories and configured to be executed by one or more processors, the second model trained using second model training data and operable to: (i) receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; (ii) receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (iii) determine one or more feature values of the EEG data and the facial biometric data; and (iv) based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient. The second model may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0019] In yet other embodiments, a third model for generating an epileptic insight based upon facial biometrics of a patient. The third model may include the third model, stored on one or more memories and configured to be executed by one or more processors, the third model trained using third model training data and operable to: (i) receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient; (ii) determine one or more feature values of the facial biometric data; and (iii) based on the one or more feature values, generate third model output data indicating the epileptic insight. The third model may be configured to perform additional, fewer, and / or alternate actions, including various actions described in the present disclosure.

[0020] In still yet other embodiments, a non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to at least: (i) obtain (a) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (b) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (ii) provide the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating a seizure of the patient; and (iii) in response to generating the first model output data, one or more of: (a) provide the first model output data to a user device; or (b) store the first model output data in a memory. The instructions may direct additional, less, or alternate functionality, including that discussed elsewhere herein.

[0021] In other embodiments, a non-transitory computer-readable medium storing processorexecutable instructions that, when executed by one or more processors, cause the one or more processors to at least: (i) obtain (a) electroencephalogram (EEG) data comprising at least one EEGsignal associated with a brain of a patient and gathered via an implant device of the patient; and (b) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; (ii) provide the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data indicating a prediction of a seizure of the patient; and (iii) in response to generating the second model output data, one or more of: (a) provide the second model output data to a user device; or (b) store the second model output data in a memory. The instructions may direct additional, less, or alternate functionality, including that discussed elsewhere herein.

[0022] In yet other embodiments, a non-transitory computer-readable medium storing processorexecutable instructions that, when executed by one or more processors, cause the one or more processors to at least: (i) obtain facial biometric data comprising at least one facial image indicating facial biometrics of a patient; (ii) provide the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating an epileptic insight; and (iii) in response to generating the third model output data, one or more of: (a) provide the third model output data to a user device; or (b) store the third model output data in a memory. The instructions may direct additional, less, or alternate functionality, including that discussed elsewhere herein.

[0023] In accordance with the above, the disclosed systems and methods address the unmet need for using facial biometric data with neurological models, when developing models that operate on facial biometric data, alone, or in conjunction with, EEG data of the patient. Such systems and methods provide comprehensive monitoring, screening, and / or assessments for patients with diagnosed, and undiagnosed, neurological disorders such as epilepsy. In combining the analysis of facial biometrics with correlated EEG data, the disclosed systems and methods enhance the accuracy of epilepsy management and early detection, including techniques to provide:

[0024] holistic patient monitoring, offering a more comprehensive assessment beyond EEG readings when using biometrics, such as facial features and pupil characteristics, to provide a holistic view of the patient’s well-being and health;

[0025] accurate seizure detection, with a quantitative approach to detect and / or substantiate a patient-reported seizure, moving beyond the limited insights of monitored physiological signals alone (e.g., heart rate and movement patterns) when also analyzing associated facial biometric information. The disclosed techniques provide the ability to (more) accurately detect and classify: (i) seizures, that may be particularly crucial for patients with subtle or non-convulsive seizures that might not be easily identified through traditional methods; (ii) seizure types, duration and severity; (iii) medication side-effects; (iv) patient well-being; and / or (v) cognitive brain states;

[0026] personalized treatment plans, based upon closely monitoring the patient's seizure status through facial biometrics, allowing clinicians to make informed decisions about medication adjustments and / or other interventions based on accurate data, and leading to improved patient outcomes;

[0027] early warning systems to detect seizure patterns using facial biometrics, and to provide notifications to a patient and / or a patient healthcare provider of the early warnings, making it possible to promptly take necessary precautions and / or administer rescue medications, potentially reducing the severity and impact of seizures;

[0028] an assessment of drug side-effects on a patient's overall health, such as adverse effects or changes caused by epileptic medications. By tracking physiological parameters and behaviors of the patient over time, clinicians can identify adverse effects or changes caused by such medications; and

[0029] objective seizure reporting using a patient’s biometric data, to make more accurate diagnoses and treatment decisions as compared to using the patients' subjective descriptions of their seizure experiences alone.

[0030] Accordingly, facial biometric information may be utilized to train, retrain, and / or fine-tune models to operate on such information when generating an output, such as models trained to detect health events (e.g., seizures), predict health events, and / or provide epilepsy-related insights, including models otherwise trained to generate such outputs based upon EEG data alone.

[0031] Additional, alternate and / or fewer actions, steps, features and / or functionality may be included in an aspect and / or embodiments, including those described elsewhere herein.BRIEF DESCRIPTION OF THE FIGURES

[0032] Fig. 1 is a block diagram of an example computing environment for using facial biometric data with neurological models, according to the described embodiments.

[0033] Fig. 2 is a block diagram of an example mobile device of the example computer environment of Fig. 1.

[0034] Fig. 3A is a block diagram of an example implant device system, according to the described embodiments.

[0035] Fig. 3B is a block diagram of an example sensor array of the example implant device system of Fig. 3A.

[0036] Fig. 3C depicts an example sensor array including a plurality of electrodes and a local processing device, including an exploded top view of the example electrode device.

[0037] Fig. 3D shows a cross-sectional view of portions of the electrode device of Fig. 3C.

[0038] Fig. 3E is a block diagram depicting in greater detail of an example implant device system implementing static models.

[0039] Fig. 4 is a combined block and logic diagram in which exemplary computer-implemented methods and systems for training a machine learning model are implemented, according to the described embodiments.

[0040] Fig. 5 is a block diagram depicting in greater detail an example implant device system implementing machine learning models.

[0041] Fig. 6 is a block diagram depicting an embodiment in which evaluative functions take place on an external device, rather than on a local processor device.

[0042] Fig. 7A is a flow chart depicting a method for training a first model to generate first model output data indicating a seizure of the patient, according to the described embodiments.

[0043] Fig. 7B is a flow chart depicting a method for training a second model to generate second model output data predicting a seizure of the patient, according to the described embodiments.

[0044] Fig. 7C is a flow chart depicting a method for training a third model to generate third model output data generating an epileptic insight, according to the described embodiments.

[0045] Fig. 8A is a flow chart depicting a method for identifying a seizure of a patient, according to the described embodiments.

[0046] Fig. 8B is a flow chart depicting a method for predicting a seizure of a patient, according to the described embodiments.

[0047] Fig. 8C is a flow chart depicting a method for generating an epileptic insight, according to the described embodiments.

[0048] Fig. 9 depicts an embodiment of the implant device system in which the sensor array and the processor device are integrated into a single unit.

[0049] Fig. 10A illustrates an example communication scheme between the sensor array and the processor device.

[0050] Fig. 10B illustrates an alternate example of a communication scheme between the sensor array and the processor device.

[0051] Fig. 11 A illustrates an example communication scheme between the processor device and external equipment.

[0052] Fig. 11 B illustrates an alternate example of a communication scheme between the processor device and external equipment.

[0053] Fig. 11C illustrates yet another example of a communication scheme between the processor device and external equipment.DETAILED DESCRIPTIONOVERVIEW

[0054] The systems and methods disclosed herein generally relate to using facial biometric data with neurological models. When providing the facial biometric data as an input to the neurological models, the models provide the ability to derive trajectories of neurological health for a patient. Moreover, information associated with the patient’s facial biometrics may compliment and / or enhance determinations, insights, predictions, and the like, otherwise established based upon EEG data alone, thereby providing a more holistic assessment of the patient’s well-being.

[0055] In one embodiment, the disclosed systems and methods may identify a seizure of the patient. This may include obtaining EEG data and facial biometric data of the patient. The EEG data may include at least one EEG signal associated with the patient’s brain and gathered via an implant device of the patient. The facial biometric data may include at least one facial image indicating facial biometrics of the patient, such as photographs and / or video of the patient’s face and / or facial features. At least some of the facial images may be captured while the EEG data is gathered, such that the facial biometrics of the facial biometric data correspond to the EEG of the EEG data.

[0056] The facial biometrics of the patient may indicate and / or include: a change in the patterns of the iris, a pupil dilation that may provide insight into a person's emotional state and cognitive processes, a blinking pattern that may indicate the frequency and duration of blinking, a facial expression providing insight into the patient’s well-being and / or emotional state, a direction of the patient’s gaze that may indicate the patient’s focus, rapid movements of the eye such as nystagmus that may be associated with overuse / prolonged us of epileptic medications, facial flushing, paleness, and / or any other suitable facial biometric. In at least some aspects, the facial biometric data may include facial images that are captured when the patient is not experiencing a seizure, such facial biometrics at times being referred to herein as baseline facial biometrics. Similarly, the EEG data may include baseline EEG of the patient recorded when the patient is not experiencing a seizure. In each case, the baseline facial biometric and / or EEG data may serve as a reference point for comparison with non-baseline facial biometrics and / or non-baseline EEG. For example, if the patient’s facial biometrics and / or their EEG deviates from the baseline, it may be an indication of a seizure, an indication that the patient’s cognitive state is changing due to excessive doses of medications and / or cumulative effects of recurrent seizures, or an indication of some other health event.

[0057] A first model, trained using first model training data, may receive the EEG data and the facial biometric data, to generate first model output data indicating a seizure of the patient. The first model training data may include historical EEG data of historical patients and historical facial biometric data of the historical patients, whereby the first model may be trained to makeassociations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures in the first model training data. The first model output data may include a classification of the seizure (e.g., seizure type, severity, a confidence metric associated with the classification, etc.), at least a portion of the EEG data (e.g., the EEG recorded during the seizure), at least a portion of the facial biometric data (e.g., facial images indicating the facial biometrics during the seizure), a request for at least one additional facial image (e.g., a request for the patient to capture one or more additional facial images potentially indicating the seizure), and / or any other suitable data.

[0058] In response to generating the first model output data, a user device may receive the first model output data. In one example, the user device of the patient receives and displays the first model output data, such as the request for more facial images. In one example, the user device of a caregiver of the patient, such as the patent’s physician, receives and displays the first model output data including the classification of a seizure of the patient, and the EEG and facial biometrics of the patient associated with the classified seizure. Any suitable user device may receive the first model output data. In response to generating the first model output data, the first model output data may be stored in memory, for example stored in the patient’s electronic medical record, stored in a database used to provide medical advice for other patients, stored as training data in database used to train, retrain and / or fine-tune a model, and / or any other suitable purpose.

[0059] In another embodiment, a second model, trained using second model training data, may receive the EEG data and the facial biometric data, to generate second model output data indicating a prediction of a seizure of the patient. The second model training data may include historical EEG data of historical patients and historical facial biometric data of the historical patients, such that the second model may be trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures. The second model output data may include a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, a request for at least one additional facial image. In response to generating the second model output data, the user device may receive the second model output data and / or the second model output data may be stored in memory, as was just described with respect to the first model output data. In at least one aspect, the second model output data may be provided to the user device proximate a time of a predicted seizure. In one example, the second model output data is provided to a user device of the patient to alert them of the predicted seizure, e.g., so they may be prepared for the seizure and out of concern for the safety of the patient. In one example, the second model output data is provided to the patient’s user device for the patient to capture facial biometric images corresponding to the predicted seizure, e.g., the facial biometric images may automatically becaptured when the patient views an alert associated with the second model output data, the patient’s user device may display a request to capture facial biometric images proximate the time of the seizure, etc.

[0060] In yet another embodiment, a third model, trained using third model training data, may receive the facial biometric data, to generate an epileptic insight. The epileptic insight may include an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize side-effects, an indication of a seizure, a prediction of a seizure, a prediction of an epilepsy-related facial biometric event, and / or any other suitable insight. The third model training data may include historical facial biometric data of historical patients, such that the third model may be trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics. The third model output data may include the epileptic insight and / or a request for at least one additional facial image. In at least one aspect, the third model may be trained to also receive and operate on the EEG data, in addition to the facial biometric data, to generate the third model output data. In response to generating the third model output data, the user device may receive the third model output data and / or the third model output data may be stored in memory, as was just described with respect to the first and second model output data. For example, the epileptic insight may predict the patient will experience a facial biometric event (e.g., facial gazing or pupil dilation), and based upon the epileptic insight, the patient may be prompted (e.g., via an alert on the user device) to capture facial biometric images which can be compared to the predicted facial biometrics. If the facial biometric images do not indicate the predicted facial biometric event, the facial biometric images may be used to retrain / fine-tune the third model, and / or the patient’s EEG recorded when the facial biometric images are captured may be analyzed to identify correlations, patterns, and / or signal features in the EEG.

[0061] In at least one aspect, the output data of any of the first, second and / or third models may:

[0062] be provided to a physician to enable treatment options for the patient;

[0063] be used to generate training data for one or more models;

[0064] be used to relabel existing training data labels associated with determining the relevancy of an EEG event;

[0065] trigger a human (re)review off EEG not previously flagged as being abnormal when it correlates with abnormal facial biometrics (e.g., biometrics indicating a seizure), potentially leading to the identification of new EEG patterns that can be used to train models and / or train clinicians to identify the new patterns in subsequent review of EEG data;

[0066] forecast biometric events and / or seizures, and also alert the patient or a patient healthcare provider of the forecast; and / or

[0067] provide guidance for physicians when treating specific neurological pathologies across multiple patients.

[0068] Although epilepsy is disclosed as an example neurological disorder above as well as in other portions of the disclosure, the disclosed embodiments and techniques may be applicable to other neurological disorders and / or other fields of use.

[0069] Various aspects of the systems and methods are described throughout this specification. Unless otherwise specified, aspects of any embodiment that are compatible with another embodiment described herein are considered as contemplated and disclosed embodiments herein, especially as described in the list of aspects at the end of this specification. For example, a feature of a particular embodiment described herein, if that feature would be recognized by a person of ordinary skill in the art to be compatible with the features of a second embodiment described herein, should be considered as a possible feature of the second embodiment. Further, embodiments describing features as optional should be considered as disclosing said embodiments both with and without the optional features, and with various optional features in any combination that would be recognized by a person of ordinary skill in the art as being compatible.

[0070] Throughout the present disclosure, embodiments are described in which various elements are optional - present in some, but not all, embodiments of the system. Where such elements are depicted in the accompanying figures and, specifically, in figures depicting block diagrams, the optional elements are generally depicted in dotted lines to denote their optional nature.EXAMPLE COMPUTER ENVIRONMENT

[0071] Fig. 1 depicts an example computing environment 100 associated with using facial biometric data with neurological models. Although Fig. 1 depicts certain entities, components, equipment, and devices, it should be appreciated that additional or alternate entities, components, equipment, and devices are envisioned.

[0072] As illustrated in Fig. 1 , the computing environment 100 may include in one aspect, one or more servers 105 that may perform at least some of the functionalities and techniques disclosed, such detecting a seizure, predicting a seizure, and / or determining an epileptic insight. The server 105 may be part of a cloud network or may otherwise communicate with other hardware or software components within one or more cloud computing environments to send, receive, retrieve, and / or otherwise analyze data or information described herein. For example, in certain aspects of the present techniques, the computing environment 100 may comprise an on-premise computing environment, a multi-cloud computing environment, a public cloud computing environment, a private cloud computing environment, and / or a hybrid cloud computing environment. For example, an entity (e.g., a business) may host one or more services in a public cloud computing environment(e.g., Alibaba Cloud, Amazon Web Services (AWS), Google Cloud, IBM Cloud, Microsoft Azure, etc.). The public cloud computing environment may be a traditional off-premise cloud (i.e. , not physically hosted at a location owned / controlled by the business). Alternatively, or in addition, aspects of the public cloud may be hosted on-premise at a location owned / controlled by the business. The public cloud may be partitioned using visualization and multi-tenancy techniques and may include one or more infrastructure-as-a-service (laaS) and / or platform-as-a-service (PaaS) services.

[0073] A network 110 may comprise any suitable network or networks, including a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof. For example, the network 110 may include a wireless cellular service (e.g., 4G, 5G, 6G, etc.). Generally, the network 110 enables bidirectional communication between the servers 105, a user device 115 and / or an implant device 150. In one aspect, the network 110 may comprise a cellular base station, such as cell tower(s), communicating to the one or more components of the computing environment 100 via wired / wireless communications based upon any one or more of various mobile phone standards, including NMT, GSM, CDMA, UMTS, LTE, 5G, 6G, or the like. Additionally or alternatively, the network 110 may comprise one or more routers, wireless switches, or other such wireless connection points communicating to the components of the computing environment 100 via wireless communications based upon any one or more of various wireless standards, including by non-limiting example, IEEE 802.11 a / ac / ax / b / c / g / n (Wi-Fi), Bluetooth, and / or the like.

[0074] Communication circuitry 122 may communicate over the network 110 via any suitable wired and / or wireless connection, e.g., using any suitable network interface controller(s) of the communication circuitry 122. The communication circuitry 122 may include one or more transceivers (e.g., WWAN, WLAN, and / or WPAN transceivers) functioning in accordance with IEEE standards, 3GPP standards, and / or other standards, and that may be used in receipt and transmission of data via external / network ports connected to computer network 110.

[0075] The server 105 may include at least one processor 120. The processor 120 may include one or more suitable processors (e.g., central processing units (CPUs) and / or graphics processing units (GPUs)). The processor 120 may be connected to a memory 125 via a computer bus (not depicted) responsible for transmitting electronic data, data packets, or otherwise electronic signals to and from the processor 120 and the memory 125 in order to implement or perform the machine- readable instructions, methods, processes, elements, or limitations, as illustrated, depicted, or described for the various flowcharts, illustrations, diagrams, figures, and / or other disclosure herein. The processor 120 may interface with the memory 125 via a computer bus to execute an operating system and / or computing instructions contained therein, and / or to access other services / aspects. For example, the processor 120 may interface with the memory 125 via the computer bus to create,read, update, delete, or otherwise access or interact with the data stored in the memory 125 and / or a database 126.

[0076] The memory 125 may include one or more forms of volatile and / or non-volatile, fixed and / or removable memory, such as read-only memory (ROM), electronic programmable read-only memory (EPROM), random access memory (RAM), erasable electronic programmable read-only memory (EEPROM), and / or other hard drives, flash memory, MicroSD cards, and others. The memory 125 may store an operating system (e.g., Microsoft Windows, Linux, UNIX, etc.) capable of facilitating the functionalities, applications, methods, or other software as described herein.

