Classification of Scalp EEG States Prior to Clinical Seizure Onset

Daniel Jacobs; Yuhan H Liu; Trevor Hilton; Martin Del Campo; Peter L Carlen; Berj L Bardakjian

doi:10.1109/JTEHM.2019.2926257

Classification of Scalp EEG States Prior to Clinical Seizure Onset

IEEE J Transl Eng Health Med. 2019 Aug 16:7:2000203. doi: 10.1109/JTEHM.2019.2926257. eCollection 2019.

Authors

Daniel Jacobs¹, Yuhan H Liu², Trevor Hilton¹, Martin Del Campo³, Peter L Carlen^{1

3

4}, Berj L Bardakjian^{1

2}

Affiliations

¹ 1Institute of Biomaterials and Biomedical Engineering, University of TorontoTorontoONM5S 3G9Canada.
² 2Department of Electrical and Computer EngineeringUniversity of TorontoTorontoONM5S 3G9Canada.
³ 3Department of Medicine (Neurology)Toronto Western HospitalTorontoONM5T 2S8Canada.
⁴ 4Krembil Research Institute, University Health NetworkTorontoONM5T 2S8Canada.

Abstract

Objective: To investigate the feasibility of improving the performance of an EEG-based multistate classifier (MSC) previously proposed by our group.

Results: Using the random forest (RF) classifiers on the previously reported dataset of patients, but with three improvements to classification logic, the specificity of our alarm algorithm improves from 82.4% to 92.0%, and sensitivity from 87.9% to 95.2%.

Discussion: The MSC could be a useful approach for seizure-monitoring both in the clinic and at home.

Methods: Three improvements to the MSC are described. Firstly, an additional check using RF outputs is made prior to alarm to confirm increasing probability of a seizure onset state. Secondly, a post-alarm detection horizon that accounts for the seizure state duration is implemented. Thirdly, the alarm decision window is kept constant.

Keywords: Epilepsy; clinical seizure onset; cross-frequency coupling features; early detection; patient trial.

Grants and funding

This work was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Canadian Institutes of Health Research (CIHR).