Quantifying the impact of a computer‐aided diagnostic score on the clinical diagnosis of functional seizures
Epilepsia · 2026
DOI: 10.1002/epi.70069 ↗Kurz gefasst
Fachartikel in der Zeitschrift Epilepsia, 2026. Verfasst von Wesley T Kerr und 38 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA. Hauptthemen laut MEDLINE: Seizures, Diagnosis, Computer-Assisted, Machine Learning, Epilepsy. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIH HHS, NINDS NIH HHS, NIDA NIH HHS.
Abstract (Originalsprache)
Objective
The diagnosis of functional/dissociative seizures (FDS) without ictal video‐electroencephalography is challenging. The Functional/Dissociative Seizures Likelihood Score (FSLS) is a machine learning‐based diagnostic score that aims to help clinicians identify FDS. We evaluated whether a human‐in‐the‐loop implementation of the FSLS improved the performance of clinicians identifying FDS as compared to epileptic seizures (ES).
Methods
We constructed 117 anonymized cases about patients with ictal video‐electroencephalography‐documented FDS, epilepsy, co‐occurring ES and FDS, or physiological seizurelike events. Text‐based clinical history was presented followed by the FSLS. Readers were asked the most likely diagnosis after each piece of information. We used mixture modeling combined with mixed effects logistic regression to perform data‐driven grouping of participants based on observed patterns of diagnostic performance.
Results
Overall, 163 readers saw 1142 cases (median = 4 cases/reader), and 146 (90%) had a performance higher than chance. More formal training in seizures was associated with better performance (epileptologist accuracy = 67%, mental health clinician accuracy = 52%). Data‐driven groups including 66% of readers benefitted from the FSLS (accuracy improvement = 12%–15%, p < .05), including those in the reference and near highest baseline performance group. Other groups had no net change in performance ( p > .75). Significance Clinicians with more formal seizure training identified possible FDS more accurately than others, but formal training did not guarantee high diagnostic performance. Two performance‐based groups, which included 66% readers, benefitted from the FSLS because they identified when to change their mind on the basis of the FSLS's suggestion. The implementation of machine learning in the diagnosis of FDS should focus on identifying clinical settings where it can effectively enhance clinicians' decision‐making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
- Department of Neurology, University of California, Los Angeles, Los Angeles, California, USA.
- Department of Psychiatry and Biobehavioral Sciences, University of California, Los Angeles, Los Angeles, California, USA.
- Department of Neurology, University of Michigan, Ann Arbor, Michigan, USA.
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
- Academic Neurology Unit, University of Sheffield, Royal Hallamshire Hospital, Sheffield, UK.
ORCID-Profile: Wesley T Kerr, Katherine N McFarlane, Corinne H Allas, Samuel W Terman, Markus Reuber, Sung Hyun Seo, Payge Barnard, Adriana Y Koek, Amir H Karimi, Siddhika S Sreenivasan, Jena S Grauer, Di Sun, Meagan Watson, Elissa H Patterson, James Castellano, Anto I Bagić, L Brian Hickman, Laurence Knowles, Alistair Wardrope, Piyush Ostwal, Bridget K MacDonald, Melissa Berry, Nicholas J Beimer, Laura A Kirkpatrick, Danielle R Carns, Alex J Israel, Jamie D Feusner, Zongqi Xia, Yanshan Wang, Laura A Strom, Page B Pennell, John M Stern, Lubomir Hadjiiski, William C Stacey
Förderung
- NIH HHS
- NINDS NIH HHS
- NIDA NIH HHS
- American Academy of Neurology
- W. M. Keck Foundation
- NIGMS NIH HHS
- Christina Louise George Trust
- NICHD NIH HHS
Zitieren
APA
Kerr, W. T., McFarlane, K. N., Allas, C. H., Terman, S. W., Reuber, M., Seo, S. H., Barnard, P., Koek, A. Y., Karimi, A. H., Sreenivasan, S. S., Grauer, J. S., Sun, D., Watson, M., Patterson, E. H., Castellano, J., Bagić, A. I., Hickman, L. B., Kutschman, K. H., Knowles, L., …, & Stacey, W. C. (2026). Quantifying the impact of a computer‐aided diagnostic score on the clinical diagnosis of functional seizures. Epilepsia. https://doi.org/10.1002/epi.70069
Vancouver
Kerr WT, McFarlane KN, Allas CH, Terman SW, Reuber M, Seo SH, et al. Quantifying the impact of a computer‐aided diagnostic score on the clinical diagnosis of functional seizures. Epilepsia. 2026. doi:10.1002/epi.70069
BibTeX
@article{Kerr2026,
author = {Kerr, Wesley T and McFarlane, Katherine N and Allas, Corinne H and Terman, Samuel W and Reuber, Markus and Seo, Sung Hyun and Barnard, Payge and Koek, Adriana Y and Karimi, Amir H and Sreenivasan, Siddhika S and Grauer, Jena S and Sun, Di and Watson, Meagan and Patterson, Elissa H and Castellano, James and Bagić, Anto I and Hickman, L Brian and Kutschman, Kenneth H and Knowles, Laurence and Wardrope, Alistair and Ostwal, Piyush and MacDonald, Bridget K and Berry, Melissa and Reddy, Lomalan and Robinson-Mayer, Najda and Beimer, Nicholas J and Reddy, Rachna and Yaghoubi, Sarah K and Kirkpatrick, Laura A and Carns, Danielle R and Israel, Alex J and Feusner, Jamie D and Xia, Zongqi and Wang, Yanshan and Strom, Laura A and Pennell, Page B and Stern, John M and Hadjiiski, Lubomir and Stacey, William C},
title = {Quantifying the impact of a computer‐aided diagnostic score on the clinical diagnosis of functional seizures},
journal = {Epilepsia},
year = {2026},
doi = {10.1002/epi.70069}
}
EUVIMED