[0077] In general, a computer program or computer based product, application, or code (e.g., machine learning (ML) models, or other computing instructions described herein) may be stored on a computer usable storage medium, or tangible, non-transitory computer-readable medium (e.g., standard random access memory (RAM), an optical disc, a universal serial bus (USB) drive, or the like) having such computer-readable program code or computer instructions embodied therein, wherein the computer-readable program code or computer instructions may be installed on or otherwise adapted to be executed by the processor(s) 120 (e.g., working in connection with the respective operating system in memory 125) to facilitate, implement, or perform the machine readable instructions, methods, processes, elements or limitations, as illustrated, depicted, or described for the various flowcharts, illustrations, diagrams, figures, and / or other disclosure herein. In this regard, the program code may be implemented in any desired program language, and may be implemented as machine code, assembly code, byte code, interpretable source code or the like (e.g., via Golang, Python, C, C++, C#, Objective-C, Java, Scala, ActionScript, JavaScript, HTML, CSS, XML, etc.).

[0078] The memory 125 may include at least one database 126. The database 126 may be a relational database, such as Oracle, DB2, MySQL, a NoSQL based database, such as MongoDB, or another suitable database. The database 126 may store data, such as model output data, patient medical records storing the model output data, data that is used to create, (re)train, operate, and / or fine-tune one or more models, such as testing, validation, feedback, and / or other model training data, and / or any other suitable data.

[0079] The memory 125 and / or the database 126 may include one or more routines or models 128. A model 128, routine, or other element stored in memory may be referred to as receiving an input, producing or storing an output, or executing, the routine, model 128, or other element. The model 128 is, in fact, executing as instructions on the processor 120. Further, those of skill in the art will appreciate that the model 128, routine, or other instructions may be stored in the memory 125 as executable instructions, which instructions the processor 120 may retrieve from the memory 125 and execute. Further, the processor 120 should be understood to retrieve from the memory125 any data necessary to perform the executed instructions (e.g., data required as an input to the routine or model 128), and to store in the memory 125 the intermediate results and / or output of any executed instructions. The model 128 may include models based on a static algorithm (e.g., a static model), or ML models, such as one or more ML models 130, as further described below.

[0080] The memory 125 may store a plurality of computing modules 135, implemented as respective sets of computer-executable instructions (e.g., one or more source code libraries, trained ML models 130 such as neural networks, convolutional neural networks, etc.), as described herein.

[0081] In one aspect, the computing modules 135 may include an ML module 140. The ML module 140 may include ML training module (MLTM) 142 and / or ML operation module (MLOM) 144. In some embodiments, at least one of a plurality of ML methods and algorithms may be applied by the ML module 140, that may include, but are not limited to: linear or logistic regression, instance-based algorithms, regularization algorithms, decision trees, Bayesian networks, cluster analysis, association rule learning, artificial neural networks, deep learning, combined learning, reinforced learning, dimensionality reduction, and support vector machines. In various embodiments, the implemented ML methods and algorithms are directed toward at least one of a plurality of categorizations of ML, such as supervised learning, unsupervised learning, and reinforcement learning. In one aspect, the ML-based algorithms may be included as a library or package executed on server(s) 105. For example, libraries may include the TensorFlow-based library, the PyTorch library, and / or the scikit-learn Python library.

[0082] In one embodiment, the ML module 140 employs supervised learning, that involves identifying patterns in existing data to make predictions about subsequently received data. Specifically, the ML module is “trained” (e.g., via MLTM 142) using training data, that includes exemplary inputs and associated exemplary outputs. Based upon the training data, the ML module 140 may generate a predictive function that maps outputs to inputs and may utilize the predictive function to generate ML outputs based upon data inputs. The exemplary inputs and exemplary outputs of the training data may include any of the data inputs or ML outputs described above. In the exemplary embodiments, a processing element may be trained by providing it with a large sample of data with known characteristics or features.

[0083] In another embodiment, the ML module 140 may employ unsupervised learning, that involves finding meaningful relationships in unorganized data. Unlike supervised learning, unsupervised learning does not involve user-initiated training based upon exemplary inputs with associated outputs. Rather, in unsupervised learning, the ML module 140 may organize unlabeled data according to a relationship determined by at least one ML method / algorithm employed by the ML module 140. Unorganized data may include any combination of data inputs and / or ML outputs as described above.

[0084] In yet another embodiment, the ML module 140 may employ reinforcement learning, that involves optimizing outputs based upon feedback from a reward signal. Specifically, the ML module 140 may receive a user-defined reward signal definition, receive a data input, utilize a decisionmaking model to generate the ML output based upon the data input, receive a reward signal based upon the reward signal definition and the ML output, and alter the decision-making model so as to receive a stronger reward signal for subsequently generated ML outputs. Other types of ML may also be employed, including deep or combined learning techniques.

[0085] The MLTM 142 may receive labeled data at an input layer of a model having a networked layer architecture (e.g., an artificial neural network, a convolutional neural network, etc.) for training the ML models 130. The received data may be propagated through one or more connected deep layers of the ML model 130 to establish weights of one or more nodes, or neurons, of the respective layers. Initially, the weights may be initialized to random values, and one or more suitable activation functions may be chosen for the training process. The present techniques may include training a respective output layer of the ML models 130. The output layer may be trained to output a prediction, for example.

[0086] The MLOM 144 may comprise a set of computer-executable instructions implementing ML loading, configuration, initialization and / or operation functionality. The MLOM 144 may include instructions for storing trained ML models 130 (e.g., as ML models 130 in memory 125). As described, once trained, the trained ML models 130 may be operated in inference mode, whereupon when provided with de novo input that the model has not previously been provided, the model may output one or more predictions, classifications, etc., as described herein.

[0087] In operation, the ML model training module 142 may access the database 126 or any other data source for training data suitable to generate the ML models 130. The training data may be sample data with assigned relevant and comprehensive labels (classes or tags) used to fit the parameters (weights) of the ML model 130 with the goal of training it by example. In one aspect, once an appropriate ML model 130 is trained and validated to provide accurate predictions and / or responses, the trained ML model 130 may be loaded into MLOM 144 at runtime to process input data and generate output data.

[0088] While various embodiments, examples, and / or aspects disclosed herein may include training and generating the ML models 130 for the server 105 to load at runtime, it is also contemplated that one or more appropriately trained ML models 130 may already exist (e.g., in memory 125) such that the server 105 may load an existing trained ML model 130 at runtime. It is further contemplated that the server 105 may retrain, fine-tune, update and / or otherwise alter an existing ML model 130 before and / or after loading the model at runtime.

[0089] In one aspect, the computing modules 135 may include an input / output (I / O) module 148, comprising a set of computer-executable instructions implementing communication functions. The I / O module 148 may include a communication component configured to communicate (e.g., send and receive) data via one or more external / network port(s) to one or more networks or local terminals, such as the computer network 110 and / or the user device 115 (for rendering or visualizing) described herein. In one aspect, the servers 105 may include a client-server platform technology such as ASP.NET, Java J2EE, Ruby on Rails, Node.js, a web service or online API, responsive for receiving and responding to electronic requests.

[0090] I / O module 148 may further include or implement an operator interface configured to present information to an administrator or operator and / or receive inputs from the administrator and / or operator. An operator interface may provide a display screen. The I / O module 148 may facilitate I / O components (e.g., ports, capacitive or resistive touch sensitive input panels, keys, buttons, lights, LEDs), that may be directly accessible via, or attached to, servers 105 or may be indirectly accessible via or attached to the user device 115. According to one aspect, an administrator or operator may access the servers 105 via the user device 115 to review information, make changes, input training data, initiate training via the MLTM 142, and / or perform other functions (e.g., operation of the one or more trained ML models 130 via the MLOM 144).

[0091] The one or more servers 105 may be in communication with at least one user device 115, e.g., the user device associated with a patient, a doctor, a clinician, a caregiver, etc. The user device 115 may comprise one or more computers, that may comprise multiple, redundant, or replicated client computers accessed by one or more users. The user device 115 may access services or other components of the computing environment 100 via the network 110, as further described herein. The user device 115 may be and / or include one or more mobile devices, wearables, smart watches, smart contact lenses, smart glasses, AR glasses / headsets, VR glasses / headsets, mixed or extended reality glasses / headsets, displays, display screens, visuals, and / or other electronic or electrical components or devices. The user device 115 may include a memory and a processor for, respectively, storing and executing one or more modules, programs, routines, etc. The memory may include one or more suitable storage media such as a magnetic storage device, a solid-state drive, random access memory (RAM), etc. The user device 115 may include one or more sensors, such as a microphone, a camera, an infra-red sensor, an accelerometer, etc., one or more of which may be used to generate the facial biometric data. The user device 115 may include communication circuitry to access services or other components of the computing environment 100, e.g., via the network 110.

[0092] The one or more servers 105 may also be in communication with at least one implant device 150. The implant device 150 may use communication circuitry to access services or othercomponents of the computing environment 100, e.g., via the network 110. The implant device 150 may include a memory and a processor for, respectively, storing and executing one or more modules, programs, routines, etc. The memory may include one or more suitable storage media such as a magnetic storage device, a solid-state drive, random access memory (RAM), etc. The implant device 150 may include a sensor array. The sensor array generally provides data in the form of one or more electrical signals, such as EEG data in the form of EEG signals, to a processor device of the implant device 150, that receives the signals. The electrical signals may be processed (e.g., via a processor of the implant device 150, or other suitable processor) and / or provided to one or more other devices (e.g., the server 105, the user device 115, a processor device, etc.), e.g., to detect, classify and / or predict a health event (e.g., seizure) indicated by the EEG data, and / or for any other suitable purpose.

[0093] The implant device 150 may gather EEG data from the brain activity of a patient in whom the sensor array of the implant device 150 is implanted. The implant device 150, via its communication circuitry, may transmit (e.g., via the network 110) the EEG data to one or more components and / or devices of the computing environment, such as the server 105, the user device 115, and / or any other suitable device or component. The server 105, the user device 115 and / or other suitable device may provide the EEG data as an input to one or more models 128, 130.

[0094] In at least one embodiment, the computing environment 100 may be used to identify a seizure of the patient. The implant device 150 may gather the EEG data of the patient, and provide the EEG data to the server via the network 110, to be operated on by the first model, such as the models 128, 130. The user device 115 may generate the facial biometric data of the patient (e.g., via facial images of the patient captured with the user device camera), although any other device capable of generating the biometric data may be used. The user device 115 may provide the facial biometric data to the server via the network 110, to be operated on by the first model. Although in the embodiment being described the server 105 executes the first model, in alternate embodiments the implant device 150, the user device 115, and / or any other suitable device and / or processor of the computing environment 100 may execute the first model. In such alternate embodiments, the device / processor executing the first model may receive the facial biometric data and the EEG data (e.g., from one or more of the implant device 150, the user device 115, from the database 126, etc.), and provide the EEG data and facial biometric data to the first model.

[0095] Referring again to an embodiment in which the server 105 executes one or more of the models, the server 105 may load the first model from memory (e.g., from the models 128, 130 in the memory 125) via the ML module 140. The server 105 may provide the EEG data and the facial biometric data to the first model, via the ML module 140, to generate the first model output data indicating the seizure. The first model output data may include a classification of the seizure, theEEG associated with the identified seizure, the facial images associated with the seizure, a request for one or more additional facial images, and / or any other suitable data. In response to generating the first model output data, the server 105 may provide, via the network 110, the first model output data to one or more user devices 115, such as a user device 115 of the patient, a healthcare provider of the patient, and / or any other suitable user device 115. In response to generating the first model output data, the server 105 may store the first model output data in one or more memories, such as the memory 125 and / or the database 126.

[0096] In at least one aspect, the first model may identify the seizure in both the EEG data (e.g., based on patterns in the EEG) and the facial biometric data (e.g., based upon facial biometric patterns). In response to identifying the seizure in the EEG data and the facial biometric data, the server 105 may apply one or more labels associated with the seizure, to the first model output data, the EEG data, and / or the facial biometric data. The labels may include labels indicating the type / classification of seizure, features of the EEG indicating the seizure, biometric features of the facial images indicating the seizure, and / or any other suitable labels. The labels may be determined by the server 105 (e.g., via the ML module 140), by a human reviewer of the data, and / or in any other suitable manner.

[0097] In another aspect, in response to the first model identifying the seizure in the facial biometric data only, i.e. , not identifying the seizure the EEG data, the server 105 may identify an EEG pattern in the EEG data corresponding to the seizure. In one example, a portion of the EEG of the EEG data may correspond to facial biometric images of the facial biometric data, the correspondence indicating the EEG is recorded during the same time that the facial biometric images are captured. The first model identifies the seizure of the patient based upon their facial biometric images (e.g., biometrics of the eye or face which deviate from the patient’s baseline facial biometrics), but the first model does not detect the seizure in the patient’s corresponding portion of the EEG. This being the case, the corresponding portion of the EEG is reviewed by a human reviewer and / or operated on by an algorithm, model, or the like, to determine pattern(s) in the EEG (e.g., EEG sharps and spikes) that do correspond to the seizure detected in the facial biometric images. In one aspect, the patterns in the portion of the EEG may include patterns which were originally classified / labelled as non-clinical or non-symptomatic, but are reclassified / relabeled as indicating the seizure. In one aspect, patterns indicating the seizure in the portion of the EEG may not have been originally identified, but upon review patterns indicating the seizure are identified, and the newly-identified patterns are classified / labeled as indicating the seizure. In either example, the portion of the EEG data indicating the seizure may be used to retrain the first model (e.g., so the first model subsequently detects and / or correctly identifies the EEG patterns associated with the seizure), and / or used for any other suitable purpose.

[0098] In yet another aspect, in response to the first model identifying the seizure in the EEG data only, i.e. , not identifying the seizure the facial biometric data, the server 105 may identify a facial biometric pattern in the facial biometric data corresponding to the EEG data indicating the seizure. For example, five facial images of the facial biometric data may be taken at the same time the EEG that indicates the seizure is recorded. The five facial images may be reviewed by a human reviewer and / or their associated data operated on by an algorithm, model, or the like, to determine a biometric pattern (e.g., changes in pupil dilation and facial expression) in the five facial images that do correspond to the seizure detected by the EEG data. The patterns in the facial biometric data may be labeled, used to retrain the first model (e.g., via ML module 140), and / or used for any other suitable purpose. Again, although the embodiment and aspects just described disclose the server 105 performing operations in response to the first model identifying the seizure in the EEG data and / or the facial biometric data, other devices or components of the computing environment 100 may perform such operations, such as the user device 115.

[0099] In another embodiment, the computing environment 100 may be used to predict a seizure of the patient. The user device 115 may provide to the server 105, via the network 110, the EEG data gathered by the implant device 150, and the facial biometric data captured by the user device 115, as just described with respect to the first model. The server 105 may execute a second model (e.g. models 128, 130) via the ML module 140, and provide the EEG data and facial biometric data to the second model to generate the second model output data indicating the prediction of the seizure. The second model output data may include a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, a request for at least one additional facial image, and / or other suitable data. In response to generating the second model output data, the server 105 may provide, via the network 110, the second model output data to one or more user devices 115, e.g., of the patient, a healthcare provider of the patient, and / or other suitable user device 115. In response to generating the second model output data, the server 105 may store the second model output data in one or more memories, such as the memory 125 and / or the database 126.

[0100] In still yet another embodiment, the computing environment 100 may be used to generate an epileptic insight, such as an indication the patient is experiencing side-effects of epilepsy medication, a suggested time to take the epilepsy medication to minimize side-effects, an indication of a seizure, a prediction of the seizure, a prediction of an epilepsy-related facial biometric event, and / or other suitable epileptic insight. The user device 115 may provide to the server 105, via the network 110, the facial biometric data captured by the user device 115, as just described with respect to the first model. The server 105 may execute a third model (e.g. models 128, 130) via the ML module 140, and provide the facial biometric data to the third model to generate the third modeloutput data indicating the epileptic insight. In response to generating the third model output data, the server 105 may provide via the network 110 the third model output data to the user device 115 of the patient, a healthcare provider of the patient, and / or other suitable user device 115. In response to generating the third model output data, the server 105 may store the second model output data in one or more memories, such as the memory 125 and / or the database 126.

[0101] The model output data of any of the first, second, or third models may be used as training data, e.g., to (re)train and / or fine-tune a model, used to provide healthcare to multiple patients (e.g., stored in a database used to determine healthcare recommendations for patients), and / or for any other suitable purpose. In an aspect where the model output data is used to retrain the model that generates the output data, the retrained model may be stored in a memory (e.g., the memory 125, the database 126) to provide subsequent model output data.

[0102] Although the computing environment 100 is shown to include one each of the server 105, the network 110, the user device 115, and the implant device 150, it should be understood that different numbers of servers 105, networks 110, user devices 115, and / or implant devices 150 may be included in the computing environment 100. In one example, the computing environment 100 may include a plurality of servers 105, thousands of user devices 115, and hundreds of implant devices 150, all of which may be interconnected via the network 110.

[0103] The computing environment 100 may include additional, fewer, and / or alternate components, and may be configured to perform additional, fewer, or alternate actions, including components / actions described herein. Although the computing environment 100 is shown in Fig. 1 as including one instance of various components such as user device 115, server 105, network 110, etc., various aspects include the computing environment 100 implementing any suitable number of any of the components shown in Fig. 1 and / or omitting any suitable ones of the components shown in Fig. 1. For instance, information described as being stored in the database 126 may be stored in the memory 125, and therefore the database 126 may be omitted. Moreover, various aspects include the computing environment 100 including any suitable additional component(s) not shown in Fig. 1 , such as but not limited to the exemplary components described above. Furthermore, it should be appreciated that additional and / or alternative connections between components shown in Fig. 1 may be implemented. As just one example, the user device 115 and the implant device 150 may be connected via a direct communication link (not shown in Fig. 1) instead of, or in addition to, via network 110.EXAMPLE COMPUTING DEVICE

[0104] Referring now to Fig. 2, in one embodiment the user device 115 may include a computing device 215, such as a laptop computer, smartphone, desktop computer, smartwatch, wearable,augmented reality device, virtual reality device, etc. The computing device 215 may include a display 240, a controller 242, one or more sensors 256, communication circuitry 258 such as communication circuitry 122, and a user-input device (not shown).

