EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Long‐term prediction of epilepsy following traumatic brain injury among veterans using routine clinical data

Mustafa Ozmen iD, Shashank Vadlamani iD, James J Gugger iD, Megan Amuan iD, Ramon Diaz-Arrastia iD, Mary Jo Pugh iD, Eamonn Kennedy iD

Epilepsia · 2026-11 · 67 (11) · 5840-5850

DOI: 10.1002/epi.70430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Epilepsia, online erschienen am 04.08.2026. Verfasst von Mustafa Ozmen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Division of Epidemiology, University of Utah, Salt Lake City, Utah, USA. Hauptthemen laut MEDLINE: Brain Injuries, Traumatic, Veterans, Epilepsy, Post-Traumatic, Machine Learning. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Despite elevated risk for epilepsy following traumatic brain injury (TBI), there are limited tools to assess epilepsy risk following TBI using routine clinical data. The objective of this study was to develop and validate a machine learning approach to predict the onset of posttraumatic epilepsy (PTE) over varying time horizons following TBI, using only routine clinical data collected up to the month of TBI documentation.

Methods

This retrospective longitudinal cohort study included post‐9/11 US veterans with a TBI diagnosis between 2008 and 2017 in US Department of War and Veterans Health Administration records. Machine learning models predicted PTE onset at 2, 5, and 10 years after the date of first TBI documentation. Only preinjury information was used for prediction. Model performance was evaluated on held‐out test data (30%). Shapley additive explanations (SHAP) were used to quantify the contribution of predictive features.

Results

The cohort of 107 987 US veterans with TBI included 4930 (4.6%) incident epilepsy cases. Predicting epilepsy status, an optimized random forest model achieved area under curve [95% confidence interval] scores from receiver operating characteristic curves of .75 [.73–.77], .74 [.72–.75], and .73 [.72–.74] for 2‐, 5‐, and 10‐year forecast windows postinjury, respectively. High‐risk stratification identified 17.5% of all 5‐year epilepsy cases at a false positive rate of just 2.3% in the TBI population. SHAP analysis identified TBI severity and a cumulative preinjury comorbidity index as important predictors of PTE risk. Significance Machine learning algorithms applied to routinely collected administrative health data can effectively stratify long‐term risk for epilepsy following TBI over a wide range of time horizons. These models open the possibility for enrichment of PTE cases in future preventative clinical trials using widely available routine clinical data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain Injuries, TraumaticVeteransEpilepsy, Post-TraumaticMachine LearningEpilepsyHumansLongitudinal StudiesMaleRetrospective StudiesUnited StatesPredictive Learning ModelsFemaleAdultMiddle AgedPrediction Algorithms

Stichwörter der Autor:innen

epilepsyposttraumatic epilepsypredictiontraumatic brain injuryveteran

Autor:innen und Institutionen

  • Division of Epidemiology, University of Utah, Salt Lake City, Utah, USA.
  • Department of Electrical and Electronics Engineering, Antalya Bilim University, Antalya, Turkey.
  • VA Salt Lake City Health Care System, Informatics, Decision-Enhancement, and Analytic Sciences Center, Salt Lake City, Utah, USA.
  • Department of Neurology, University of Rochester, Rochester, New York, USA.
  • Department of Neurology, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.

ORCID-Profile: Mustafa Ozmen, Shashank Vadlamani, James J Gugger, Megan Amuan, Ramon Diaz-Arrastia, Mary Jo Pugh, Eamonn Kennedy

Förderung

  • NINDS NIH HHS

Zitieren

APA

Ozmen, M., Vadlamani, S., Gugger, J. J., Amuan, M., Diaz-Arrastia, R., Pugh, M. J., & Kennedy, E. (2026). Long‐term prediction of epilepsy following traumatic brain injury among veterans using routine clinical data. Epilepsia, 67(11), 5840-5850. https://doi.org/10.1002/epi.70430

Vancouver

Ozmen M, Vadlamani S, Gugger JJ, Amuan M, Diaz-Arrastia R, Pugh MJ, et al. Long‐term prediction of epilepsy following traumatic brain injury among veterans using routine clinical data. Epilepsia. 2026;67(11):5840-5850. doi:10.1002/epi.70430

BibTeX
@article{Ozmen2026,
  author = {Ozmen, Mustafa and Vadlamani, Shashank and Gugger, James J and Amuan, Megan and Diaz-Arrastia, Ramon and Pugh, Mary Jo and Kennedy, Eamonn},
  title = {Long‐term prediction of epilepsy following traumatic brain injury among veterans using routine clinical data},
  journal = {Epilepsia},
  year = {2026},
  volume = {67},
  number = {11},
  pages = {5840--5850},
  doi = {10.1002/epi.70430}
}
Kostenlos starten →