Automated Interictal Epileptiform Discharge Detection From Scalp EEG Using Scalable Time-series Classification Approaches

Abstract

Deep learning for automated interictal epileptiform discharge (IED) detection has been topical with many published papers in recent years. All existing work viewed EEG signals as time-series and developed specific models for IED classification; however, general time-series classification (TSC) methods were not considered. Moreover, none of these methods were evaluated on any public datasets, making direct comparisons challenging. This paper explored two state-of-the-art convolutional-based TSC algorithms, InceptionTime and Minirocket, on IED detection. We fine-tuned and cross-evaluated them on two private and public (Temple University Events - TUEV) datasets and provided ready metrics for benchmarking future work. We observed that the optimal parameters correlated with the clinical duration of an IED and achieved the best AUC, AUPRC and F1 scores of 0.98, 0.80 and 0.77 on the private datasets, respectively. The AUC, AUPRC and F1 on TUEV were 0.99, 0.99 and 0.97, respectively. While algorithms trained on the private sets maintained the performance when tested on the TUEV data, those trained on TUEV could not generalise well to the private data. These results emerge from differences in the class distributions across datasets and indicate a need for public datasets with a better diversity of IED waveforms, background activities and artifacts to facilitate standardisation and benchmarking of algorithms.