Estimating the likelihood of epilepsy from clinically noncontributory electroencephalograms using computational analysis: A retrospective, multisite case-control study.

Autor: Tait L; Cardiff University, Cardiff, UK.; University of Birmingham, Birmingham., Staniaszek LE; University Hospitals Bristol and Weston National Health Service Foundation Trust, Bristol, UK.; Neuronostics, Bristol, UK., Galizia E; St. George's Hospital National Health Service Foundation Trust, London, UK., Martin-Lopez D; St. George's Hospital National Health Service Foundation Trust, London, UK.; Kingston Hospital National Health Service Foundation Trust, Kingston, UK., Walker MC; University College London, London, UK.; University College London Hospitals, London, UK., Azeez AAA; University College London Hospitals, London, UK., Meiklejohn K; Neuronostics, Bristol, UK.; University Hospital Southampton National Health Service Foundation Trust, Southampton, UK., Allen D; University Hospital Southampton National Health Service Foundation Trust, Southampton, UK., Price C; Royal Devon and Exeter National Health Service Foundation Trust, Exeter, UK., Georgiou S; Royal Devon and Exeter National Health Service Foundation Trust, Exeter, UK., Bagary M; Birmingham and Solihull Mental Health National Health Service Foundation Trust, Birmingham, UK., Khalsa S; Birmingham and Solihull Mental Health National Health Service Foundation Trust, Birmingham, UK., Manfredonia F; Royal Wolverhampton National Health Service Trust, Wolverhampton, UK., Tittensor P; Royal Wolverhampton National Health Service Trust, Wolverhampton, UK.; University of Wolverhampton, Wolverhampton, UK., Lawthom C; Royal Gwent Hospital, Newport, UK.; Swansea University, Swansea, UK., Howes BB; Neuronostics, Bristol, UK., Shankar R; University of Plymouth, Plymouth, UK.; Cornwall Partnership National Health Service Foundation Trust, Bodmin, UK., Terry JR; University of Birmingham, Birmingham.; Neuronostics, Bristol, UK., Woldman W; University of Birmingham, Birmingham.; Neuronostics, Bristol, UK.
Jazyk: angličtina
Zdroj: Epilepsia [Epilepsia] 2024 Aug; Vol. 65 (8), pp. 2459-2469. Date of Electronic Publication: 2024 May 23.
DOI: 10.1111/epi.18024
Abstrakt: Objective: This study was undertaken to validate a set of candidate biomarkers of seizure susceptibility in a retrospective, multisite case-control study, and to determine the robustness of these biomarkers derived from routinely collected electroencephalography (EEG) within a large cohort (both epilepsy and common alternative conditions such as nonepileptic attack disorder).
Methods: The database consisted of 814 EEG recordings from 648 subjects, collected from eight National Health Service sites across the UK. Clinically noncontributory EEG recordings were identified by an experienced clinical scientist (N = 281; 152 alternative conditions, 129 epilepsy). Eight computational markers (spectral [n = 2], network-based [n = 4], and model-based [n = 2]) were calculated within each recording. Ensemble-based classifiers were developed using a two-tier cross-validation approach. We used standard regression methods to assess whether potential confounding variables (e.g., age, gender, treatment status, comorbidity) impacted model performance.
Results: We found levels of balanced accuracy of 68% across the cohort with clinically noncontributory normal EEGs (sensitivity =61%, specificity =75%, positive predictive value =55%, negative predictive value =79%, diagnostic odds ratio =4.64, area under receiver operated characteristics curve =.72). Group level analysis found no evidence suggesting any of the potential confounding variables significantly impacted the overall performance.
Significance: These results provide evidence that the set of biomarkers could provide additional value to clinical decision-making, providing the foundation for a decision support tool that could reduce diagnostic delay and misdiagnosis rates. Future work should therefore assess the change in diagnostic yield and time to diagnosis when utilizing these biomarkers in carefully designed prospective studies.
(© 2024 The Author(s). Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)
Databáze: MEDLINE
Externí odkaz: