Performance metrics for online seizure prediction

Hsiang-Han Chen; Vladimir Cherkassky

doi:10.1016/j.neunet.2020.04.022

Performance metrics for online seizure prediction

Neural Netw. 2020 Aug:128:22-32. doi: 10.1016/j.neunet.2020.04.022. Epub 2020 Apr 29.

Authors

Hsiang-Han Chen¹, Vladimir Cherkassky²

Affiliations

¹ Bioinformatics and Computational Biology, University of Minnesota, Minneapolis, MN 55455, USA. Electronic address: chen4646@umn.edu.
² Bioinformatics and Computational Biology, University of Minnesota, Minneapolis, MN 55455, USA; Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, USA. Electronic address: cherk001@umn.edu.

Abstract

Many recent studies on online seizure prediction from iEEG signal describe various prediction algorithms and their prediction performance. In contrast, this paper focuses on proper specification of system parameters, such as prediction period, prediction horizon and data-driven characterization of lead seizures. Whereas prediction performance clearly depends on these system parameters many researchers simply set the values of these parameters in an ad hoc manner. Our paper investigates the effect of these system parameters on online prediction performance, using both synthetic and real-life data sets. Therefore, meaningful comparison of methods/algorithms (for online seizure prediction) should consider proper specification of system parameters.

Keywords: Lead seizure; Online seizure prediction; Prediction horizon; Prediction period; Sensitivity; iEEG signal.

MeSH terms

Electroencephalography / methods*
Electroencephalography / standards
Humans
Models, Neurological*
Seizures / physiopathology*
Software / standards*

Abstract

MeSH terms

Grants and funding