[0105] The controller 242 may include a program memory 246 (e.g., such as the memory 125 and / or the database 126), a microcontroller / processor / microprocessor (pP) 248 (e.g., such as the processor 120), a random-access memory (RAM) 250 (e.g., such as the memory 125), and / or an input / output (I / O) module 254 (e.g., such as the I / O module 148), all of which may be interconnected via an address / data bus 252. The program memory 246 may include an operating system 260, a data storage 262 (e.g., such as the memory 125 and / or the database 126), a plurality of software applications 264, and / or a plurality of software routines 268. The operating system 260 may be an operating system as previously described with respect to server 105, a mobile operating system such as iOS® or Android™ developed by Apple Inc. and Google Inc., respectively, and / or any other suitable operating system.

[0106] The computing device 215 may include one or more sensors 256. Exemplary sensors 256 may include one or more accelerometers, gyroscopes, inertial measurement units (IMUs), GPS units, proximity sensors, infrared sensors, cameras, microphones, as well as any other suitable sensors. Additionally, other types of currently available or later-developed sensors may be included in some embodiments. The sensors 256 may be used to capture the facial biometric data of the patient (e.g., facial images), data regarding the physical environment of the patient, and / or any other suitable data. The sensors 256 may be integrated with the computing device 215, and / or communicatively coupled to the computing device 215. The data the sensors 256 generate may be stored in memory, such as the memory 246, 250, provided to one or more devices, such as to the server 105 via the network 110, etc.

[0107] The communication circuitry 258 may communicate with the one or more servers 105, user devices 115, implant devices 150, or another suitable device or devices via any suitable wired or wireless communication protocol network, such as those described with respect to communication circuitry 122, such as a wireless telephony network (e.g., GSM, CDMA, LTE, 5G, 6G, UWB etc.), a Wi-Fi network (802.11 standards), a WiMAX network, a LAN, Ethernet, a Bluetooth network, etc. The user-input device (not shown) may include a “soft” keyboard that is displayed on the display 240 of the computing device 215, an external hardware keyboard communicating via a wired and / or a wireless connection (e.g., a Bluetooth keyboard), an external mouse, a touchscreen, a stylus, and / or any other suitable user-input device.

[0108] It should be appreciated that although Fig. 2 depicts, for example, one controller 242, one processor 248, one display 240, etc., the computing device 215 may include controllers 242, multiple processors 248, multiple displays 240, etc. Similarly, the memory of the controller 242 mayinclude multiple RAMs 250 and / or multiple program memories 246. Although Fig. 2 depicts the I / O circuit 254 as a single block, the I / O circuit 254 may include a number of different types of I / O circuits. The controller 242 may implement the RAM(s) 250 and / or the program memories 246 as semiconductor memories, magnetically readable memories, and / or optically readable memories, for example.

[0109] The one or more processors 248 may be adapted and / or configured to execute any one or more of the plurality of software applications 264 and / or any one or more of the plurality of software routines 268 residing in the program memory 242, in addition to other software applications. The software applications 264 and / or software routines 268 may be implemented as a series of machine-readable instructions executed by the processor 248.

[0110] One of the plurality of applications 264 may be a client application 266, e.g., an application for using facial biometric data with neurological models such as the models 128, 130, an application associated with the implant device 150, etc. The client application 266 may perform various tasks associated with the implant device 150, the models 128, 130 and / or the server 105, such as receiving data from, transmitting information to, and / or displaying information associated with, such components, among other things. In one aspect, the client application 266 may be used by the patient to capture facial biometric images. In such an aspect, the client application 266 may provide visual stimuli to the patient via the display 240, and capture facial biometric images using the sensor 256 (e.g., camera) to assess the focus of the patient’s eye(s) in response to the stimuli. The facial biometric images may be used (e.g., by the models 128, 130) to assess the patient’s ability to track the movement with their eye(s). Poor tracking may indicate a change in cognitive state or side-effects of drugs, which the client application 266 may then indicate, such as via a message displayed on the computing device 215, a message sent by the computing device 215 via the network 110 to a user device 115 of the patient’s physician, and / or in any other suitable manner. In one aspect, the client application 266 may be used to flag one or more facial biometric images for review, such as review by a human reviewer (e.g., a clinician) and / or model / algorithm (e.g., the models 128, 130). For example, the patient may notice, or the client application 266 may detect, facial biometric images which deviate from the patient’s baseline facial biometric images. In one example, this may include long-term facial biometrics which deviate from the patient’s baseline, which may not be detected (e.g., by the models 128, 130) when analyzing short-term facial biometrics. By flagging the facial biometric images which deviate from the baseline, e.g., using the client application 266, the client application 266 may generate a signal which is sent to the server 105, the user device 115 of a caregiver of the patient, etc. The signal may indicate the flagged facial biometric images, and / or the EEG corresponding thereto, should be further reviewed, e.g., toidentify patterns (which may otherwise go undetected) indicating a health event such as a seizure, excessive doses of medication, cumulative effects of recurrent seizures, etc.

[0111] One of the plurality of applications 264 may be a native application and / or web browser 270, such as Apple’s Safari®, Google Chrome™ mobile web browser, that may be implemented as a series of machine-readable instructions for receiving, interpreting, and / or displaying application screens or web page information from the one or more servers 105 while also receiving inputs from the user. Another application of the plurality of applications may include an embedded web browser 276 that may be implemented as a series of machine-readable instructions for receiving, interpreting, and / or displaying web page information.

[0112] In one aspect, a user may launch a client application 266 from a client device, such as one of the user devices 115, to communicate with the one or more servers 105. In one example, the client application 266 may provide access to (e.g., capturing, downloading, viewing, annotating, labeling, providing feedback on, etc.) the facial biometric data generated by the computing device 215, the EEG data generated by the implant device 150, models output data, model training data, and / or any other suitable data. Additionally, the user may also launch or instantiate any other suitable user interface application (e.g., the native application or web browser 270, and / or any other one of the plurality of software applications 264) to access the one or more servers 105 to realize aspects of the inventive system.

[0113] The computing device 215 may include additional, fewer, and / or alternate components, and may be configured to perform additional, fewer, or alternate actions, including components / actions described herein. Although the computing device 215 is shown in Fig. 2 as including one instance of various components such as display 240, processor 248, etc., various aspects include the computing device 215 implementing any suitable number of any of the components shown in Fig. 2 and / or omitting any suitable ones of the components shown in Fig. 2. Moreover, various aspects include the computing device 215 including any suitable additional component(s) not shown in Fig. 2, such as but not limited to the exemplary components described above. Furthermore, it should be appreciated that additional and / or alternative connections between components shown in Fig. 2 may be implemented.EXAMPLE IMPLANT DEVICE SYSTEM

[0114] Fig. 3A depicts, in its simplest form, a block diagram of the implant device system 300, such as implant device 150. The implant device system 300 includes a sensor array 302, a processor device 304, and a user interface 306. The sensor array 302 generally provides data, in the form of electrical signals, to the processor device 304. The user interface 306 may facilitate self-reporting by the patient of any of various data including events perceived by the patient, as wellas medication types, doses, dose times, patient mood, potentially relevant environmental data, and the like. The user interface 306 may also facilitate programming of the unit, calibration of the sensor array 302, providing feedback to the patient (e.g., haptic, vibratory feedback warning of a potential impending health event), etc.

[0115] Turning now to Fig. 3B, the implant device system 300 is presented as a block diagram in greater detail. The sensor array 302 may include a local processing / memory device 344 and a plurality of electrode devices 310A-D, each including an electrode 312. The local processing device / memory 344 may include an electrical amplifier 346 (e.g., pre-amp), a battery 348, battery charging technology 349, a transceiver 350, an analog-to-digital converter (ADC) 352, and a processor 354 to process electrical signals (e.g., EEG signals indicative of brain activity of the patient) received from or transmitted to the electrodes devices 310A-D.

[0116] The local processing device 344 may include a battery 348 and battery charging technology 349 to power the local processing device 344, among other things. The battery charging technology 349 may include a battery charging circuit, for facilitating charging of the battery 348. The battery charging technology 349 may be any known battery charging technology compatible with the arrangement of the sensor array 302. In particular, in embodiments the battery technology 349 may be an inductive charging circuit that facilitates charging through the patient’s skin when the sensor array 302 is disposed beneath the scalp of the patient. In other embodiments, the battery technology 349 may draw energy from the movements of the patient throughout the day by, for example, harnessing the movements of the patient to turn a small generator. In still other embodiments, the battery technology 349 may draw power from the environment in the form of RF signals. In further examples still, the battery technology 349 may draw power from chemical reactions taking place in the environment of the sensor array 302. Of course, more traditional charging methods (e.g., using a wired connection to provide power to the battery technology 349) may also be employed.

[0117] The local processing device 344 may include a transceiver 350, such as a transceiver receiver / transmitter pair that facilitates communication with other various devices (e.g., in a wired and / or wireless manner). The local processing device 344 may include a memory 355 to store EEG data, and / or any other suitable data. The local processing device 344 may be similar to a processing device of a type commonly used with cochlear implants, although other configurations are possible.

[0118] The data processed and stored by the local processing device 344 may be raw (e.g., unprocessed) EEG signal(s) or partially processed (e.g., partially or fully compressed) EEG signal(s), for example. The EEG signal(s) may be processed and / or otherwise converted to EEG data by the local processing device 344, e.g., via the ADC 352, although as used herein the termsEEG signal(s), EEG, and EEG data may, in instances, be used interchangeably. The EEG data may be transmitted from the local processing device 344 wirelessly, or via a wire / in a wired manner, to the processor device 304 for further storage, processing, and / or analyzing of the EEG data. The processor device 304 may analyze (e.g., via one or more models, such as a models 128, 130) the EEG data (or other electrical signals) and / or the facial biometric data to identify a seizure, predict a seizure, etc., among other things. Data may be generated by the processor device 304 on the basis of the analysis, such as the first, second, and / or third model output data, etc.

[0119] By carrying out data analysis externally to the sensor array 302, using the processor device 304, for example, there may be a reduction in power consumption within the sensor array 302, enabling the sensor array 302 to retain a smaller geometrical form. Moreover, the processor device 304 may have significantly higher processing power than would be possible with any processor included in the sensor array 302. The processor device 304 may run software that continuously records electrical data received from the sensor array 302. In other embodiments, the sensor array 302 and / or processor device 304 may store the EEG data to, and / or retrieve the EEG data from, a memory at one or more times, e.g., the memory 125, the database 126, the memory 355, and / or any other suitable memory. In such embodiments, the EEG data, and potentially the facial biometric data, may be processed by the processor device 304 at any suitable time, e.g., the processor device 304 may retrieve the EEG data, and potentially the facial biometric data, of the patient from one or more memories several hours after it is recorded, for processing by one or more models.

[0120] The following description of the sensor array 302 is illustrative in nature. While one of skill in the art would recognize a variety of sensor arrays that may be compatible with the described embodiments, the sensor arrays 302 explicitly described herein may have particular advantages and, in particular, the sensor arrays 302 may include the sensors described in U.S. Patent Application 16 / 125,152 (U.S. Patent Application Publication No. 2019 / 0053730 A1) and U.S. Patent Application 16 / 125,148 (U.S. Patent No. 10,568,574) the specifications of each being hereby incorporated herein by reference, for all purposes. Alternative embodiments of the sensor array 102 are contemplated, such as that described in U.S. Patent Application No. 16 / 797,315, entitled “Electrode Device for Monitoring and / or Stimulating Activity in a Subject,” the entirety of which is hereby incorporated by reference herein.

[0121] Turning to Fig. 3C, an electrode device 310 is provided comprising an elongate, implantable body 342 and a plurality of electrodes 312 positioned along the implantable body 342 in the length direction of the implantable body 342. At a proximal end of the implantable body 342, a processing unit 344 is provided for processing electrical signals that can be sent to and / or received from the electrodes 312. Though not required, in some embodiments, an electrical amplifier 346 ispositioned in the implantable body 342 between the electrodes 312 and the processing unit 344. In an alternative embodiment, the electrical amplifier 346 may be integrated into the processing unit 344 of the electrode device 310, instead of being positioned in the implantable body 342. A plurality of anchors 313 may be positioned along a length of the implantable body 342, each adjacent a respective one of the electrodes 312. The anchors 313 may be designed to provide stabilization to the electrode device 310 when it is in the implantation position.

[0122] Fig. 3C depicts the electrode device 310 as having four electrodes 312 in the embodiment to a local processing device 344. Of course, in different embodiments, more or fewer numbers of electrodes 312 may be implemented, according to the needs of the electrical signals required for the implementation of the methods described herein. In particular, the electrode device 310 may include, in embodiments, four (4), eight (8), ten (10), twelve (12), sixteen (16), twenty (20), twenty- four (24), or more electrodes 312. In the embodiment depicted, the local processing device 344 and electrode 312 are formed in the electrode device 310 as a one-piece construct. The arrangement is such that the local processing device 344 and the electrodes 312 are permanently fixed together (for the purpose of normal operation and use). There is therefore no requirement or indeed possibility for a user, such as a surgeon, to connect these components of the sensor array 302 together prior to implantation, therefore increasing the strength, cleanliness and ease of use of the sensor array 302.

[0123] The electrodes 310 may be configured to form pairs / channels 341A, 341 B, e.g., one pair 341 A implanted over the right hemisphere of the brain and one pair 341 B implanted over the left hemisphere of the brain, respectively. For example, the first electrode pair 341 A may be used to monitor electrical activity at right hemisphere of the brain and the second electrode pair 341 B may be used to monitor electrical activity at the left hemisphere of the brain, or vice-versa. Independent electrical activity data may be recorded for each of the right and left hemispheres. The electrode pairs 341 A, 341 B may be positioned away from the subject’s eyes and chewing muscles to avoid introduction of signal artifacts from these locations (e.g., clipping during chewing).

[0124] Fig. 3D provides a cross-sectional view of the implantable body 342 and the electrode 312. The implantable body 342 may have a round, e.g., substantially circular or ovate, cross- sectional profile. Similarly, each of the electrodes 312 may have a round, e.g., substantially circular or ovate, cross-sectional profile. Each of the electrodes 312 may extend circumferentially, completely around a portion of the implantable body 342. By configuring the implantable body 342 and electrodes 312 in this manner, the exact orientation of the implantable body 342 and electrodes 312, when implanted in a subject, is less critical. For example, the electrodes 312 may interact electrically with tissue in substantially any direction. In this regard, the electrodes 312 may be considered to have a 360-degree functionality. The round cross-sectional configuration may alsoprovide for easier insertion of the implantable portions of the electrode device 310 to the target location and with less risk of damaging body tissue. For example, the implantable body 342 may be used with insertion cannulas or sleeves and may have no sharp edges that might otherwise cause trauma to tissue.

[0125] In one embodiment, the implantable body 342 may be formed of an elastomeric material such as medical grade silicone. Each electrode 312 may comprise an annular portion of conductive material that extends circumferentially around a portion of the implantable body 342. More specifically, each electrode 312 may comprise a hollow cylinder of conductive material that extends circumferentially around a portion of the implantable body 342 and, in particular, a portion of the elastomeric material of the implantable body 342. The electrodes 312 may be considered ‘ring’ electrodes.

[0126] In one embodiment, to strengthen the engagement between the electrodes 312 and the implantable body 342, straps 365 may be provided that extend across an outer surface of each electrode 312. In such an embodiment, two straps 365 may be located on substantially opposite sides of each electrode 312 in a direction perpendicular to the direction of elongation of the implantable body 342. The straps 365 may prevent side sections of the implantable body 342 from pulling or breaking away from the electrodes 312 when the implantable body 342 is placed under tension and / or is bent. The straps 365 may similarly be formed of elastomeric material. In alternative embodiments, a different number of straps 365 may be employed (e.g., one, three, four or more straps 365), or the straps 365 may be omitted.

[0127] An electrical connection 340 may extend through the implantable body 342. The electrical connection 340 to the electrodes 312 may comprises relatively fragile platinum wire conductive elements. To reduce the likelihood that the platinum wires will break or snap during bending, flexing and / or stretching of the implantable body 342, the electrical connection 340 may be provided with a wave-like shape and, more specifically, a helical shape, although other non-linear shapes may be used. The helical shape, for example, of the electrical connection 340 enables the electrical connection 340 to stretch, flex and bend in conjunction with the implantable body 342. Bending, flexing, and / or stretching of the implantable body 342 typically occurs during implantation of the implantable body 342 in a subject and upon any removal of the implantable body 342 from the subject after use.

[0128] A reinforcement device 368 may be provided in the electrode device 312, which reinforcement device 368 extends through the implantable body 342 and limits the degree by which the length of the implantable body 342 can extend under tension. The reinforcement device 368 may take the bulk of the strain placed on the electrode device 310 when the electrode device 310 is placed under tension. The reinforcement device 368 may comprise a fiber (e.g., strand, filament,cord or string) of material that is flexible, and that has a high tensile strength. In particular, a fiber of ultra-high-molecular-weight polyethylene (UHMwPE), e.g., Dyneema™, may be provided as the reinforcement device 368 in the present embodiment. The reinforcement device 368 may extend through the implantable body 342 in the length direction of the implantable body 342 and may be generally directly encased by the elastomeric material of the implantable body 342.

[0129] The reinforcement device 368 may comprise a variety of different materials in addition to or as an alternative to UHMwPE. The reinforcement device may comprise other plastics and / or non-conductive material such as a poly-paraphenylene terephthalamide, e.g., Kevlar™. In some embodiments, a metal fiber or surgical steel may be used.

[0130] Similar to the electrical connection 340, the reinforcement device 368 may also have a wave-like shape and, more specifically, a helical shape, although other non-linear shapes may be used. The helical shape of the reinforcement device 368 may be different from the helical shape of the electrical connection 340, for example the helical shape of the reinforcement device 368 may have a smaller diameter than the helical shape of the electrical connection 340. Moreover, the helical shape of the reinforcement device 368 may have a greater pitch than the helical shape of the electrical connection 340.

[0131] Turning now to Fig. 3E, the processor device 304 is presented as a block diagram in greater detail. As depicted in Fig. 3E, the implant device system 300 includes, in embodiments, one or more sensors 351 , in addition to the sensor array 302 (e.g., one or more of which may be part of implant device 150), the processor device 304, and the user interface 306. The sensor array 302 and / or the sensors 351 may sense or collect respective data and communicate the respective data to the processor device 304. As may by now be understood, in embodiments, the sensor array 302 may include an array of electrode devices 310 that provide electrical signal data. In particular, the electrode devices 310 may provide electrical signal data indicative of brain activity of the patient (e.g., EEG signal data). While the sensor array 302 may be disposed beneath the scalp of the patient, e.g., on and extending into the cranium so as to facilitate accurate sensing of brain activity, in embodiments it is also contemplated that the sensor array 302 need not be placed beneath the scalp.

