Automated Seizure Detection: Unrecognized Challenges, Unexpected Insights

TL;DR

This study compares three signal analysis methods for seizure detection to evaluate the feasibility of a universal seizure definition, revealing challenges due to variability in seizure signals and suggesting insights into clinical consensus.

Contribution

It introduces and compares three novel signal analysis techniques for seizure detection, highlighting challenges in establishing a universal seizure definition.

Findings

Methods show fluctuating concordance depending on seizure duration.

Spectral non-stationarity affects seizure detection accuracy.

Clinical consensus on seizure definition may be attainable despite challenges.

Abstract

One of epileptology's fundamental aims is the formulation of a universal, internally consistent seizure definition. To assess this aim's feasibility, three signal analysis methods were applied to a seizure time series and performance comparisons were undertaken among them and with respect to a validated algorithm. One of the methods uses a Fisher's matrix weighted measure of the rate of parameters change of a 2n order auto-regressive model, another is based on the Wavelet Transform Maximum Modulus for quantification of changes in the logarithm of the standard deviation of ECoG power and yet another employs the ratio of short-to-long term averages computed from cortical signals. The central finding, fluctuating concordance among all methods' output as a function of seizure duration, uncovers unexpected hurdles in the path to a universal definition, while furnishing relevant knowledge in the dynamical (spectral non-stationarity and varying ictal signal complexity) and clinical (probable attainability of consensus) domains.