Multi-task seizure detection: addressing intra-patient variation in seizure morphologies

Abstract

The accurate and early detection of epileptic seizures in continuous electroencephalographic (EEG) data has a growing role in the management of patients with epilepsy. Early detection allows for therapy to be delivered at the start of seizures and for caregivers to be notified promptly about potentially debilitating events. The challenge to detecting epileptic seizures, however, is that seizure morphologies exhibit considerable inter-patient and intra-patient variability. While recent work has looked at addressing the issue of variations across different patients (inter-patient variability) and described patient-specific methodologies for seizure detection, there are no examples of systems that can simultaneously address the challenges of inter-patient and intra-patient variations in seizure morphology. In our study, we address this complete goal and describe a multi-task learning approach that trains a classifier to perform well across many kinds of seizures rather than potentially overfitting to the most common seizure types. Our approach increases the generalizability of seizure detection systems and improves the tradeoff between latency and sensitivity versus false positive rates. When compared against the standard approach on the CHB–MIT multi-channel scalp EEG data, our proposed method improved discrimination between seizure and non-seizure EEG for almost 83 % of the patients while reducing false positives on nearly 70 % of the patients studied.