Systems for analyzing patterns in electrodermal activity recordings of patients to predict seizure likelihood and methods of use thereof

Abstract

Systems and methods of the present disclosure enable improved seizure detection and/or prediction using a seizure monitoring system. The system receives a data stream including wearable sensor data associated with a user, where the data stream includes electrodermal activity data and where the electrodermal activity data includes circadian rhythm-dependent amplitudes. The system receives a time associated with a seizure of the user. The system trains seizure machine learning model to identify a pre-ictal period associated with a time segment based on the circadian rhythm dependent amplitudes and the time associated with the seizure. The system deploys the seizure machine learning model to ingest a new data stream. Based on the new data stream, the seizure machine learning model predicts a seizure likelihood in a prediction period.

Dependencies are inferred from the claim text.