Computer-assisted analysis of routine EEG to identify hidden biomarkers of epilepsy: A systematic review.

Biomarker Computer-assisted Diagnosis Electroencephalogram Epilepsy Machine Learning

Journal

Computational and structural biotechnology journal
ISSN: 2001-0370
Titre abrégé: Comput Struct Biotechnol J
Pays: Netherlands
ID NLM: 101585369

Informations de publication

Date de publication:
Dec 2024
Historique:
received: 26 09 2023
revised: 05 12 2023
accepted: 05 12 2023
medline: 11 1 2024
pubmed: 11 1 2024
entrez: 11 1 2024
Statut: epublish

Résumé

Computational analysis of routine electroencephalogram (rEEG) could improve the accuracy of epilepsy diagnosis. We aim to systematically assess the diagnostic performances of computed biomarkers for epilepsy in individuals undergoing rEEG. We searched MEDLINE, EMBASE, EBM reviews, IEEE Explore and the grey literature for studies published between January 1961 and December 2022. We included studies reporting a computational method to diagnose epilepsy based on rEEG without relying on the identification of interictal epileptiform discharges or seizures. Diagnosis of epilepsy as per a treating physician was the reference standard. We assessed the risk of bias using an adapted QUADAS-2 tool. We screened 10 166 studies, and 37 were included. The sample size ranged from 8 to 192 (mean=54). The computed biomarkers were based on linear (43%), non-linear (27%), connectivity (38%), and convolutional neural networks (10%) models. The risk of bias was high or unclear in all studies, more commonly from spectrum effect and data leakage. Diagnostic accuracy ranged between 64% and 100%. We observed high methodological heterogeneity, preventing pooling of accuracy measures. The current literature provides insufficient evidence to reliably assess the diagnostic yield of computational analysis of rEEG. We provide guidelines regarding patient selection, reference standard, algorithms, and performance validation.

Sections du résumé

Background UNASSIGNED
Computational analysis of routine electroencephalogram (rEEG) could improve the accuracy of epilepsy diagnosis. We aim to systematically assess the diagnostic performances of computed biomarkers for epilepsy in individuals undergoing rEEG.
Methods UNASSIGNED
We searched MEDLINE, EMBASE, EBM reviews, IEEE Explore and the grey literature for studies published between January 1961 and December 2022. We included studies reporting a computational method to diagnose epilepsy based on rEEG without relying on the identification of interictal epileptiform discharges or seizures. Diagnosis of epilepsy as per a treating physician was the reference standard. We assessed the risk of bias using an adapted QUADAS-2 tool.
Results UNASSIGNED
We screened 10 166 studies, and 37 were included. The sample size ranged from 8 to 192 (mean=54). The computed biomarkers were based on linear (43%), non-linear (27%), connectivity (38%), and convolutional neural networks (10%) models. The risk of bias was high or unclear in all studies, more commonly from spectrum effect and data leakage. Diagnostic accuracy ranged between 64% and 100%. We observed high methodological heterogeneity, preventing pooling of accuracy measures.
Conclusion UNASSIGNED
The current literature provides insufficient evidence to reliably assess the diagnostic yield of computational analysis of rEEG.
Significance UNASSIGNED
We provide guidelines regarding patient selection, reference standard, algorithms, and performance validation.

Identifiants

pubmed: 38204455
doi: 10.1016/j.csbj.2023.12.006
pii: S2001-0370(23)00480-4
pmc: PMC10776381
doi:

Types de publication

Journal Article Review

Langues

eng

Pagination

66-86

Informations de copyright

© 2023 The Authors.

Déclaration de conflit d'intérêts

ÉL is supported by a scholarship from the Canadian Institute of Health Research (CIHR). BR wishes to acknowledge financial support from the Centre for Clinical Brain Sciences of the University of Edinburgh, the CIHR, the Fonds de recherche du Québec—Santé (FRQS) and the Ministère de la Santé et des Services sociaux du Québec, and the Power Corporation of Canada Chair in Neurosciences of the University of Montreal. MRK and DKN report unrestricted educational grants from UCB and Eisai, and research grants for investigator-initiated studies from UCB and Eisai. DKN and FL are supported by the Canada Research Chairs Program, the Canadian Institutes of Health Research, and Natural Sciences and Engineering Research Council of Canada. OG is supported by the Institute for Data Valorization (IVADO). EBA is supported by IVADO (51628), the CHUM research center (51616), and the Brain Canada Foundation (76097). Funding sources had no role in the design or conduct of the study.

Auteurs

Émile Lemoine (É)

Department of Neurosciences, University of Montreal, Canada.
Institute of biomedical engineering, Polytechnique Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Joel Neves Briard (J)

Department of Neurosciences, University of Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Bastien Rioux (B)

Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom.

Oumayma Gharbi (O)

Department of Neurosciences, University of Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Renata Podbielski (R)

University of Montreal Hospital Center's Research Center, Canada.

Bénédicte Nauche (B)

University of Montreal Hospital Center's Research Center, Canada.

Denahin Toffa (D)

Department of Neurosciences, University of Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Mark Keezer (M)

Department of Neurosciences, University of Montreal, Canada.
School of Public Health, University of Montreal, Canada.
Stichting Epilepsie Instellingen Nederland (SEIN), Heemstede, the Netherlands.

Frédéric Lesage (F)

Institute of biomedical engineering, Polytechnique Montreal, Canada.

Dang K Nguyen (DK)

Department of Neurosciences, University of Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Elie Bou Assi (E)

Department of Neurosciences, University of Montreal, Canada.
University of Montreal Hospital Center's Research Center, Canada.

Classifications MeSH