[0132] The sensors 351 , such as sensors 256, may include one or more infrared sensors, cameras, microphones, as well as any other suitable sensors. Additionally, other types of currently available or later-developed sensors may be included in some embodiments. The sensors 256 may be used to capture the facial biometric data of the patient (e.g., facial images), data regarding the physical environment, such as the environmental data, and / or any other suitable data. The sensors 351 may be integrated with the sensory array 302, the electrodes 310, the processor device 304,and / or communicatively coupled to the sensory array 302, the electrodes 310, and / or the processor device 304.

[0133] The sensors 351 may include at least one camera to capture images related to the patient and the patient’s environment. The camera may be, and or include, a CMOS sensor, an infrared sensor, a digital camera, a web camera, and / or any other suitable camera. The camera may be any type of camera suitable for capturing images of the patient, such as black and white images, color images, infrared images, stereo images, video, etc. In embodiments, the camera may be configured to capture facial biometrics of the patient automatically (e.g., according to a schedule, based upon EEG data indicating a health event, based upon recognition of a facial biometric, etc.). The camera may be disposed on the patient and suitable for operation from a portable power source such as a battery, e.g., one or more cameras in a smart watch, headset / head-mounted display (e.g., augmented reality, virtual reality, mixed reality, smart glasses), and / or other wearable camera. In some embodiments, the camera may be integrated with, and / or communicatively coupled to, one or more devices, such as the user device 115, the computing device 215, and / or the processor device 304.

[0134] The sensors 351 , such as the camera, may generate data (e.g., facial biometric data) indicating biometrics of the patient, such as facial biometrics via images or video of the patient’s face showing facial expressions, eye movements, etc. The facial biometrics, individually or in combination with data from the sensor array 302 (e.g., EEG data), self-reported data received via the user interface 306, and / or other suitable data, may assist algorithms executing within the processor device 304 in determining whether the patient has experienced a health event of interest (e.g., seizure, medication side effect, etc.) and, if so, classifying the health event. For example, the camera may generate facial biometric data comprising images which depict a drooping eye of the patient, that may indicate that patient is experiencing a seizure. Such an indication, in conjunction with electrical signals detected by the sensor array 302, may provide corroboration that the patient has, in fact, experienced a health event of interest.

[0135] The sensors 351 may include at least one microphone to detect sound related to the patient and the patient’s environment. The microphone may be any type of microphone suitable for disposal on the patient and suitable for operation from a portable power source such as a battery. In particular, the microphone may be a piezoelectric microphone, a MEMS microphone, or a fiber optic microphone. The microphone may be disposed at any of a variety of positions on the patient including, but not limited to, the patient’s head, arm, torso, leg, hand, or neck. In some embodiments, the microphone may be integrated with the sensor array 302 and placed on or beneath the scalp of the patient with the sensor array 302, while in others the microphone may beintegrated with the processor device 304, and still in others the microphone may be distinct from both the sensor array 302 and the processor device 304. In embodiments, especially those in which the patient’s voice is the primary sensing target for the microphone, the microphone senses sound via bone conduction. Of course, while depicted in the accompanying figures as a single microphone, the microphone may be one or more microphones, disposed as an array in a particular position on the patient, or as distinct units on a variety of positions on the patient. In embodiments implementing multiple microphones, the multiple microphones may be of the same type, or may be different, depending on the location of each on the patient, the environment in which each is disposed (e.g., sub-scalp vs. not), the location of each in the hardware (e.g., separate from other devices or integrated within the processor device 304, for example), etc. Each may have the same or different directionality and / or sensitivity characteristics as the others, depending on the placement of the microphone and the noises or vibrations the microphone is intended to detect.

[0136] The sensors 351 , such as the microphone, may detect the patient’s voice, in embodiments, with the goal of determining one or more of: vocal biometrics, pauses in vocalization; stutters; periods of extended silence; abnormal vocalization; and / or other vocal abnormalities that, individually or in combination with data from the sensor array 302, and / or self-reported data received via the user interface 306, may assist algorithms executing within the processor device 304 in determining whether the patient has experienced an health event of interest (e.g., seizure, medication side effect, etc.) and, if so, classifying the health event. In embodiments, the microphone may record one or more samples of the user’s voice when biometric images of the patient (e.g., of the face, eyes, etc.), and / or EEG of the patient, are captured. The vocal biomarkers of the voice samples can then be correlated to facial biometrics and / or the EEG. In embodiments, the microphone may also detect other noises in the patient’s environment that may be indicative that the patient experienced a health event of interest. For example, the microphone may detect the sound of glass breaking, that may indicate that the patient has dropped a glass. Such an indication, in conjunction with electrical signals detected by the sensor array 302, may provide corroboration that the patient has, in fact, experienced a health event of interest.

[0137] In some embodiments, the sensors 351 may neither be necessary nor required in order to generate data associated with the detection and / or prediction of a health event, generate an epileptic insight, etc., and thus are considered optional. Accordingly, the sensors 351 are depicted with dotted lines to denote that they are optional.

[0138] Together, the sensor array 302 and, if present, the sensor(s) 351 , may provide data from which biomarker data related to the patient(s) may be extracted. As used herein, the term “biomarker” refers to a broad subcategory of objective indications of medical state, observable from outside the patient, that may be measured accurately and reproducibly. Biomarkers differ fromsymptoms, which are generally perceived by patients themselves. The system 100 may be configured to determine a variety of biomarkers depending on the inclusion and / or placement of the various sensor devices (i.e. , the sensor array 302 and, if present, the sensors(s) 351). By way of example, and not limitation, mood disruption biomarker data may be determined from microphone data collected by one or more microphones; speech production biomarker data may be determined from microphone data collected by one or more microphones; epileptiform activity biomarker data may be determined from EEG data received from one or more electrode devices 310 in the sensor array 302; jaw movement biomarker data may be determined from a combination of electromyography data and microphone data collected by one or more devices (e.g., electrode devices 310) disposed on the patient; vomiting biomarker data may be determined from a combination of electromyography data and / or microphone data collected by one or more devices (e.g., electrode devices 310, sensors 351) disposed on the patient; sleep biomarker data may be determined from EEG data received from one or more electrode devices 310 in the sensor array 302, etc.

[0139] Turning to the processor device 304, the processor device 304 may include communication circuitry 356, the sensors 351 , a microprocessor 358, and a memory device 360. The microprocessor 358 may be any known microprocessor configurable to execute the routines (e.g., for detecting and classifying health events of interest, generating signal acquisition settings, and / or filtering health event data), including, by way of example and not limitation, general purpose microprocessors (GPUs), RISC microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).

[0140] The communication circuitry 356, such as communication circuitry 122, 258, may be any transceiver and / or receiver / transmitter pair that facilitates communication with the various devices from which the processor device 304 receives data and / or transmits data, such as the server 105, user device 115, and / or any other suitable device. The communication circuitry 356 may be communicatively coupled, in a wired or wireless manner, to each of the sensor array 302, the sensors 351 , and the user interface 306, among other things. Additionally, the communication circuitry 356 may be coupled to the microprocessor 358, that, in addition to executing various routines and instructions for performing analysis (e.g., of EEG data and / or the facial biometric data), may also facilitate storage in the memory 360 of data received, via the communication circuity 356, from the sensor array 302, the sensors 351 , and / or the user interface 306.

[0141] The sensors 351 , e.g., via the microprocessor 358 and / or communication circuitry 356, may generate and store sensor data in memory such as the memory 360, provide the sensor data to another device, such as the server 105 and / or user device 115, etc.

[0142] The memory 360 may include both volatile memory (e.g., random access memory (RAM)) and non-volatile memory, in the form of magnetic and / or solid state media. In addition to an operating system (not shown), the memory 360 may store sensor array data 364 received from the sensor array 302. The data stored in the memory 360 may be stored with corresponding metadata, labels, time stamps, etc.

[0143] In some embodiments, the memory 360 may include one or more models 370. The models 370 may include a first model 370A that operates on the EEG data 372 and the facial biometric data 374, to generate the first model output data 375A indicating a seizure. As previously described, the first model output data 375A may include and / or indicate a classification of the seizure, at least a portion of the EEG data 372, at least a portion of the facial biometric data 374, a request for at least one additional facial image, and / or any other suitable data associated with indicating the seizure.

[0144] The models 370 may include a second model 370B that operates on the EEG data 372 and the facial biometric data 374, to generate second model output data 375B indicating a prediction of the seizure of the patient. As previously described, the second model output data 375B may include and / or indicate includes a time of a predicted seizure, at least a portion of the EEG data 372, at least a portion of the facial biometric data 374, a request for at least one additional facial image, and / or any other suitable data associated with predicting the seizure.

[0145] The models 370 may include a third model 370C that operates on the facial biometric data 374, to generate third model output data 375C indicating an epileptic insight. As previously described, the third model output data 375C may include and / or indicate the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, a seizure, a prediction of the seizure, a prediction of an epilepsy-related facial biometric event, and / or any other suitable data associated with the epileptic insight.

[0146] Of course, it should be understood that wherever a routine, model, or other element stored in memory is referred to as receiving an input, producing or storing an output, or executing, the routine, model, or other element, it is, in fact, executing as instructions on the microprocessor 358. Further, those of skill in the art will appreciate that the model or routine or other instructions would be stored in the memory 360 as executable instructions, which instructions the microprocessor 358 would retrieve from the memory 360 and execute. Further, the microprocessor 358 should be understood to retrieve from the memory 360 any data necessary to perform the executed instructions (e.g., data required as an input to the routine or model), and to store in the memory 360 the intermediate results and / or output of any executed instructions.EXAMPLE ML MODEL TRAINING

[0147] Fig. 4 schematically illustrates how the server 105, the user device 115, the computing device 215, the processor device 304, and / or any other suitable device, may execute an ML module 405 to train one or more ML models 410 using training data 420 to operate on at least one input 430 to generate at least one output 440.

[0148] In one aspect, the ML module 405 may include one or more hardware and / or software components such as the ML module 140, the MLTM 142, and / or the MLOM 144 of server 105. The ML module 405 may obtain, create, train, retrain, fine-tune, retrieve, load, operate and / or save one or more ML models 410, such as ML model(s) 130.

[0149] The ML module 405 may use training data 420 to generate, train, retrain and / or fine-tune the one or more ML models 410. For the purposes of discussion herein, the term training data may be used interchangeably with the term historical training data, and more generally data may at times be used interchangeably with the term historical data (e.g., data that is already in existence may be considered historical relative to data that is yet- to-be generated). The server may store the training data 420 in a memory at one or more times (e.g., to update the training data 420), such as the memory 125 and / or the database 126 of the server 105, data storage 262 of computing device 215, and / or any other suitable memory of any other suitable device. In one aspect, the training data 420 may include one or more training datasets, such as training datasets 420A, 420B, 420C, etc. The one or more training datasets may include any suitable training data 420, such one or more types of training data described herein.

[0150] In one aspect, one or more sets of training data may be used to train iterations of an ML model 410 such as ML models iterations 410A, 410B, 410C, etc. The ML model iterations 410A, 410B, 410C may be trained to provide one or more outputs associated with each iterative ML model, such as output 440A associated with first iterative ML model 410A, output 440B associated with second iterative ML model 410B, output 440C associated with third iterative ML model 410C, and so on. While three sets of training data 420A-420C, three iterative ML models 410A-410C, and three sets of outputs 440A-440C are depicted in Fig. 4, this is merely an example for ease of illustration only and any number and / or variety of training data 420, models, 410 and / or outputs 440 may be implemented by the disclosed techniques.

[0151] The ML module 405 may implement a supervised or unsupervised machine learning program or algorithm, as previously described. In some aspects, a training dataset may include a set of feature values. In embodiments in which the ML module 405 implements unsupervised learning algorithms, the ML module 405 may find its own structure in unlabeled feature values of a training dataset. In embodiments in which the ML module 405 implements supervised learning algorithms, the ML module 405 (e.g., via MLTM 142) may store one or more routines that facilitate the labeling of the feature values (e.g., by clinician reviewing the feature values and / or the trainingdataset, such as training datasets 420A, 420B, 420C, etc.) to create one or more label attributes associated with the feature values. The ML module 405 may use both the feature values and the label attributes to discover rules, relationships, or other “models” that map the features to the labels by, for example, determining and / or assigning weights or other metrics. The ML module 405 may output the set of rules, relationships, or other models as a trained ML model 410, such as first ML model 410A.

[0152] In one aspect, the first trained ML model 410A may operate on the first training dataset 420A and / or the feature values extracted therefrom, or on a portion of the first training dataset 420A and / or a portion of the feature values extracted therefrom that were reserved for validating the first trained ML model 410A, in order to provide results, such as first trained ML model output 440A, for comparison and / or analysis by a trained professional in order to validate the output 440A of the first ML model 410A.

[0153] In embodiments, the first trained ML model 410A may be trained by a first set of hardware, such as the server 105, and stored to a memory such as the memory 125 and / or the database 126. The model 410A may be subsequently trained and / or operated by the first set of hardware, or may be provided (or otherwise received - e.g., via portable storage media) to second set of data collection hardware for further training, execution, etc., such as the implant device system 300 depicted in any of Figs. 3A-3E. The second set of data collection hardware may implement the first trained ML model 410A to provide an associated output 440A based on data that was collected the data collection hardware and not part of the first training dataset 420A or, alternatively, may simply collect additional data for use by the ML module 405 to iterate the first trained ML model 410A.

[0154] As should be understood, the training data 420 may include additional training datasets, such as a second training dataset 420B. The ML module 405 may implement a supervised or unsupervised machine learning program or algorithm, as described above, for iterating the first trained ML model 410A, that may have a first error rate associated with its first / primary output 440A, to create a second trained ML model 410B, that may have a second error rate, reduced from the first error rate, associated with the second / secondary trained ML model output 440B. The second trained ML model 410B may use the second training dataset 420B and / or the feature values extracted therefrom, or on a portion of the second training dataset 420B and / or a portion of the feature values extracted for validating the second trained ML model 410B, in order to provide an output 440B for comparison and / or analysis by a trained professional in order to validate the output of the second trained ML model 410B. An error rate of the output 440B by the second trained ML model 410B may be reduced relative to an error rate of the output 440A by the first trained ML model 410A. The second trained ML model 410B (e.g., due to its reduced relative error rate) maybe stored to a memory such as the memory 125, the database 126, and / or other suitable memory, as a new model, and / or replacing a previous model, and / or otherwise provided to one or more systems, such as implant device system 300.

[0155] Once trained, the ML model 410 may perform operations on one or more data inputs 430 to produce one or more desired data outputs 440. In one aspect, the ML model 410 may be loaded at runtime from a database (e.g., loaded by ML engine 405 from the database 126) to process the input data 430. The ML engine 405 may obtain the input data 430 (e.g., from the memory 125, the database 126, the user device 115, etc.), and provide the input data 430 for the trained ML model 410 to operate on, and generate the output data 440.

[0156] The ML module 405 may use training data 420 to retrain and / or fine-tune one or more ML models 410. For the purposes of discussion herein, the terms training, retraining and / or fine-tuning may at times be used interchangeably. In one aspect, the ML model 410 may be retrained based upon (updated) training data 420. Retraining the model may provide for improved operation of the model 410, e.g., retraining the second model 412 to improve the accuracy of the predictions of seizures. In one aspect, the model 410 may be fine-tuned using the training data 420. In one aspect, fine-tuning may include adding and / or adjusting the parameters (e.g., weights, layers) of a previously trained ML model 410 based upon data (e.g., specific data, new data, etc.). For example, a model 410 may be trained to detect a seizure based upon receiving only the EEG data of a patient. The model 410 may be fine-tuned through a training process to accept and operate on the facial biometric data of the patient to detect the seizure, improving the seizure detection capabilities of the model 410.FIRST MODEL

[0157] In one aspect, the models 410 may include a first model 411. The first model 411 may be trained via the ML module 405 using training data 420 (referred to as first model training data) to receive the EEG data and the facial biometric data as an input 430 to generate the first model output data 441 indicating a seizure, as the output 440. The first model training data 420 may include, for a plurality of historical patients, historical EEG data, historical facial biometric data, historical data indicating historical seizures, and / or any other suitable training data 420. The first model 411 may be trained to determine, for the historical patients, associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures, and / or any other suitable associations or patterns. For example, patterns of epileptiform activity, EEG spikes, or EEG sharps in the EEG of the historical EEG data may be indicative of the seizure; patterns of facial biometric features of historical facial biometric data may be indicative of the seizure; and / or patterns and association between the historical EEGdata and the historical facial biometric data may indicate the seizure, such as associations between EEG patterns and facial biometrics. The first model 411 may generate first model output data 441 , indicating the seizure. In response to generating the first model output data 441 , the first model 411 , the device operating the first model 411 , and / or any other suitable component, may provide the first model output data 441 to a user device (e.g., the user device 115, computing device 215, etc.), and / or store the first model output data 441 to one or more memories (e.g., memory of the user device, server, etc.).

