Augmented neuromodulation and biofeedback for symptom intervention

A system comprising a non-transitory computer-readable storage medium storing instructions for execution and a hardware processor configured to execute the instructions, the instructions, when executed, cause the hardware processor to perform steps comprising:

• monitoring a plurality of movement signals at a muscle group of a foot, a shank, or a thigh of a user, the movement signals representative of a phase in a gait cycle of the user;
• determining, using a machine-learned model configured to identify an onset of a symptom of a physical condition based on the monitored plurality of movement signals, that the user is exhibiting the symptom of a plurality of symptoms of the physical condition, wherein the machine-learned model is trained using a first training set comprising historical activity data collected from sensors monitoring a plurality of users having the physical condition, the first training set being labeled with symptom onset events for said plurality of users and wherein the model is retrained by adjusting parameters of the model in response to a second training set comprising data representative of measured movement collected from the user, the second training set being labeled with symptom onset events detected for the user such that the machine-learned model is customized to the user;
• based on a magnitude of the symptom exhibited by the user and characteristics of the user, identifying a neuromodulation operation comprising an electrical stimulation signal to mitigate the symptom;
• and
• applying the identified neuromodulation operation to the user via a wearable neuromodulation system comprising a plurality of electrodes physically coupled to the user.

A non-transitory computer readable storage medium storing executable instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:

• monitoring a plurality of movement signals at a muscle group of a foot, a shank, or a thigh of a user, the movement signals representative of a phase in a gait cycle of the user;
• determining, using a machine-learned model configured to identify an onset of a symptom of a physical condition based on the monitored plurality of movement signals, that the user is exhibiting the symptom of a plurality of symptoms of the physical condition, wherein the machine-learned model is trained using a first training set comprising historical activity data collected from sensors monitoring a plurality of users having the physical condition, the first training set being labeled with symptom onset events for said plurality of users and wherein the model is retrained by adjusting parameters of the model in response to a second training set comprising data representative of measured movement collected from the user, the second training set being labeled with symptom onset events detected for the user such that the machine-learned model is customized to the user;
• based on a magnitude of the symptom exhibited by the user and characteristics of the user, identifying a neuromodulation operation comprising an electrical stimulation signal to mitigate the symptom;
• and
• applying the identified neuromodulation operation to the user via a wearable neuromodulation system comprising a plurality of electrodes physically coupled to the user.