Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection.

Thijs Becker,Kaat Vandecasteele,Maarten De Vos,Christos Chatzichristos,Wim Van Paesschen,Dirk Valkenborg,Sabine Van Huffel

doi:10.3390/s21041046

Thijs Becker, Kaat Vandecasteele + Show 5 more

Open Access

https://doi.org/10.3390/s21041046

Copy DOI

Abstract

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

Highlights

Epilepsy is a neurological disorder that affects around 0.8% of the population worldwide [1]
We investigated the support vector machine (SVM) models that were trained to perform automated seizure detection on patients with focal epilepsy in [23]
For detecting 5-min segments that contain false negatives our results suggest that SVM confidences and trust scores behave

Summary

Introduction

Epilepsy is a neurological disorder that affects around 0.8% of the population worldwide [1]. Seizures are detected with devices that record biosignals, most commonly full scalp electroencephalography (EEG) [6], which is uncomfortable to wear for a long period of time. Other biosignals such as electrocardiograms, electromyograms, accelerometry and EEG from behind-the-ear sensors can be used outside the hospital [7]. They have the advantage that those measuring devices are more tolerated when being worn for an extended period of time. Combining several of these biosignals can improve seizure detection performance [8,9]

Methods

Results

Discussion

Conclusion