[0158] In one example of the first model 411 , an implant device such as implant device 150 is implanted in a patient Andy, and captures Andy’s EEG data (e.g., via a sensor array such as sensor 302) over the course of several weeks. The EEG device transmits, via the communication circuitry 356, the EEG data to Andy’s smartphone (e.g., user device 115 , computing device 215, processor device 405). The smartphone executes a mobile app associated with the implant device, and also executes the first 411 , second 412, and third 413 models, wherein both the mobile app and the models 411-413 are stored in a memory of the smartphone, such as computing device 215 memory 250 and / or program memory 246, processor device 304 memory 360. The smartphone also generates facial biometric data when capturing Andy’s facial images over the course of the same several weeks using the smartphone’s camera (e.g., sensors 256, 351), including some baseline facial images when Andy is not experiencing a seizure, and some facial images captured when the mobile app prompts Andy to take facial images, e.g., during a time when Andy may be experiencing a seizure (e.g., as determined by Andy and / or a model), during a predicted time of a seizure, etc. The smartphone provides Andy’s EEG data and facial biometric data to the first model 411 executing on the smartphone, to determine that Andy is experiencing a seizure. The first model 411 process the input data 430 at one or more times, such as periodically, substantially in real-time, etc. The first model 411 generates first model output data 441 , that is displayed via the mobile app. The display of the first model output data 441 indicates to Andy that, based upon patterns in her EEG, she may be experiencing a seizure. The first model output data 411 being displayed also requests Andy take additional facial biometric images. Andy takes several new facial images using the smartphone camera via the mobile app, which the first model 411 receives. The first model 411 further operates on Andy’s new facial images. The first model 411 then generates updated first model output data 441 indicating that Andy is indeed experiencing a clonic seizure, based upon patterns detected in the new facial images in conjunction with her EEG data. The mobile app displays the updated first model output data 441 , which informs Andy of the type of seizure, provides a visualization of the EEG and EEG patterns indicating the seizure, provides the facial images, and identifies facial biometric patterns in the facial images indicating the seizure.Additionally, the updated first model output data 411 is transmitted by the smartphone, via anetwork (e.g., network 110), to a medical server associated with Andy’s doctor, where the updated first model output data 441 is stored in a database containing Andy’s medical records. Moreover, all of the data just described with respect to Andy, i.e. , the original and updated first model output data 441 , Andy’s EEG data, Andy’s facial biometric data including the original and new facial images, is transmitted by the smartphone, via the network, to an ML model training server, where it is stored as training data 420. In one aspect, Andy’s data may be labeled, e.g., by a human reviewer of the data, with one or more labels, such as labeling indicating EEG patterns, facial biometric patterns, the classification of the seizure, and / or any other suitable labels. In one aspect, the first model 411 may be trained, via the ML module 405 on the ML model training server, using Andy’s data stored as training data 420, to improve the performance of the first model 411. In one aspect, a seizure classification model that is trained to operate only on EEG data to detect a seizure in a patient, may be fine-tuned using the training data 420 which includes Andy’s data, to also operate on facial biometric data to detect the seizure. In one aspect, Andy’s data may be stored and further analyzed in a database used to provide healthcare to other patents.

[0159] In examples where the first model 411 may only detect a seizure in either the EEG data or the facial biometric data, but not both, the data in which the seizure is not detected may be analyzed to identify patterns that may indicate the seizure, e.g., analyzed by a human reviewer, by an algorithm or other automated process, and / or in any other suitable manner. In the example where the EEG data does not identify a seizure but the facial biometric data does, the EEG recorded when the facial images indicating the seizure were captured may be further analyzed to detect EEG patterns in the EEG that may indicate the seizure. If such patterns are found in the EEG, they may be labeled in the EEG data, used as training data, etc. In the example where the facial biometric data does not identify a seizure but the EEG data does, the facial images captured during the time when the EEG indicating the seizure was recorded, may be further analyzed to detect facial biometric patterns that may indicate the seizure. If such patterns are found in the facial images, they may be labeled in the facial biometric data, used as training data, etc. In one example, the facial biometric data may be used to confirm whether a patient self-reported seizure (e.g., reported by the patient via the smart implant system user interface 306, the user device 115, the computing device 215, the processor device 304, etc.) is, in fact, a seizure. Such an analysis may be conducted by a model, an algorithm, and / or other suitable means.

[0160] In any of the embodiments, aspects, and / or examples disclosed herein, detecting a seizure in the EEG data may include identifying (e.g., via the server, a model, etc.) an EEG pattern potentially indicating the seizure, for example the EEG pattern may indicate a seizure, or may indicate some other health event, or neither indicate the seizure nor the health event. In such instances, the facial biometric data may be used to either confirm that the potential seizure either is,or is not, a seizure, confirm the potential seizure is some other health event, adjust a confidence metric (e.g., confidence score) associated with the identification of the potential seizure, and / or any other suitable purpose.SECOND MODEL

[0161] In one aspect, the models 410 may include a second model 412 for predicting a seizure. The second model 412 may be trained using training data 420 (referred to as second model training data) to receive the EEG data and facial biometric data as an input 430, to generate the second model output data 442 indicating the seizure of the patient, as the output 440. The second model training data 420 may include, for a plurality of historical patients, historical EEG data, historical facial biometric data, historical data indicating historical seizures, historical predictions of seizures, and / or any other suitable training data 420. The second model 412 may be trained to determine, for the historical patients, associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures. In one example, the frequency and profile over time of certain EEG patterns and / or facial biometric patterns may be indicative of how often a seizure may occur, and may be used to predict a future seizure. The second model 412 may generate second model output data 442, predicting the seizure. In response to generating the second model output data 442, the second model 412, the device operating the second model 442, and / or other suitable component, may provide the second model output data 442 to a user device (e.g., the user device 115, computing device 215, etc.), and / or store the second model output data 442 to one or more memories (e.g., memory of the user device, server, etc.).

[0162] Continuing with the above example, Andy’s smartphone executes the second model 412 stored in the smartphone memory, to operate on Andy’s EEG data and facial biometric data to generate second model output data 442. The second model output data 422 indicates that Andy’s next seizure is predicted to occur in 3 days. In response to generating the second model output data 442, the smartphone mobile app displays the second model output data 422, informing Andy of the date of the predicted seizure. Additionally, near the time of the predicted seizure, the mobile app may again display the second model output data 422, as a reminder to Andy that the predicted seizure may be about to occur. Additionally, and similar to that described with respect to the first model 411 , any of the data the second model 412 operates on and / or generates, e.g. Andy’s EEG data, facial biometric data, the second model output data 442, may be stored in one or more memories, e.g., for model training, fine-tuning, further analysis, labeling, etc.THIRD MODEL

[0163] In one aspect, the models 410 may include a third model 413 for generating an epileptic insight for a patient. The third model 413 may be trained using training data 420 (referred to as third model training data) to receive the facial biometric data as an input 430, to generate the third model output data 443 indicating the epileptic insight, as the output 440. The third model training data 420 may include, for a plurality of historical patients, historical facial biometric data and historical data indicating historical epileptic insights, and / or any other suitable training data 420. The third model 413 may be trained to determine, for the historical patients, associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics. In one example, facial biometrics like a pupil dilation may be associated with an epileptic mediation side-effect. The third model 413 may generate third model output data 443, indicating the epileptic insight. In response to generating the third model output data 443, the third model 413, the device operating the third model 413, and / or other suitable component, may provide the third model output data 443 to a user device (e.g., the user device 115, computing device 215, etc.), and / or store the third model output data 443 to one or more memories (e.g., memory of the user device, server, etc.).

[0164] Continuing with the above example, Andy’s smartphone executes the third model 413 stored in the smartphone memory, to operate on Andy’s facial biometric data to generate the third model output data 443. The third model output data indicates that Andy’s is experiencing a side effect from epilepsy medication based on biometric patterns in her eyes. In response to generating the third model output data 443, the smartphone mobile app may display the third model output data 433, informing Andy of the epileptic insight. Additionally, and similar to that described with respect to the first model 411 , any of the data the third model 413 operates on and / or generates, i.e. Andy’s facial biometric data and the third model output data 443, may be stored in one or more memories, e.g., for model training, fine-tuning, further analysis, labeling, etc.

[0165] While various ML models 410 (e.g., models 411-413) are described with respect to Fig. 4 and more generally throughout the present disclosure, a single ML model may provide at least some functionality associated with one or more separately described ML models. For example, the first model 411 to detect a seizure may provide the functionality of both the first 411 and second412 models, e.g., to detect and predict seizures. Additionally, the functionality described with respect to a single ML model may be carried out by one or more separate ML models. Moreover, one or more ML models may have additional functionality provided by the training data 420 that may not be expressly described. Furthermore, although the each of the models 411-413 are described as generating specific output(s) based upon receiving specific input(s), the models 411-413 may receive other input(s) and / or produce other output(s). For example, during a seizure, the patient may indicate that they are experiencing a seizure via the user interface 306 of the implantdevice, and as a result, the implant device may generate patient reported seizure data. This data may be provided to the first model 411 as an input, and operated on by the first model 411 in addition to the EEG data and facial biometric data, to generate the first model output data 441 indicating a seizure of the patient. The considerations just described likewise apply to static models, that may not be ML models.EXAMPLE IMPLANT DEVICE SYSTEM

[0166] Fig. 5 is a block diagram of an example implant device system 500 similar to the system 300 of Fig. 3E, but which includes one or more trained ML models 380 (e.g., such as ML model(s) 130, 410-413) instead of the model 370 based on a static algorithm (e.g., a static model). That is, Fig. 5 corresponds generally to Fig. 3E, with the only difference between the implant device system 300 and the implant device system 500 in respective figures being the inclusion of the trained ML models 380, including models 380A-380C, such as models 411-413 respectively, rather than the model 370A-370C based on a static algorithm. The implant device system 500, as depicted in Fig. 5, is the same in all respects as in Fig. 3E, above, except that the trained ML models 370 are created using ML algorithms to search for patterns in training data and, upon implementation in the processor device 304, the trained models 370 may receive an input and determine (e.g., from one or more feature values) an output, as previously described.

[0167] Fig. 6 is a block diagram depicting another example embodiment, in which generating the first model output data 375A, the second model output data 375B, and / or the third model output data 375C may take place on a device other than the processor device 304 and, specifically, on an external device 504. In the embodiments depicted in Fig. 6, it is contemplated that the one or more models may be either the static models 370 or the trained ML models 380 and, as a result, Fig. 6 illustrates an alternate embodiment of Fig. 3E and of Fig. 5. In the embodiments contemplated within Fig. 6, the processor device 304 generally collects the EEG data 372 from the sensor array 302. The EEG data 372 is stored in the memory 360 of the processor device 304. The processor device 304, via the sensors 351 , generally generates the facial biometric data 374, and stores the facial biometric data 374 in the memory 360. While the processor device 304 may be equipped to perform the modeling - that is may have stored in the memory 360 the models 370 or 380, and may be configured to operate on the input data to generate the output data associated with the models 370, 380 - in the embodiments contemplated by Fig. 6, this functionality is optional. Instead, the microprocessor 358 may be configured to communicate with the external device 504 such that the external device 504 may perform the analysis.

[0168] The external device 504 may be a server such as server 105, a user device such as user device 115, a computing device such as computing device 215, a workstation, a cloud computingplatform, or any other suitable device, configured to receive data from the one or more processor devices 304 associated with one or more respective patients. The external device 504 may include communication circuitry 556 and sensors 551 , coupled to a processor 558 that, in turn, is coupled to a memory 560. The processor 558 may be any known processor configurable to execute the routines necessary for generating the first model output data 375A, the second model output data 375B, and / or the third model output data 375C, including, by way of example and not limitation, general purpose microprocessors (GPUs), RISC microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or any other suitable processor, such as the processor 120, 248, and the like.

[0169] The communication circuitry 556 may be any transceiver and / or receiver / transmitter pair that facilitates communication with the various devices from or to which the processor device 504 receives data and / or transmits data, such as communication circuitry 122. The communication circuitry 556 is coupled to the processor 558, that, in addition to executing various routines and instructions for performing analysis, may also facilitate storage in the memory 560 of data received, via the communication circuity 556, from the processor devices 304 of the one or more patients.

[0170] The sensors 551 , such as the sensors 256, 351 , may include one or more proximity sensors, infrared sensors, cameras, microphones, as well as any other suitable sensors. The sensors 551 may be integrated with the external device 504, and / or communicatively coupled to the external device 504. The sensors 551 may capture sensor data, such as the facial biometric data 374 of the patient (e.g., facial images including facial biometrics, etc.), data regarding the physical environment, and / or any other suitable data capable of being captured by the sensors 551 . The sensors 551 , via the processor 558 and / or communication circuitry 556, may store the sensor data in memory such as the memory 560, provide the sensor data to another device, such as the server 105, the user device 115, the processor device 304, etc.

[0171] The memory 560 may include one or more memories, such as the memory 125 and / or the database 126. The memory 560 may include both volatile memory (e.g., random access memory (RAM)) and non-volatile memory, in the form of magnetic and / or solid state media. In addition to an operating system (not shown), the memory 560 may store data received from the processor devices 304, such as received data 581 that may include the EEG data 372, the facial biometric data 374, and / or any other suitable data.

[0172] Like the processor device 304, the external device 504 may have, stored in its memory 560, one or more static models 370 and / or trained ML models 380, such as the first models 370A, 380A, the second models 370B, 380B, and / or the third models. The processor 558 may execute one or more of the models 370, 380, receiving as inputs one or more of the EEG data 372, the facial biometric data 374, and / or any other suitable data, as previously described with respect to thestatic models 370 of Fig. 3E and / or ML models 380 of Fig. 5, to generate the first model output data 375A, second model output data 375B, third model output data 375C, and / or any other suitable data.

[0173] The embodiments depicted in Fig. 6 also contemplate that, even in embodiments in which the processor device 304 executes the models 370 or 380 to produce results 375A, 375B, 375C, the processor device 304 may communicate the outputs / results 375A, 375B, 375C, as well as the data 372, 374 upon which the outputs / results are based, to the external device 504. The external device 504 may receive such data, and may store the data, for later viewing or analysis by the patient(s), physicians, or others, etc. In embodiments in which the external device 504 performs analysis of data of multiple patients, or for which the external device 504 receives from multiple processor devices 304 data of multiple patients, the external device 504 may store the received data 581 , the first model output data 375A, the second model output data 375B, the third model output data 375C, and / or any other suitable data for each patient separately in the memory 560.EXAMPLE METHOD FOR TRAINING A FIRST MODEL TO GENERATE FIRST MODEL OUTPUT DATA

[0174] Fig. 7A is a flow chart depicting a computer-implemented method 700 for training the first model to generate first model output data indicating a seizure of the patient. The first model, including the first iteration, second iteration, or other iterations of the first model, may be trained to determine, for the historical patients, associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures. The first model output data may include one or more of a classification of the seizure, at least a portion of EEG data indicating the seizure, at least a portion of facial biometric data indicating the seizure, or a request for at least one additional facial image.

[0175] The method 700 may include obtaining, by one or more processors, a first training dataset (block 701).

[0176] The method 700 may include receiving as feature values a selection of one or more attributes of the first training dataset (block 702). The one or more attributes may comprise one or more of epileptiform activity, EEG spikes, EEG sharps, or facial biometrics. A training dataset may comprise historical EEG data of historical patients and historical facial biometric data of the historical patients.

[0177] The method 700 may include training, by the one or more processors, a first iteration of the first model using the first training dataset (block 703) using the feature values defined for the first training dataset to generate first primary first model output data (block 704). The primary first model output data may have associated first error rates.

[0178] The method 700 may include obtaining, by one or more processors, a second training dataset (block 705). The method 700 may include receiving as feature values the selection of one or more attributes of the second training dataset (block 706).

[0179] The method 700 may include training, by the one or more processors, a second iteration of the first model using the second training dataset (block 707) using the feature values defined for the second training dataset to generate secondary first model output data (block 708). The secondary first model output data may have associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0180] In one aspect, the method 700 may further include obtaining, by the one or more processors, (i) EEG data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0181] In one aspect, the method 700 may further include receiving one or more labels for the first training dataset, wherein training the first iteration of the first model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the first model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the first model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the second first model output data.EXAMPLE METHOD FOR TRAINING A SECOND MODEL TO GENERATE SECOND MODEL OUTPUT DATA

[0182] Fig. 7B is a flow chart depicting a computer-implemented method 710 for training a second model to generate second model output data predict a seizure of the patient. The second model, including the first iteration, second iteration, or other iterations of the second model, may be trained to determine, for the historical patients, associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures. The second model output data may include one or more of a time of a predicted seizure, at least a portion of EEG data, at least a portion of facial biometric data, or a request for at least one additional facial image.

[0183] The method 710 may include obtaining, by one or more processors, a first training dataset (block 711). A training dataset may comprise historical EEG data of historical patients and historical facial biometric data of the historical patients.

[0184] The method 710 may include receiving as feature values a selection of one or more attributes of the first training dataset (block 712). The one or more attributes may comprise one or more of epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

[0185] The method 710 may include training, by the one or more processors, a first iteration of the second model using the first training dataset (block 713) using the feature values defined for the first training dataset to generate first primary second model output data (block 714). The primary second model output data may have associated first error rates.

[0186] The method 710 may include obtaining, by one or more processors, a second training dataset (block 715). The method 710 may include receiving as feature values the selection of one or more attributes of the second training dataset (block 716).

[0187] The method 710 may include training, by the one or more processors, a second iteration of the second model using the second training dataset (block 717) using the feature values defined for the second training dataset to generate secondary second model output data (block 718). The secondary second model output data may have associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0188] In one aspect, the method 710 may include obtaining, by the one or more processors, (i) EEG data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0189] In one aspect, the method 710 may include receiving one or more labels for the first training dataset, wherein training the first iteration of the second model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the primary second model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the second model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the secondary second model output data.EXAMPLE METHOD FOR TRAINING A THIRD MODEL TO GENERATE THIRD MODEL OUTPUTDATA

[0190] Fig. 7C is a flow chart depicting a computer-implemented method 720 for training a third model to generate third model output data, the third model output data indicating an epileptic insight. The third model, including the first iteration, second iteration, or other iterations of the third model, may be trained to determine, for the historical patients, associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics. The third model output data may include the epileptic insight and / or a request for at least one additional facial image.

[0191] The method 720 may include obtaining, by one or more processors, a first training dataset (block 721). A training dataset may comprise historical facial biometric data of historical patients.

[0192] The method 720 may include receiving as feature values a selection of one or more attributes of the first training dataset (block 722). The one or more attributes may comprise include facial biometrics.

[0193] The method 720 may include training, by the one or more processors, a first iteration of the third model using the first training dataset (block 723) using the feature values defined for the first training dataset to generate first primary third model output data (block 724). The primary third model output data may have associated first error rates.

[0194] The method 720 may include obtaining, by one or more processors, a second training dataset (block 725). The method 720 may include receiving as feature values the selection of one or more attributes of the second training dataset (block 726).

