Enhanced extra trees classifier for epileptic seizure prediction

Maurice Ntahobari, Levin Kuhlmann, Mario Boley, Zhinoos Razavi Hesabi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

For a machine learning based epileptic seizure prediction, it is important for the model to be implemented in small and implantable or wearable devices. These devices can be used to monitor the epileptic patients. However, the current state-of-the-art seizure prediction methods are complex and computationally intensive. We use SHapley Additive exPlanation (SHAP) to find relevant intracranial electroencephalogram (iEEG) features and improve the computational efficiency of a state-of-the-art seizure prediction method based on the extra trees classifier while maintaining prediction performance. Results for a small contest dataset and a much larger dataset with continuous recordings of up to 3 years per patient from 15 patients yield better than chance prediction performance (p < 0.004). Moreover, while performance of the SHAP-based model is comparable to that of the benchmark, the overall training and prediction time of the model has been reduced by a factor of 1.83. It can also be noted that of the feature called zero crossing value is the best EEG feature for seizure prediction. These results suggest state-of-the-art seizure prediction performance can be achieved using efficient methods based on optimal feature selection.

Original languageEnglish
Title of host publication2022 5th International Conference on Signal Processing and Information Security (ICSPIS)
EditorsAmjad Gawanmeh, Husameldin Mukhtar
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages175-179
Number of pages5
ISBN (Electronic)9781665492652
ISBN (Print)9781665492669
DOIs
Publication statusPublished - 2022
EventInternational Conference on Signal Processing and Information Security 2022 - Dubai, United Arab Emirates
Duration: 7 Dec 20228 Dec 2022
Conference number: 5th
https://ieeexplore.ieee.org/xpl/conhome/10002418/proceeding (Proceedings)
http://www.spiscs.net/ (Website)

Publication series

Name2022 5th International Conference on Signal Processing and Information Security, ICSPIS 2022
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2831-3828
ISSN (Electronic)2831-3844

Conference

ConferenceInternational Conference on Signal Processing and Information Security 2022
Abbreviated titleICSPIS 2022
Country/TerritoryUnited Arab Emirates
CityDubai
Period7/12/228/12/22
Internet address

Keywords

  • Epilepsy
  • Extra Tree Classifier
  • Machine learning
  • Seizure Prediction
  • SHAP

Cite this