Application of Machine Learning Approaches to Predict Seizure-Onset Zones in Patients with Drug-Resistant Epilepsy: Systematic Review

Ali Haider Bangash¹M. Michael Bercu²Richard W. Byrne³Spriha Pavuluri⁴Afshin Salehi^5*

• ¹Department of Neurosurgery, Montefiore Einstein Medical Center, New York, United States
• ²Department of Neurosurgery, Corewell Health Helen DeVos Children's Hospital, Grand Rapids, United States
• ³Department of Neurosurgery, Mayo Clinic in Florida, Jacksonville, United States
• ⁴Department of Neurology, University of Nebraska Medical Center, Omaha, United States
• ⁵Department of Neurosurgery, University of Nebraska Medical Center, Omaha, United States

Machine learning (ML) approaches have emerged as promising tools for improving seizure onset zone (SOZ) prediction in patients with drug-resistant epilepsy (DRE). This systematic review aimed to evaluate the application and performance of ML approaches for SOZ prediction in patients with DRE. A comprehensive search was conducted across PubMed/Medline, Cochrane Database of Systematic Reviews, and Epistemonikos databases for tudies employing ML algorithms for SOZ prediction in patients with DRE. The Quality Assessment of Diagnostic Accuracy Studies – version 2 (QUADAS-2) tool was adopted to assess the methodological quality and risk of bias of included studies. Data on patient demographics, data acquisition methods, ML algorithms, and performance metrics were extracted and systematically synthesized. Out of a total of 38 studies, fifteen studies met the inclusion criteria, encompassing 352 patients (Mean age: of 28 years, 34% female population). The studies employed various ML techniques, including traditional methods such as Support Vector Machines and advanced deep learning architectures. Performance metrics varied widely across studies, with some approaches achieving accuracy, sensitivity, and specificity, respectively, above 90%. Deep learning models generally outperformed traditional methods, particularly in handling complex, multimodal data. Notably, personalized models demonstrated superior performance in reducing localization error and spatial dispersion. However, heterogeneity in data acquisition methods, patient populations, and reporting standards complicated direct comparisons between studies. This review highlighted the potential of ML approaches, particularly deep learning and personalized models, to enhance SOZ prediction accuracy in patients with DRE. However, several challenges were identified, including the need for standardized data collection protocols, larger prospective studies, and improved model interpretability. The findings underscore the importance of considering network-level changes in epilepsy when developing ML models for SOZ prediction. While ML approaches show promise for improving surgical planning and outcomes in DRE, their clinical utility, particularly in complex epilepsy cases, requires further investigation. Addressing these challenges will be crucial in realizing the full potential of ML in enhancing epilepsy care.