[0195] The method 720 may further include training, by the one or more processors, a second iteration of the third model using the second training dataset (block 727) using the feature values defined for the second training dataset to generate secondary third model output data (block 728). The secondary third model output data may have associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0196] In one aspect, the method 720 may further include obtaining, by the one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; and based upon the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0197] In one aspect, the method 720 may include receiving one or more labels for the first training dataset, wherein training the first iteration of the third model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the primary third model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the third model using the second training dataset further comprisesusing the one or more labels for the second training dataset to generate the secondary third model output data.EXAMPLE METHOD FOR IDENTIFYING A SEIZURE OF A PATIENT

[0198] Fig. 8A is a flow chart depicting a computer-implemented method 800 for identifying a seizure of a patient. The method 800 may include obtaining, by one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered (block 802). The facial biometrics may indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction. The at least one facial image may include baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0199] The method 800 may include providing, by the one or more processors, the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating the seizure of the patient (block 804). The first model training data may include historical EEG data of historical patients and historical facial biometric data of the historical patients, and the first model may be trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures. The first model output data may include one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0200] The method 800 may include, in response to generating the first model output data, one or more of: providing, by the one or more processors, the first model output data to a user device; or storing, by the one or more processors, the first model output data in a memory (block 806). The user device may be associated with the patient or a healthcare provider of the patient.

[0201] In one aspect, the method 800 may include, in response to identifying the seizure in the EEG data and the facial biometric data, applying, by the one or more processors, at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data. In such an aspect, identifying the seizure in the EEG data and the facial biometric data may further include identifying, by the one or more processors, in the EEG data, an EEG pattern potentially indicating the seizure; and determining, by the one or more processors, the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

[0202] In another aspect, the method 800 may include, in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identifying, by the one or more processors, an EEG pattern in the EEG data corresponding to the seizure.

[0203] In yet another aspect, the method 800 may include, in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identifying, by the one or more processors, a facial biometric pattern in the facial biometric data corresponding to the seizure.

[0204] In still yet another aspect, the method 800 may include, using the first model output data to one or more of (i) retrain, by the one or more processors, the first model; (ii) fine-tune, by the one or more processors, a seizure detection model that operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure; or (iii) provide healthcare to at least one other patient.

[0205] In another aspect, the method 800 may include, (i) obtaining, by the one or more processors, additional first model training data; (ii) retraining, by the one or more processors, the first model using the additional first model training data; and (iii) storing, by the one or more processors, the retrained first model in the memory to generate subsequent first model output data.EXAMPLE METHOD FOR PREDICTING A SEIZURE OF A PATIENT

[0206] Fig. 8B is a flow chart depicting a computer-implemented method 810 for predicting a seizure of a patient. The method 810 may include obtaining, by one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered (block 812). The facial biometrics may indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction. The at least one facial image may include baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0207] The method 810 may include providing, by the one or more processors, the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data predicting the seizure of the patient (block 814). The first model training data may include historical EEG data of historical patients and historical facial biometric data of the historical patients, and the first model may be trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures. The second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0208] The method 810 may include, in response to generating the second model output data, one or more of: providing, by the one or more processors, the second model output data to a user device; or storing, by the one or more processors, the second model output data in a memory (block 816). The user device may be associated with the patient or a healthcare provider of the patient. The second model output data may be provided to the user device proximate a time of a predicted seizure.

[0209] In one aspect, the method 810 may include using the second model output data to one or more of: (i) retrain, by the one or more processors, the second model; (ii) fine-tune, by the one or more processors, a seizure prediction model that operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure; or (iii) provide healthcare to at least one other patient.

[0210] In yet another aspect, the method 810 may include (i) obtaining, by the one or more processors, additional second model training data; (ii) retraining, by the one or more processors, the second model using the additional second model training data; and (iii) storing, by the one or more processors, the retrained second model in the memory to generate subsequent second model output data.EXAMPLE METHOD FOR GENERATING AN EPILEPTIC INSIGHT BASED UPON FACIAL BIOMETRICS OF A PATIENT

[0211] Fig. 8C is a flow chart depicting a computer-implemented method 820 for generating an epileptic insight based upon facial biometrics of a patient. The method 820 may include obtaining, by one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient (block 822). The facial biometrics may indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction. The at least one facial image may include baseline facial biometrics associated with a period during which the patient is not experiencing the seizure, and / or data indicating the at least one facial image is captured during a patient-reported seizure. The epileptic insight may include one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

[0212] The method 820 may include providing, by the one or more processors, the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating the epileptic insight (block 824). The third model training data may include historical facial biometric data of historical patients, and the third model may be trained to make associations between historical facial biometrics, and historical epileptic insights indicated by thehistorical facial biometrics. The third model output data may include the epileptic insight and / or a request for at least one additional facial image.

[0213] The method 820 may include, in response to generating the third model output data, one or more of: (i) providing, by the one or more processors, the third model output data to a user device; or (ii) storing, by the one or more processors, the third model output data in a memory (block 826). The user device is associated with the patient or a healthcare provider of the patient.

[0214] In one aspect, the method 820 may include using the third model output data to one or more of: (i) retrain, by the one or more processors, the third model; (ii) fine-tune, by the one or more processors, an epileptic insight model that does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight; or (iii) provide healthcare to at least one other patient.

[0215] In another aspect, the method 820 may include (i) obtaining, by the one or more processors, additional third model training data; (ii) retraining, by the one or more processors, the third model using the additional third model training data; and (iii) storing, by the one or more processors, the retrained third model in the memory to generate subsequent third model output data.

[0216] As may by now be understood, the presently disclosed method and system are amenable to a variety of embodiments, some of which have already been described herein.

[0217] Fig. 9 depicts an alternate embodiment, in which the sensor array 302 and the processor device 304 are integrated into a single unit 910. The combined unit 910 includes the battery 348 and battery charging technology 349 for powering the unit 910, as previously described. The battery charging technology 349 may include a battery charging circuit, for facilitating charging of the battery 348. The battery charging technology 349 may be any known battery charging technology compatible with the arrangement of the sensor array 302. In particular, in embodiments the battery technology 349 may be an inductive charging circuit that facilitates charging through the patient’s skin when the sensor array 302 is disposed beneath the scalp of the patient. In other embodiments, the battery technology 349 may draw energy from the movements of the patient throughout the day by, for example, harnessing the movements of the patient to turn a small generator. In still other embodiments, the battery technology 349 may draw power from the environment in the form of RF signals. In further examples still, the battery technology 349 may draw power from chemical reactions taking place in the environment of the sensor array 302. Of course, more traditional charging methods (e.g., using a wired connection to provide power to the battery technology 349) may also be employed.

[0218] The single unit 910 includes electrode devices 310. As in previously described embodiments, the unit 910 may include one or more sensors 351. Additionally, the unit 910 may,as previously described, be communicatively coupled to one or more sensors 351 , that are external to the unit 910. The amplifier 346 and analog-to-digital converter (ADC) 352 are also included. The microprocessor 358, memory 360, and communication circuitry 356 function as described throughout. The single unit 910 may be connected to external equipment 905. The external equipment 905 may be one or more servers, such as server 105, or other suitable external equipment, that may receive and store the data for individual patients and / or communicate the data for the patients to the respective medical personnel or physicians diagnosing and / or treating the patients.

[0219] Various communication schemes are contemplated, as well. Figs. 10A and 10B illustrate possible communication schemes between the sensor array 302 and the processor device 304 and, in particular, Fig. 10A illustrates a wireless connection 1002 between the sensor array 302 and the processor device 304 (i.e. , between the communication circuitry of the sensor array 302 and the communication circuitry 356 of the processor device 304). The wireless connection 1002 may be any known type of wireless connection, including a Bluetooth® connection (e.g., low-energy Bluetooth), a wireless internet connect (e.g., IEEE 802.11 , known as “Wi-Fi”), a near-field communication connection, or similar. Fig. 10B illustrates a wired connection 1004 between the sensor array 302 and the processor device 304. The wired connection may be a serial connection, for example.

[0220] The sensor array 302 may communicate data to the processor device 304 as the data are acquired by the sensor array 302 or periodically. For example, the sensor array 302 may store, in the memory 355 of the local processing unit 344, data as it is acquired from the electrode devices 310, and may periodically (e.g., every second, every minute, every half hour, every hour, every day, when the memory 355 is full, etc.) transmit the data to the processor device 304. In other embodiments, the sensor array 302 may store data until the processor device 304 is coupled to the sensor array 302 (e.g., via wireless or wired connection). The sensor array 302 may also store the data until the processor device 304 requests the transmission of the data from the sensor array 302 to the processor device 304. In these manners, the sensor array 302 may be optimized, for example, to preserve battery life, etc.

[0221] Figs. 11A-11C illustrate possible communication schemes between the processor device 304 and external equipment or servers 905, regardless of whether or not the processor device 304 is integrated with the sensor array 302 (e.g., as in Fig. 9). In Fig. 11 A, for example, the processor device 304 may be coupled by a wireless communication connection to a mobile device 915, such as user device 115 or computing device 215, that may, in turn, be coupled to the external equipment 905 by, for example, the Internet. In Fig. 11 B, the processor device 304 is coupled to one or more intermediary devices 920 (e.g., a mobile telephony base station, a wireless router,etc.), that in turn provides connectivity to the external equipment 905 via the Internet. In Fig. 11C, the processor device 304 is itself a mobile device, such as a mobile telephony device, that may be coupled by one or more intermediary devices 920 to the external equipment 905 by way of the Internet.

[0222] The following list of aspects reflects a variety of the embodiments explicitly contemplated by the present disclosure. Those of ordinary skill in the art will readily appreciate that the aspects below are neither limiting of the embodiments disclosed herein, nor exhaustive of all of the embodiments conceivable from the disclosure above, but are instead meant to be exemplary in nature.

[0223] 1 . A system for identifying a seizure of a patient, the system comprising: an implant device comprising a sensor array and a processor device, the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient, and provide the EEG data to the processing device; and the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor array via the communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; a first model, stored in the memory and configured to be executed by the microprocessor, the first model trained using first model training data, and operable to: receive the facial biometric data and the EEG data; determine one or more feature values of the facial biometric data and the EEG data; and based on the one or more feature values, generate first model output data indicating the seizure of the patient; and in response to generating the first mode output data, the processor device is configured to one or more of: provide the first model output data to a user device; or store the first model output data in the memory.

[0224] 2. The system according to aspect 1 , wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0225] 3. The system according to aspects 1 or 2, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0226] 4. The system according to any one of aspects 1 to 3, wherein the one or more feature values indicate attributes including one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

[0227] 5. The system according to any one of aspects 1 to 4, wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

[0228] 6. The system according to any one of aspects 1 to 5, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0229] 7. The system according to any one of aspects 1 to 6, wherein the processor device is further configured to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

[0230] 8. The system according to aspect 7, wherein to identify the seizure in the EEG data and the facial biometric data, the first model is further operable to: identify, in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

[0231] 9. The system according to any one of aspects 1 to 8, wherein the processor device is further configured to use the first model output data to: retrain the first model; and / or fine-tune a seizure detection model which operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure.

[0232] 10. The system according to any one of aspects 1 to 9, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0233] 11 . The system according to any one of aspects 1 to 10, wherein the processor device is further configured to: obtain additional first model training data; retrain the first model using theadditional first model training data; and store the retrained first model in the memory to generate subsequent first model output data.

[0234] 12. The system according to any one of aspects 1 to 11 , wherein the processor device is a wearable processor device.

[0235] 13. The system according to any one of aspects 1 to 12, wherein the processor device is embedded in the sensor array or disposed adjacent to the sensor array.

[0236] 14. The system according to any one of aspects 1 to 13, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

[0237] 15. The system according to aspect 14, wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

[0238] 16. The system according to any one of aspects 1 to 15, wherein the processor device is the imaging device, the user device, or a server.

[0239] 17. The system according to any one of aspects 1 to 16, wherein the processor device is remote from the sensor array and is communicatively coupled to the sensor array via an Internet.

[0240] 18. The system according to any one of aspects 1 to 17, wherein the plurality of electrodes provide one or more electrical signals indicating a presence or absence of a biomarker.

[0241] 19. The system according to aspect 18, wherein the biomarker includes epileptiform activity biomarker data determined from the EEG data received from one or more sensor arrays.

[0242] 20. The system according to any one of aspects 1 to 19, wherein the sensor array comprises a wireless transceiver.

[0243] 21 . The system according to any one of aspects 1 to 20, wherein the imaging device is the processor device or the user device.

[0244] 22. The system according to any one of aspects 1 to 21 , wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

[0245] 23. A system for predicting a seizure of a patient, the system comprising: an implant device comprising a sensor array and a processor device, the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gatheredvia an implant device of the patient, and provide the EEG data to the processing device; and the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor array via the communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; a second model, stored in the memory and configured to be executed by the microprocessor, the second model trained using second model training data, and operable to: receive the facial biometric data and the EEG data; determine one or more feature values of the facial biometric data and the EEG data; and based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient; and in response to generating the second model output data, the processor device is configured to one or more of: provide the second model output data to a user device; or store the second model output data in the memory.

[0246] 24. The system according to aspect 23, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0247] 25. The system according to aspects 23 or 24, wherein the one or more feature values indicate attributes including one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

[0248] 26. The system according to any one of aspects 23 to 25, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0249] 27. The system according to any one of aspects 23 to 26, wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

[0250] 28. The system according to any one of aspects 23 to 27, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0251] 29. The system according to any one of aspects 23 to 28, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

[0252] 30. The system according to any one of aspects 23 to 29, wherein the processor device is further configured to use the second model output data to: retrain the second model; and / or finetune a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure.

[0253] 31 . The system according to any one of aspects 23 to 30, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0254] 32. The system according to any one of aspects 23 to 31 , wherein the processor device is further configured to: obtain additional second model training data; retrain the second model using the additional second model training data; and store the retrained second model in the memory to generate subsequent second model output data.

[0255] 33. The system according to any one of aspects 23 to 32, wherein the processor device is a wearable processor device.

[0256] 34. The system according to any one of aspects 23 to 33, wherein the processor device is embedded in the sensor array or disposed adjacent to the sensor array.

[0257] 35. The system according to any one of aspects 23 to 34, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

[0258] 36. The system according to aspect 35, wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

[0259] 37. The system according to any one of aspects 23 to 36, wherein the processor device is the imaging device, the user device, or a server.

[0260] 38. The system according to any one of aspects 23 to 37, wherein the processor device is remote from the sensor array and is communicatively coupled to the sensor array via an Internet.

[0261] 39. The system according to any one of aspects 23 to 38, wherein the plurality of electrodes provide one or more electrical signals indicating a presence or absence of a biomarker.

[0262] 40. The system according to aspect 39, wherein the biomarker includes epileptiform activity biomarker data determined from the EEG data received from one or more sensor arrays.

[0263] 41 . The system according to any one of aspects 23 to 40, wherein the sensor array comprises a wireless transceiver.

[0264] 42. The system according to any one of aspects 23 to 41 , wherein the imaging device is the processor device or the user device.

[0265] 43. The system according to any one of aspects 23 to 42, wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

[0266] 44. A system for generating an epileptic insight based upon facial biometrics of a patient, the system comprising: a processor device comprising a processor, a memory, and communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient; a third model, stored in the memory and configured to be executed by the processor, the third model trained using third model training data, and operable to: receive the facial biometric data; determine one or more feature values of the facial biometric data; and based on the one or more feature values, generate third model output data indicating the epileptic insight; and in response to generating the third mode output data, the processor device is configured to one or more of: provide the third model output data to a user device; or store the third model output data in the memory.

[0267] 45. The system according to aspect 44, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0268] 46. The system according to aspects 44 or 45, wherein the one or more feature values indicate attributes of facial biometrics.

[0269] 47. The system according to any one of aspects 44 to 46, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient-reported seizure.

[0270] 48. The system according to any one of aspects 44 to 47, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

[0271] 49. The system according to any one of aspects 44 to 48, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

[0272] 50. The system according to any one of aspects 44 to 49, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

[0273] 51 . The system according to any one of aspects 44 to 50, wherein the processor device is further configured to using the third model output data to: retrain the third model; and / or fine-tune an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight.

[0274] 52. The system according to any one of aspects 44 to 51 , wherein the processor device is further configured to: obtain additional third model training data; retrain the third model using the additional third model training data; and store the retrained third model in the memory to generate subsequent third model output data.

[0275] 53. The system according to any one of aspects 44 to 52, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0276] 54. The system according to any one of aspects 44 to 53, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

[0277] 55. The system according to aspect 51 , wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

[0278] 56. The system according to any one of aspects 44 to 55, wherein the processor device is the imaging device, the user device, or a server.

[0279] 57. The system according to any one of aspects 44 to 56, wherein the imaging device is the processor device or the user device.

[0280] 58. The system according to any one of aspects 44 to 57, wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

[0281] 59. A computer-implemented method for identifying a seizure of a patient, the computer- implemented method comprising: obtaining, by one or more processors, electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; providing, by the one or more processors, the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating the seizure of the patient; and in response to generating the first model output data, one or more of: providing, by the one or more processors, the first model output data to a user device; or storing, by the one or more processors, the first model output data in a memory.

[0282] 60. The computer-implemented method according to aspect 59, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0283] 61 . The computer-implemented method according to aspects 59 or 60, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0284] 62. The computer-implemented method according to any one of aspects 59 to 61 , wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

[0285] 63. The computer-implemented method according to any one of aspects 59 to 62, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0286] 64. The computer-implemented method according to any one of aspects 59 to 63, further comprising: in response to identifying the seizure in the EEG data and the facial biometric data, applying, by the one or more processors, at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identifying, by the one or more processors, an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identifying, by the one or more processors, a facial biometric pattern in the facial biometric data corresponding to the seizure.

[0287] 65. The computer-implemented method according to aspect 64, wherein identifying the seizure in the EEG data and the facial biometric data further comprises: identifying, by the one or more processors, in the EEG data, an EEG pattern potentially indicating the seizure; and determining, by the one or more processors, the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

[0288] 66. The computer-implemented method according to any one of aspects 59 to 65, further comprising using the first model output data to one or more of: retrain, by the one or more processors, the first model; fine-tune, by the one or more processors, a seizure detection modelwhich operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure; or provide healthcare to at least one other patient.

[0289] 67. The computer-implemented method according to any one of aspects 59 to 66, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0290] 68. The computer-implemented method according to any one of aspects 59 to 67, further comprising: obtaining, by the one or more processors, additional first model training data; retraining, by the one or more processors, the first model using the additional first model training data; and storing, by the one or more processors, the retrained first model in the memory to generate subsequent first model output data.

