EUVIMEDEUVIMED entdecken
Validierungsstudie

Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy

Mohammad-Reza Nazem-Zadeh iD, Richard Shek-Kwan Chang, Sarah Barnard iD, Heath R Pardoe iD, Ruben Kuzniecky, Debabrata Mishra, Hadi Kamkar iD, Duong Nhu, Deval Metha, Daniel Thom, Zhibin Chen, Zongyuan Ge und 5 weitere

Epilepsia · 2026-01 · 67 (1) · 120-137

DOI: 10.1111/epi.18668 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Epilepsia, online erschienen am 24.10.2025. Verfasst von Mohammad-Reza Nazem-Zadeh und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Victori…. Hauptthemen laut MEDLINE: Deep Learning, Anticonvulsants, Machine Learning, Epilepsy. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Health and Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Antiseizure medications (ASMs) are the first‐line treatment for epilepsy, yet they are ineffective in controlling seizures in about 40% of patients with unpredictable individual response to treatment. This study aimed to develop and validate artificial intelligence (AI) models using clinical and brain magnetic resonance imaging (MRI) data to predict responses to the first two ASMs in people with epilepsy.

Methods

People with recently diagnosed epilepsy treated with ASM monotherapy at the Alfred Hospital, Melbourne, Australia formed the development cohort. We developed AI models employing various combinations of clinical features, prescribed ASMs, and brain multimodal MRI images/features to predict the probability of seizure freedom at 12 months while taking the first or second ASM monotherapy. Five‐fold cross‐internal validation was performed. External validation was conducted on a validation cohort comprising participants of the Human Epilepsy Project.

Results

The development cohort included 154 individuals (36% female, 85% focal epilepsy), of whom 29% had received both the first and second ASM monotherapy. The validation cohort included 301 individuals (61% female, all focal epilepsy), of whom 33% had received both the first and second ASM monotherapy. A fusion deep learning (DL) model comprising an 18‐layer 3D videoResNet (for multi‐sequence MRI data), a transformer encoder (ASM regimens), and a dual linear neural network (for clinical characteristics) outperformed other models. It achieved an internal cross validation F1 score of 0.75 ± 0.05 (average ± 95% confidence interval), higher than other machine learning (ML) models and DL models with less complex architecture or integration of fewer imaging sequences. This DL model significantly outperformed the best ML model on validation cohort ( p < 0.001). Significance AI‐based models incorporating brain MRI, clinical, and medication data can efficiently predict seizure freedom in recently diagnosed epilepsy. They may enhance treatment selection in epilepsy and offer a foundation for clinical decision support systems. Further validation in larger cohorts is warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAnticonvulsantsMachine LearningEpilepsyHumansFemaleMaleMagnetic Resonance ImagingAdultMiddle AgedYoung AdultCohort StudiesAdolescentTreatment OutcomeBrain

Stichwörter der Autor:innen

antiseizure medicationartificial intelligencebrain MRIepilepsyepilepsy imagingmachine learning

Substanzen

Anticonvulsants

Autor:innen und Institutionen

  • Department of Neuroscience, School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Victoria, Australia.
  • Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
  • Department of Neurology, Alfred Health, Melbourne, Victoria, Australia.
  • Imaging and Epilepsy Group, Florey Institute of Neuroscience and Mental Health, Melbourne, Victoria, Australia.
  • Northwell Health, New York City, New York, USA.
  • School of Computer Science & Software Engineering, Monash University, Melbourne, Victoria, Australia.

ORCID-Profile: Mohammad-Reza Nazem-Zadeh, Sarah Barnard, Heath R Pardoe, Hadi Kamkar, Jacqueline French, Patrick Kwan

Förderung

  • National Health and Medical Research Council

Zitieren

APA

Nazem-Zadeh, M. R., Chang, R. S., Barnard, S., Pardoe, H. R., Kuzniecky, R., Mishra, D., Kamkar, H., Nhu, D., Metha, D., Thom, D., Chen, Z., Ge, Z., O'Brien, T. J., Sinclair, B., French, J., Law, M., & Kwan, P. (2026). Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy. Epilepsia, 67(1), 120-137. https://doi.org/10.1111/epi.18668

Vancouver

Nazem-Zadeh MR, Chang RS, Barnard S, Pardoe HR, Kuzniecky R, Mishra D, et al. Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy. Epilepsia. 2026;67(1):120-137. doi:10.1111/epi.18668

BibTeX
@article{NazemZadeh2026,
  author = {Nazem-Zadeh, Mohammad-Reza and Chang, Richard Shek-Kwan and Barnard, Sarah and Pardoe, Heath R and Kuzniecky, Ruben and Mishra, Debabrata and Kamkar, Hadi and Nhu, Duong and Metha, Deval and Thom, Daniel and Chen, Zhibin and Ge, Zongyuan and O'Brien, Terence J and Sinclair, Ben and French, Jacqueline and Law, Meng and Kwan, Patrick},
  title = {Development and validation of clinico‐imaging machine learning and deep learning models to predict responses to initial antiseizure medications in epilepsy},
  journal = {Epilepsia},
  year = {2026},
  volume = {67},
  number = {1},
  pages = {120--137},
  doi = {10.1111/epi.18668}
}
Kostenlos starten →