Seizure detection using the wristband accelerometer, gyroscope, and surface electromyogram signals based on in-hospital and out-of-hospital dataset

Objective: Wearable devices are effective for detecting generalized tonic-clonic seizures (GTCS). However, many daily activities are often misclassified as GTCS, leading to a decline in user confidence. This study recommends utilizing wristband three-axis accelerometer (ACC), three-axis gyroscope (GYRO), and surface electromyography (sEMG) signals for GTCS detection and presents a novel seizure detection algorithm that offers high sensitivity and a reduced false alarm rate (FAR). Methods: Inpatients with epilepsy and out-of-hospital healthy subjects were recruited and required to wear a wristband device to collect wristband signals. The proposed algorithm comprises five steps: preprocessing, motion filtering, feature extraction, classification, and postprocessing. The variations in performance across different signal combinations were compared. Additionally, the impact of training the model using only inpatient data versus the complete dataset on the algorithm's performance was also investigated. Results: Wristband signals were collected from 45 patients and 30 healthy subjects, encompassing a total of 3367.3 h and including 60 GTCS. The proposed algorithm achieved 100 % sensitivity and a FAR of 0.1070/24 h. It demonstrated higher sensitivity and lower FAR compared to combinations with fewer signal modalities. In addition, the model trained on only in-hospital data demonstrates high sensitivity (98.33 %) and high FAR (0.9845/24 h). Significance: The algorithm proposed for detecting GTCS using wristband ACC, GYRO, and sEMG signals achieved encouraging results, demonstrating the feasibility of this signal combination. Furthermore, incorporating out-of-hospital data into model training proved to be an effective solution for reducing FAR, which could facilitate the clinical application of seizure detection algorithms.