[0291] 69. A computer-implemented method for predicting a seizure of a patient, the computer- implemented method comprising: obtaining, by one or more processors, electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; providing, by the one or more processors, the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data indicating the prediction of the seizure of the patient; and in response to generating the second model output data, one or more of: providing, by the one or more processors, the second model output data to a user device; or storing, by the one or more processors, the second model output data in a memory.

[0292] 70. The computer-implemented method according to aspect 69, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0293] 71 . The computer-implemented method according to aspects 69 or 70, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0294] 72. The computer-implemented method according to any one of claims 69 to 71 , wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

[0295] 73. The computer-implemented method according to any one of claims 69 to 72, wherein the second model output data includes one or more of a time of a predicted seizure, at least aportion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0296] 74. The computer-implemented method according to any one of claims 69 to 73, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

[0297] 75. The computer-implemented method according to any one of claims 69 to 74, further comprising using the second model output data to one or more of: retrain, by the one or more processors, the second model; fine-tune, by the one or more processors, a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure; or provide healthcare to at least one other patient.

[0298] 76. The computer-implemented method according to any one of claims 69 to 75, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0299] 77. The computer-implemented method according to any one of claims 69 to 76, further comprising: obtaining, by the one or more processors, additional second model training data; retraining, by the one or more processors, the second model using the additional second model training data; and storing, by the one or more processors, the retrained second model in the memory to generate subsequent second model output data.

[0300] 78. A computer-implemented method for generating an epileptic insight based upon facial biometrics of a patient, the computer-implemented method comprising: obtaining, by one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; providing, by the one or more processors, the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating the epileptic insight; and in response to generating the third model output data, one or more of: providing, by the one or more processors, the third model output data to a user device; or storing, by the one or more processors, the third model output data in a memory.

[0301] 79. The computer-implemented method according to aspect 78, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0302] 80. The computer-implemented method according to aspects 78 or 79, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient-reported seizure.

[0303] 81 . The computer-implemented method according to any one of claims 78 to 30, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

[0304] 82. The computer-implemented method according to any one of claims 78 to 81 , wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

[0305] 83. The computer-implemented method according to any one of claims 78 to 82, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

[0306] 84. The computer-implemented method according to any one of claims 78 to 83, further comprising using the third model output data to one or more of: retrain, by the one or more processors, the third model; fine-tune, by the one or more processors, an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight; or provide healthcare to at least one other patient.

[0307] 85. The computer-implemented method according to any one of claims 78 to 84, further comprising: obtaining, by the one or more processors, additional third model training data; retraining, by the one or more processors, the third model using the additional third model training data; and storing, by the one or more processors, the retrained third model in the memory to generate subsequent third model output data.

[0308] 86. The computer-implemented method according to any one of claims 78 to 85, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0309] 87. A first model for identifying a seizure of a patient, the first model comprising: the first model, stored on one or more memories and configured to be executed by one or more processors, the first model trained using first model training data and operable to: receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; determine one or more feature values of theEEG data and the facial biometric data; and based on the one or more feature values, generate first model output data indicating the seizure of the patient.

[0310] 88. The first model according to aspect 87, wherein the first model is a machine learning model.

[0311] 89. The first model according to aspects 87 or 88, wherein the first model is based upon a static algorithm.

[0312] 90. The first model according to any one of aspects 87 to 89, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0313] 91 . The first model according to any one of aspects 87 to 90, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0314] 92. The first model according to any one of aspects 87 to 91 , wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

[0315] 93. The first model according to any one of aspects 87 to 92, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0316] 94. The first model according to any one of aspects 87 to 93, wherein the first model is further configured, when executed by the one or more processors, to be operable to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

[0317] 95. The first model according to aspect 94, wherein to identify the seizure in the EEG data and the facial biometric data, the first model is further configured, when executed by the one ormore processors, to be operable to: identify in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

[0318] 96. A second model for predicting a seizure of a patient, the second model comprising: the second model, stored on one or more memories and configured to be executed by one or more processors, the second model trained using second model training data and operable to: receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; determine one or more feature values of the EEG data and the facial biometric data; and based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient.

[0319] 97. The second model according to aspect 96, wherein the second model is a machine learning model.

[0320] 98. The second model according to aspects 96 or 97, wherein the second model is based upon a static algorithm.

[0321] 99. The second model according to any one of aspects 96 to 98, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0322] 100. The second model according to any one of aspects 96 to 99, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0323] 101. The second model according to any one of aspects 96 to 100, wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

[0324] 102. The second model according to any one of aspects 96 to 101 , wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0325] 103. A third model for generating an epileptic insight based upon facial biometrics of a patient, the third model comprising: the third model, stored on one or more memories and configured to be executed by one or more processors, the third model trained using third model training data and operable to: receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient; determine one or more feature values of the facial biometric data; and based on the one or more feature values, generate third model output data indicating the epileptic insight.

[0326] 104. The third model according to aspect 103, wherein the third model is a machine learning model.

[0327] 105. The third model according to aspects 103 or 104, wherein the third model is based upon a static algorithm.

[0328] 106. The third model according to any one of aspects 103 to 105, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0329] 107. The third model according to any one of aspects 103 to 106, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

[0330] 108. The third model according to any one of aspects 103 to 107, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

[0331] 109. The third model according to any one of aspects 103 to 108 wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

[0332] 110. A computer-implemented method for training a first model to identify a seizure of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the first model using the first training dataset using the feature values defined for the first training dataset to generate primary first model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset; receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset;and training, by the one or more processors, a second iteration of the first model using the second training dataset using the feature values defined for the second training dataset to generate secondary first model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0333] 111. The computer-implemented method according to aspect 110, wherein:

[0334] a first model training dataset includes historical electroencephalogram (EEG) data of historical patients and historical facial biometric data of the historical patients.

[0335] 112. The computer-implemented method according to aspects 110 or 111 , wherein: the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

[0336] 113. The computer-implemented method according to any one of aspects 110 to 112, wherein the one or more attributes include one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

[0337] 114. The computer-implemented method according to any one of aspects 110 to 113, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of EEG data indicating the seizure, at least a portion of facial biometric data indicating the seizure, or a request for at least one additional facial image.

[0338] 115. The computer-implemented method according to any one of aspects 110 to 114, further comprising: obtaining, by the one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0339] 116. The computer-implemented method according to any one of aspects 110 to 115, further comprising: receiving one or more labels for the first training dataset, wherein training the first iteration of the first model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the first model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the first model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the first model output data.

[0340] 117. A computer-implemented method for training a second model to predict a seizure of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the second model using the first training dataset using the feature values defined for the first training dataset to generate primary second model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset; receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and training, by the one or more processors, a second iteration of the second model using the second training dataset using the feature values defined for the second training dataset to generate secondary second model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0341] 118. The computer-implemented method according to aspect 117, wherein: a second model training dataset includes historical electroencephalogram (EEG) data of historical patients and historical facial biometric data of the historical patients.

[0342] 119. The computer-implemented method according to aspects 117 or 118, wherein: the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

[0343] 120. The computer-implemented method according to any one of aspects 117 to 119, wherein the one or more attributes include one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

[0344] 121. The computer-implemented method according to any one of aspects 117 to 120, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of EEG data, at least a portion of facial biometric data, or a request for at least one additional facial image.

[0345] 122. The computer-implemented method according to any one of aspects 117 to 121 , further comprising: obtaining, by the one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data,generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0346] 123. The computer-implemented method according to any one of aspects 117 to 122, further comprising: receiving one or more labels for the first training dataset, wherein training the first iteration of the second model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the second model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the second model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the second model output data.

[0347] 124. A computer-implemented method for training a third model to generate an epileptic insight based upon facial biometrics of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the third model using the first training dataset using the feature values defined for the first training dataset to generate primary third model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset; receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and training, by the one or more processors, a second iteration of the third model using the second training dataset using the feature values defined for the second training dataset to generate secondary third model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

[0348] 125. The computer-implemented method according to aspect 124, wherein: a third model training dataset includes historical facial biometric data of historical patients.

[0349] 126. The computer-implemented method according to aspects 124 or 125, wherein: the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

[0350] 127. The computer-implemented method according to any one of aspects 124 to 126, wherein the one or more attributes include facial biometrics.

[0351] 128. The computer-implemented method according to any one of aspects 124 to 127, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

[0352] 129. The computer-implemented method according to any one of aspects 124 to 128, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy- related facial biometric event.

[0353] 130. The computer-implemented method according to any one of aspects 124 to 129, further comprising: obtaining, by the one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; and based upon the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

[0354] 131. The computer-implemented method according to any one of aspects 124 to 130, further comprising: receiving one or more labels for the first training dataset, wherein training the first iteration of the third model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the third model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the third model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the third model output data.

[0355] 132. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to at least: obtain (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; provide the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating a seizure of the patient; and in response to generating the first model output data, one or more of: provide the first model output data to a user device; or store the first model output data in a memory.

[0356] 133. The non-transitory computer-readable medium according to aspect 132, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0357] 134. The non-transitory computer-readable medium according to aspects 132 or 133, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0358] 135. The non-transitory computer-readable medium according to any one of aspects 132 to 134, wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

[0359] 136. The non-transitory computer-readable medium according to any one of aspects 132 to 135, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0360] 137. The non-transitory computer-readable medium according to any one of aspects 132 to 136, further comprising instructions that, when executed, cause the one or more processors to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

[0361] 138. The non-transitory computer-readable medium according to aspect 137, wherein identifying the seizure in the EEG data and the facial biometric data further comprises instructions that, when executed, cause the one or more processors to: identify, in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

[0362] 139. The non-transitory computer-readable medium according to any one of aspects 132 to 138, further comprising instructions that, when executed, cause the one or more processors to use the first model output data to: retrain the first model; and / or fine-tune a seizure detection model which operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure.

[0363] 140. The non-transitory computer-readable medium according to any one of aspects 132 to 139, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0364] 141. The non-transitory computer-readable medium according to any one of aspects 132 to 140, further comprising instructions that, when executed, cause the one or more processors to:obtain additional first model training data; retrain the first model using the additional first model training data; and store the retrained first model in the memory to generate subsequent first model output data.

[0365] 142. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to at least: obtain (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; provide the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data indicating a prediction of a seizure of the patient; and in response to generating the second model output data, one or more of: provide the second model output data to a user device; or store the second model output data in a memory.

[0366] 143. The non-transitory computer-readable medium according to aspect 142, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0367] 144. The non-transitory computer-readable medium according to aspects 142 or 143, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

[0368] 145. The non-transitory computer-readable medium according to any one of aspects 142 to 144, wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

[0369] 146. The non-transitory computer-readable medium according to any one of aspects 142 to 145, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

[0370] 147. The non-transitory computer-readable medium according to any one of aspects 142 to 146, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

[0371] 148. The non-transitory computer-readable medium according to any one of aspects 142 to 147, further comprising instructions that, when executed, cause the one or more processors touse the second model output data to: retrain the second model; and / or fine-tune a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure.

[0372] 149. The non-transitory computer-readable medium according to any one of aspects 142 to 148, wherein the user device is associated with the patient or a healthcare provider of the patient.

[0373] 150. The non-transitory computer-readable medium according to any one of aspects 142 to 149, further comprising instructions that, when executed, cause the one or more processors to: obtain additional second model training data; retrain the second model using the additional second model training data; and store the retrained second model in the memory to generate subsequent second model output data.

[0374] 151. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to: obtain facial biometric data comprising at least one facial image indicating facial biometrics of a patient; provide the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating an epileptic insight; and in response to generating the third model output data, one or more of: provide the third model output data to a user device; or store the third model output data in a memory.

[0375] 152. The non-transitory computer-readable medium according to aspect 151 , wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

[0376] 153. The non-transitory computer-readable medium according to aspects 151 or 152, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient-reported seizure.

[0377] 154. The non-transitory computer-readable medium according to any one of aspects 151 to 153, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

[0378] 155. The non-transitory computer-readable medium according to any one of aspects 151 to 154, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

[0379] 156. The non-transitory computer-readable medium according to any one of aspects 151 to 155, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

[0380] 157. The non-transitory computer-readable medium according to any one of aspects 151 to 156, further comprising instructions that, when executed by one or more processors, cause the one or more processors to use the third model output data: retrain the third model; and / or fine-tune an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight.

[0381] 158. The non-transitory computer-readable medium according to any one of aspects 151 to 157, further comprising instructions that, when executed by one or more processors, cause the one or more processors to: obtain additional third model training data; retrain the third model using the additional third model training data; and store the retrained third model in the memory to generate subsequent third model output data.

[0382] 159. The non-transitory computer-readable medium according to any one of aspects 151 to 158, wherein the user device is associated with the patient or a healthcare provider of the patient

Claims

CLAIMS1. A system for identifying a seizure of a patient, the system comprising: an implant device comprising a sensor array and a processor device, the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient, and provide the EEG data to the processing device; and the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor array via the communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; a first model, stored in the memory and configured to be executed by the microprocessor, the first model trained using first model training data, and operable to: receive the facial biometric data and the EEG data; determine one or more feature values of the facial biometric data and the EEG data; and based on the one or more feature values, generate first model output data indicating the seizure of the patient; and in response to generating the first mode output data, the processor device is configured to one or more of: provide the first model output data to a user device; or store the first model output data in the memory.

2. The system of claim 1 , wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

3. The system of claims 1 or 2, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

4. The system of any of claims 1 to 3, wherein the one or more feature values indicate attributes including one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

5. The system of any of claims 1 to 4, wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

6. The system of any of claims 1 to 5, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

7. The system of any of claims 1 to 6, wherein the processor device is further configured to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

8. The system of claims 7, wherein to identify the seizure in the EEG data and the facial biometric data, the first model is further operable to: identify, in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

9. The system of any of claims 1 to 8, wherein the processor device is further configured to use the first model output data to: retrain the first model; and / orfine-tune a seizure detection model which operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure.

10. The system of any of claims 1 to 9, wherein the user device is associated with the patient or a healthcare provider of the patient.11 . The system of any of claims 1 to 10, wherein the processor device is further configured to: obtain additional first model training data; retrain the first model using the additional first model training data; and store the retrained first model in the memory to generate subsequent first model output data.

12. The system of any of claims 1 to 11 , wherein the processor device is a wearable processor device.

13. The system of any of claims 1 to 12, wherein the processor device is embedded in the sensor array or disposed adjacent to the sensor array.

14. The system of any of claims 1 to 13, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

15. The system of claim 14, wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

16. The system of any of claims 1 to 15, wherein the processor device is the imaging device, the user device, or a server.

17. The system of any of claims 1 to 16, wherein the processor device is remote from the sensor array and is communicatively coupled to the sensor array via an Internet.

18. The system of any of claims 1 to 17, wherein the plurality of electrodes provide one or more electrical signals indicating a presence or absence of a biomarker.

19. The system of claim 18, wherein the biomarker includes epileptiform activity biomarker data determined from the EEG data received from one or more sensor arrays.

20. The system of any of claims 1 to 19, wherein the sensor array comprises a wireless transceiver.21 . The system of any of claims 1 to 20, wherein the imaging device is the processor device or the user device.

22. The system of any of claims 1 to 21 , wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

23. A system for predicting a seizure of a patient, the system comprising: an implant device comprising a sensor array and a processor device, the sensor array comprising a plurality of electrodes and a local processing device comprising local device communication circuitry, the sensor array being communicatively coupled to the processor device via communication circuitry of the local processing device, the sensor array being configured to gather electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient, and provide the EEG data to the processing device; and the processor device comprising a microprocessor, a memory, and communication circuitry, the processing device being communicatively coupled to the sensor array via the communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; a second model, stored in the memory and configured to be executed by the microprocessor, the second model trained using second model training data, and operable to: receive the facial biometric data and the EEG data; determine one or more feature values of the facial biometric data and the EEG data; and based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient; and in response to generating the second model output data, the processor device is configured to one or more of: provide the second model output data to a user device; orstore the second model output data in the memory.

24. The system of claim 23, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

25. The system of claims 23 or 24, wherein the one or more feature values indicate attributes including one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

26. The system of any of claims 23 to 25, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

27. The system of any of claims 23 to 26, wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

28. The system of any of claims 23 to 27, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

29. The system of any of claims 23 to 28, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

30. The system of any of claims 23 to 29, wherein the processor device is further configured to use the second model output data to: retrain the second model; and / or fine-tune a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure.31 . The system of any of claims 23 to 30, wherein the user device is associated with the patient or a healthcare provider of the patient.

32. The system of any of claims 23 to 31 , wherein the processor device is further configured to: obtain additional second model training data; retrain the second model using the additional second model training data; and store the retrained second model in the memory to generate subsequent second model output data.

33. The system of any of claims 23 to 32, wherein the processor device is a wearable processor device.

34. The system of any of claims 23 to 33, wherein the processor device is embedded in the sensor array or disposed adjacent to the sensor array.

35. The system of any of claims 23 to 34, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

36. The system of claim 35, wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

37. The system of any of claims 23 to 36, wherein the processor device is the imaging device, the user device, or a server.

38. The system of any of claims 23 to 37, wherein the processor device is remote from the sensor array and is communicatively coupled to the sensor array via an Internet.

39. The system of any of claims 23 to 38, wherein the plurality of electrodes provide one or more electrical signals indicating a presence or absence of a biomarker.

40. The system of claim 39, wherein the biomarker includes epileptiform activity biomarker data determined from the EEG data received from one or more sensor arrays.41 . The system of any of claims 23 to 40, wherein the sensor array comprises a wireless transceiver.

42. The system of any of claims 23 to 41 , wherein the imaging device is the processor device or the user device.

43. The system of any of claims 23 to 42, wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

44. A system for generating an epileptic insight based upon facial biometrics of a patient, the system comprising: a processor device comprising a processor, a memory, and communication circuitry; an imaging device configured to generate facial biometric data comprising at least one facial image captured by the imaging device, the at least one facial image indicating facial biometrics of the patient; a third model, stored in the memory and configured to be executed by the processor, the third model trained using third model training data, and operable to: receive the facial biometric data; determine one or more feature values of the facial biometric data; and based on the one or more feature values, generate third model output data indicating the epileptic insight; and in response to generating the third mode output data, the processor device is configured to one or more of: provide the third model output data to a user device; or store the third model output data in the memory.

