An automated, machine learning-based detection algorithm for spike-wave discharges (SWDs) in a mouse model of absence epilepsy

Abstract

Summary and KeywordsObjectiveManual detection of spike-wave discharges (SWDs) from EEG records is time intensive, costly, and subject to inconsistencies/biases. Additionally, manual scoring often omits information on SWD confidence/intensity which may be important for the investigation of mechanistic-based research questions. Our objective is to develop an automated method for the detection of SWDs in a mouse model of absence epilepsy that is focused on the characteristics of human scoring of pre-selected events to establish a confidence-based, continuous-valued scoring.MethodsWe develop a support vector machine (SVM)-based algorithm for the automated detection of SWDs in the γ2R43Q mouse model of absence epilepsy. The algorithm first identifies putative SWD events using frequency- and amplitude-based peak detection. Four humans scored a set of 2500 putative events identified by the algorithm. Then, using predictors calculated from the wavelet transform of each event and the labels from human scoring, we trained a SVM to classify (SWD/nonSWD) and assign confidence scores to each event identified from 60 24-hour EEG records. We provide a detailed assessment of intra- and inter-rater scoring that demonstrates advantages of automated scoring.ResultsThe algorithm scored SWDs along a continuum that is highly correlated with human confidence and that allows us to more effectively characterize ambiguous events. We demonstrate that events along our scoring continuum are temporally and proportionately correlated with abrupt changes in spectral power bands relevant to normal behavioral states including sleep.SignificanceWhile there are automated and semi-automated methods for the detection of SWDs in humans and rats, we contribute to the need for continued development of SWD detection in mice. Our results demonstrate the value of viewing detection of SWDs as a continuous classification problem to better understand ‘ground truth’ in SWD detection (i.e., the most reliable features agreed upon by humans that also correlate with objective physiological measures).Key Point BoxClinicians and researchers may benefit from an automated method of SWD detection that provides a framework for the quantitative description of SWDs and how they relate to other electrographic events.We present an algorithm for the automated, consistent, and rapid scoring of SWDs that assigns a confidence to detected events that is highly correlated with human scoring confidence.We characterize the human inter- and intra-rater consistency in the scoring of potential SWD events and compare them with the algorithm.Events along the scoring continuum generated by the algorithm are temporally and proportionately correlated with changes in spectral power bands relevant to behavioral states including sleep.