Title : Machine learning for epileptic seizure detection and prediction: Non-invasive approaches using wearable technology
Abstract:
Epilepsy, a brain disorder causing recurring seizures, affects approximately 65 million people worldwide, making it one of the most common neurological diseases. Additionally, epilepsy severely reduces individuals' quality of life, with a disability-adjusted life year (DALY) of 0.657—where 1 represents full disability—indicating a substantial reduction in health (Mehndiratta & Wadhai, 2015). There is a need to predict seizures in real time and warn patients or caregivers of imminent seizures. We hypothesized that machine learning could be leveraged to predict seizures in real time and provide timely warnings to patients or caregivers.
Using two datasets—CHB-MIT and Siena Scalp EEG—comprising 1160 hours of data from patients aged 0.5 to 71, we trained four models for seizure detection (K-Nearest Neighbors, Logistic Regression, Random Forest Classifier, Support Vector Machine) and one for prediction (Long Short-Term Memory). Evaluation metrics, including accuracy, recall, precision, and F1-score, showed a detection accuracy of 98.67%. Subsequently, the model was integrated with a wearable EEG headset (Muse) and a web app was developed that successfully predicts seizures 5 minutes ahead of time, with 84.54% accuracy. This work demonstrates the potential of machine learning to enhance seizure prediction and improve patient safety.