45. The system of claim 44, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

46. The system of claims 44 or 45, wherein the one or more feature values indicate attributes of facial biometrics.

47. The system of any of claims 44 to 46, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient-reported seizure.

48. The system of any of claims 44 to 47, wherein:the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

49. The system of any of claims 44 to 48, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

50. The system of any of claims 44 to 49, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.51 . The system of any of claims 44 to 50, wherein the processor device is further configured to using the third model output data to: retrain the third model; and / or fine-tune an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight.

52. The system of any of claims 44 to 51 , wherein the processor device is further configured to: obtain additional third model training data; retrain the third model using the additional third model training data; and store the retrained third model in the memory to generate subsequent third model output data.

53. The system of any of claims 44 to 52, wherein the user device is associated with the patient or a healthcare provider of the patient.

54. The system of any of claims 44 to 53, wherein the processor device communicates wirelessly with one or more of a server, the imaging device, or the user device.

55. The system of claim 51 , wherein the user device is configured to communicate data from the processor device and / or the imaging device to one or more servers via a network.

56. The system of any of claims 44 to 55, wherein the processor device is the imaging device, the user device, or a server.

57. The system of any of claims 44 to 56, wherein the imaging device is the processor device or the user device.

58. The system of any of claims 44 to 57, wherein the imaging device communicates wirelessly with a server, the processor device and / or the user device.

59. A computer-implemented method for identifying a seizure of a patient, the computer- implemented method comprising: obtaining, by one or more processors, electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; providing, by the one or more processors, the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating the seizure of the patient; and in response to generating the first model output data, one or more of: providing, by the one or more processors, the first model output data to a user device; or storing, by the one or more processors, the first model output data in a memory.

60. The computer-implemented method of claim 59, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.61 . The computer-implemented method of claims 59 or 60, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

62. The computer-implemented method of any of claims 59 to 61 , wherein:the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

63. The computer-implemented method of any of claims 59 to 62, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

64. The computer-implemented method of any of claims 59 to 63, further comprising: in response to identifying the seizure in the EEG data and the facial biometric data, applying, by the one or more processors, at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identifying, by the one or more processors, an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identifying, by the one or more processors, a facial biometric pattern in the facial biometric data corresponding to the seizure.

65. The computer-implemented method of claim 64, wherein identifying the seizure in the EEG data and the facial biometric data further comprises: identifying, by the one or more processors, in the EEG data, an EEG pattern potentially indicating the seizure; and determining, by the one or more processors, the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

66. The computer-implemented method of any of claims 59 to 65, further comprising using the first model output data to one or more of: retrain, by the one or more processors, the first model;fine-tune, by the one or more processors, a seizure detection model which operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure; or provide healthcare to at least one other patient.

67. The computer-implemented method of any of claims 59 to 66, wherein the user device is associated with the patient or a healthcare provider of the patient.

68. The computer-implemented method of any of claims 59 to 67, further comprising: obtaining, by the one or more processors, additional first model training data; retraining, by the one or more processors, the first model using the additional first model training data; and storing, by the one or more processors, the retrained first model in the memory to generate subsequent first model output data.

69. A computer-implemented method for predicting a seizure of a patient, the computer- implemented method comprising: obtaining, by one or more processors, electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of the patient and gathered via an implant device of the patient; and facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; providing, by the one or more processors, the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data indicating the prediction of the seizure of the patient; and in response to generating the second model output data, one or more of: providing, by the one or more processors, the second model output data to a user device; or storing, by the one or more processors, the second model output data in a memory.

70. The computer-implemented method of claim 69, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.71 . The computer-implemented method of claims 69 or 70, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

72. The computer-implemented method of any one of claims 69 to 71 , wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

73. The computer-implemented method of any one of claims 69 to 72, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

74. The computer-implemented method of any one of claims 69 to 73, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

75. The computer-implemented method of any one of claims 69 to 74, further comprising using the second model output data to one or more of: retrain, by the one or more processors, the second model; fine-tune, by the one or more processors, a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure; or provide healthcare to at least one other patient.

76. The computer-implemented method of any one of claims 69 to 75, wherein the user device is associated with the patient or a healthcare provider of the patient.

77. The computer-implemented method of any one of claims 69 to 76, further comprising: obtaining, by the one or more processors, additional second model training data; retraining, by the one or more processors, the second model using the additional second model training data; andstoring, by the one or more processors, the retrained second model in the memory to generate subsequent second model output data.

78. A computer-implemented method for generating an epileptic insight based upon facial biometrics of a patient, the computer-implemented method comprising: obtaining, by one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; providing, by the one or more processors, the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating the epileptic insight; and in response to generating the third model output data, one or more of: providing, by the one or more processors, the third model output data to a user device; or storing, by the one or more processors, the third model output data in a memory.

79. The computer-implemented method of claim 78, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

80. The computer-implemented method of claims 78 or 79, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient-reported seizure.81 . The computer-implemented method of any one of claims 78 to 80, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

82. The computer-implemented method of any one of claims 78 to 81 , wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

83. The computer-implemented method of any one of claims 78 to 82, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect ofepilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

84. The computer-implemented method of any one of claims 78 to 83, further comprising using the third model output data to one or more of: retrain, by the one or more processors, the third model; fine-tune, by the one or more processors, an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight; or provide healthcare to at least one other patient.

85. The computer-implemented method of any one of claims 78 to 84, further comprising: obtaining, by the one or more processors, additional third model training data; retraining, by the one or more processors, the third model using the additional third model training data; and storing, by the one or more processors, the retrained third model in the memory to generate subsequent third model output data.

86. The computer-implemented method of any one of claims 78 to 85, wherein the user device is associated with the patient or a healthcare provider of the patient.

87. A first model for identifying a seizure of a patient, the first model comprising: the first model, stored on one or more memories and configured to be executed by one or more processors, the first model trained using first model training data and operable to: receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; determine one or more feature values of the EEG data and the facial biometric data; and based on the one or more feature values, generate first model output data indicating the seizure of the patient.

88. The first model of claim 87, wherein the first model is a machine learning model.

89. The first model of claims 87 or 88, wherein the first model is based upon a static algorithm.

90. The first model of any of claims 87 to 89, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.91 . The first model of any of claims 87 to 90, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

92. The first model of any of claims 87 to 91 , wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

93. The first model of any of claims 87 to 92, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

94. The first model of any of claims 87 to 93, wherein the first model is further configured, when executed by the one or more processors, to be operable to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

95. The first model of claim 94, wherein to identify the seizure in the EEG data and the facial biometric data, the first model is further configured, when executed by the one or more processors, to be operable to: identify in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

96. A second model for predicting a seizure of a patient, the second model comprising: the second model, stored on one or more memories and configured to be executed by one or more processors, the second model trained using second model training data and operable to: receive electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; determine one or more feature values of the EEG data and the facial biometric data; and based on the one or more feature values, generate second model output data indicating the prediction of the seizure of the patient.

97. The second model of claim 96, wherein the second model is a machine learning model.

98. The second model of claims 96 or 97, wherein the second model is based upon a static algorithm.

99. The second model of any of claims 96 to 98, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

100. The second model of any of claims 96 to 99, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.101 . The second model of any of claims 96 to 100, wherein:the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

102. The second model of any of claims 96 to 101 , wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

103. A third model for generating an epileptic insight based upon facial biometrics of a patient, the third model comprising: the third model, stored on one or more memories and configured to be executed by one or more processors, the third model trained using third model training data and operable to: receive facial biometric data comprising at least one facial image indicating facial biometrics of the patient; determine one or more feature values of the facial biometric data; and based on the one or more feature values, generate third model output data indicating the epileptic insight.

104. The third model of claim 103, wherein the third model is a machine learning model.

105. The third model of claims 103 or 104, wherein the third model is based upon a static algorithm.

106. The third model of any of claims 103 to 105, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

107. The third model of any of claims 103 to 106, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

108. The third model of any of claims 103 to 107, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

109. The third model of any of claims 103 to 108, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

110. A computer-implemented method for training a first model to identify a seizure of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the first model using the first training dataset using the feature values defined for the first training dataset to generate primary first model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset; receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and training, by the one or more processors, a second iteration of the first model using the second training dataset using the feature values defined for the second training dataset to generate secondary first model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

111. The computer-implemented method of claim 110, wherein: a first model training dataset includes historical electroencephalogram (EEG) data of historical patients and historical facial biometric data of the historical patients.

112. The computer-implemented method of claims 110 or 111 , wherein: the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

113. The computer-implemented method of any of claims 110 to 112, wherein the one or more attributes include one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

114. The computer-implemented method of any of claims 110 to 113, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of EEG data indicating the seizure, at least a portion of facial biometric data indicating the seizure, or a request for at least one additional facial image.

115. The computer-implemented method of any of claims 110 to 114, further comprising: obtaining, by the one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

116. The computer-implemented method of any of claims 110 to 115, further comprising: receiving one or more labels for the first training dataset, wherein training the first iteration of the first model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the first model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the first model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the first model output data.

117. A computer-implemented method for training a second model to predict a seizure of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the second model using the first training dataset using the feature values defined for the first training dataset to generate primary second model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset;receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and training, by the one or more processors, a second iteration of the second model using the second training dataset using the feature values defined for the second training dataset to generate secondary second model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

118. The computer-implemented method of claim 117, wherein: a second model training dataset includes historical electroencephalogram (EEG) data of historical patients and historical facial biometric data of the historical patients.

119. The computer-implemented method of claims 117 or 118, wherein: the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

120. The computer-implemented method of any of claims 117 to 119, wherein the one or more attributes include one or more or epileptiform activity, EEG spikes, EEG sharps, or facial biometrics.

121. The computer-implemented method of any of claims 117 to 120, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of EEG data, at least a portion of facial biometric data, or a request for at least one additional facial image.

122. The computer-implemented method of any of claims 117 to 121 , further comprising: obtaining, by the one or more processors, (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; and based upon the EEG data and the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

123. The computer-implemented method of any of claims 117 to 122, further comprising:receiving one or more labels for the first training dataset, wherein training the first iteration of the second model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the second model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the second model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the second model output data.

124. A computer-implemented method for training a third model to generate an epileptic insight based upon facial biometrics of a patient, the computer-implemented method comprising: obtaining, by one or more processors, a first training dataset; receiving as feature values, by the one or more processors, a selection of one or more attributes of the first training dataset; training, by the one or more processors, a first iteration of the third model using the first training dataset using the feature values defined for the first training dataset to generate primary third model output data having associated first error rates; obtaining, by the one or more processors, a second training dataset; receiving as feature values, by the one or more processors, the selection of one or more attributes of the second training dataset; and training, by the one or more processors, a second iteration of the third model using the second training dataset using the feature values defined for the second training dataset to generate secondary third model output data having associated second error rates, wherein the second error rates have a reduced overall error rate compared to an overall error rate of the first error rates.

125. The computer-implemented method of claim 124, wherein: a third model training dataset includes historical facial biometric data of historical patients.

126. The computer-implemented method of claims 124 or 125, wherein: the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

127. The computer-implemented method of any of claims 124 to 126, wherein the one or more attributes include facial biometrics.

128. The computer-implemented method of any of claims 124 to 127, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

129. The computer-implemented method of any of claims 124 to 128, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

130. The computer-implemented method of any of claims 124 to 129, further comprising: obtaining, by the one or more processors, facial biometric data comprising at least one facial image indicating facial biometrics of the patient; and based upon the facial biometric data, generating, by the one or more processors, one or more of the first training dataset or the second training dataset.

131. The computer-implemented method of any of claims 124 to 130, further comprising: receiving one or more labels for the first training dataset, wherein training the first iteration of the third model using the first training dataset further comprises using the one or more labels for the first training dataset to generate the third model output data; and receiving one or more labels for the second training dataset, wherein training the second iteration of the third model using the second training dataset further comprises using the one or more labels for the second training dataset to generate the third model output data.

132. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to at least: obtain (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; provide the facial biometric data and the EEG data to a first model, trained using first model training data, to generate first model output data indicating a seizure of the patient; and in response to generating the first model output data, one or more of: provide the first model output data to a user device; orstore the first model output data in a memory.

133. The non-transitory computer-readable medium of claim 132, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

134. The non-transitory computer-readable medium of claims 132 or 133, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

135. The non-transitory computer-readable medium of any of claims 132 to 134, wherein: the first model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the first model is trained to make associations between historical seizures, historical EEG patterns indicating the historical seizures, and historical facial biometrics indicating the historical seizures.

136. The non-transitory computer-readable medium of any of claims 132 to 135, wherein the first model output data includes one or more of a classification of the seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

137. The non-transitory computer-readable medium of any of claims 132 to 136, further comprising instructions that, when executed, cause the one or more processors to: in response to identifying the seizure in the EEG data and the facial biometric data, apply at least one label associated with the seizure to one or more of the first model output data, the EEG data, or the facial biometric data; in response to identifying the seizure in the facial biometric data and not identifying the seizure the EEG data, identify an EEG pattern in the EEG data corresponding to the seizure; and in response to identifying the seizure in the EEG data and not identifying the seizure in the facial biometric data, identify a facial biometric pattern in the facial biometric data corresponding to the seizure.

138. The non-transitory computer-readable medium of claim 137, wherein identifying the seizure in the EEG data and the facial biometric data further comprises instructions that, when executed, cause the one or more processors to: identify, in the EEG data, an EEG pattern potentially indicating the seizure; and determine the EEG pattern potentially indicating the seizure, is indicating the seizure, based upon a facial biometric pattern in the facial biometric data indicating the seizure.

139. The non-transitory computer-readable medium of any of claims 132 to 138, further comprising instructions that, when executed, cause the one or more processors to use the first model output data to: retrain the first model; and / or fine-tune a seizure detection model which operates on the EEG data to detect the seizure, to further operate on the facial biometric data to detect the seizure.

140. The non-transitory computer-readable medium of any of claims 132 to 139, wherein the user device is associated with the patient or a healthcare provider of the patient.

141. The non-transitory computer-readable medium of any of claims 132 to 140, further comprising instructions that, when executed, cause the one or more processors to: obtain additional first model training data; retrain the first model using the additional first model training data; and store the retrained first model in the memory to generate subsequent first model output data.

142. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to at least: obtain (i) electroencephalogram (EEG) data comprising at least one EEG signal associated with a brain of a patient and gathered via an implant device of the patient; and (ii) facial biometric data comprising at least one facial image indicating facial biometrics of the patient, wherein at least a portion of the at least one facial image is captured while the EEG data is gathered; provide the facial biometric data and the EEG data to a second model, trained using second model training data, to generate second model output data indicating a prediction of a seizure of the patient; and in response to generating the second model output data, one or more of: provide the second model output data to a user device; orstore the second model output data in a memory.

143. The non-transitory computer-readable medium of claim 142, wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

144. The non-transitory computer-readable medium of claims 142 or 143, wherein the at least one facial image includes baseline facial biometrics associated with a period during which the patient is not experiencing the seizure.

145. The non-transitory computer-readable medium of any of claims 142 to 144, wherein: the second model training data includes historical EEG data of historical patients and historical facial biometric data of the historical patients; and the second model is trained to make associations between historical seizures, historical facial biometrics predicting the historical seizures, and historical EEG patterns predicting the historical seizures.

146. The non-transitory computer-readable medium of any of claims 142 to 145, wherein the second model output data includes one or more of a time of a predicted seizure, at least a portion of the EEG data, at least a portion of the facial biometric data, or a request for at least one additional facial image.

147. The non-transitory computer-readable medium of any of claims 142 to 146, wherein the second model output data is provided to the user device proximate a time of a predicted seizure.

148. The non-transitory computer-readable medium of any of claims 142 to 147, further comprising instructions that, when executed, cause the one or more processors to use the second model output data to: retrain the second model; and / or fine-tune a seizure prediction model which operates on the EEG data to predict the seizure, to further operate on the facial biometric data to predict the seizure.

149. The non-transitory computer-readable medium of any of claims 142 to 148, wherein the user device is associated with the patient or a healthcare provider of the patient.

150. The non-transitory computer-readable medium of any of claims 142 to 149, further comprising instructions that, when executed, cause the one or more processors to: obtain additional second model training data; retrain the second model using the additional second model training data; and store the retrained second model in the memory to generate subsequent second model output data.151 . A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to: obtain facial biometric data comprising at least one facial image indicating facial biometrics of a patient; provide the facial biometric data to a third model, trained using third model training data, to generate third model output data indicating an epileptic insight; and in response to generating the third model output data, one or more of: provide the third model output data to a user device; or store the third model output data in a memory.

152. The non-transitory computer-readable medium of claim 151 , wherein the facial biometrics indicate one or more of an iris change, a pupil dilation, a blinking pattern, a facial expression, or a gaze direction.

153. The non-transitory computer-readable medium of claims 151 or 152, wherein the facial biometric data includes at least one baseline facial image indicating baseline facial biometrics of the patient, and / or data indicating the at least one facial image is captured during a patient- reported seizure.

154. The non-transitory computer-readable medium of any of claims 151 to 153, wherein: the third model training data includes historical facial biometric data of historical patients; and the third model is trained to make associations between historical facial biometrics, and historical epileptic insights indicated by the historical facial biometrics.

155. The non-transitory computer-readable medium of any of claims 151 to 154, wherein the third model output data includes the epileptic insight and / or a request for at least one additional facial image.

156. The non-transitory computer-readable medium of any of claims 151 to 155, wherein the epileptic insight includes one or more of: an indication the patient is experiencing a side-effect of epilepsy medication, a suggested time to take the epilepsy medication to minimize the side-effect, an indication of a seizure, a prediction of the seizure, or a prediction of an epilepsy-related facial biometric event.

157. The non-transitory computer-readable medium of any of claims 151 to 156, further comprising instructions that, when executed by one or more processors, cause the one or more processors to use the third model output data: retrain the third model; and / or fine-tune an epileptic insight model which does not operate on the facial biometric data to generate the epileptic insight, to further operate on the facial biometric data to generate the epileptic insight.

158. The non-transitory computer-readable medium of any of claims 151 to 157, further comprising instructions that, when executed by one or more processors, cause the one or more processors to: obtain additional third model training data; retrain the third model using the additional third model training data; and store the retrained third model in the memory to generate subsequent third model output data.

159. The non-transitory computer-readable medium of any of claims 151 to 158, wherein the user device is associated with the patient or a healthcare provider of the patient.