Prediction of Seizure Recurrence. A Note of Caution

William J Bosl; Alan Leviton; Tobias Loddenkemper

doi:10.3389/fneur.2021.675728

Prediction of Seizure Recurrence. A Note of Caution

Front Neurol. 2021 May 13:12:675728. doi: 10.3389/fneur.2021.675728. eCollection 2021.

Authors

William J Bosl^{1

2

3}, Alan Leviton^{1

2}, Tobias Loddenkemper^{1

2}

Affiliations

¹ Boston Children's Hospital, Boston, MA, United States.
² Harvard Medical School, Boston, MA, United States.
³ Health Informatics Program, University of San Francisco, San Francisco, CA, United States.

Abstract

Great strides have been made recently in documenting that machine-learning programs can predict seizure occurrence in people who have epilepsy. Along with this progress have come claims that appear to us to be a bit premature. We anticipate that many people will benefit from seizure prediction. We also doubt that all will benefit. Although machine learning is a useful tool for aiding discovery, we believe that the greatest progress will come from deeper understanding of seizures, epilepsy, and the EEG features that enable seizure prediction. In this essay, we lay out reasons for optimism and skepticism.

Keywords: chaos & non-linearity; dynamical systems; electroencephalography; machine learning; seizure prediction.