Machine learning in epilepsy

Clinical Snapshot

Key Findings

• P Value: Not applicable - narrative review

• Effect Size: Not applicable - narrative review

• Primary Outcome: ML methods show promise across three levels: unsupervised learning for cellular phenotyping, supervised learning for seizure detection/prediction, and multiscale mechanistic modeling

• Nnt Or Sensitivity: Supervised ML has substantially advanced automated seizure detection, though specific performance metrics not systematically reported

• Confidence Interval: Not applicable - narrative review

Clinical Application

Implementation requires significant computational resources and expertise; interpretability challenges limit immediate clinical adoption Relevant to Australian epilepsy centers and research institutions; aligns with TGA requirements for interpretable medical devices; applicable to PBS-funded EEG monitoring services Patients with epilepsy requiring seizure monitoring, prediction, or phenotyping; researchers developing epilepsy biomarkers

Abstract

Epilepsy is a complex neurological disorder characterized by pathological processes that unfold across multiple biological scales, from cellular excitability and synaptic integration to large-scale network dynamics observable in electroencephalographic (EEG) recordings. While traditional analytical approaches have provided valuable insights, they often fail to capture high-dimensional and nonlinear structure of contemporary electrophysiological and clinical datasets. Consequently, machine learning (ML) has emerged as a powerful analytical framework in epilepsy research, although its rapid adoption has revealed a growing gap between algorithmic performance and biological interpretability. This review examines ML methods operating across three analytically distinct yet interconnected levels: (i) unsupervised learning for cellular-level phenotyping using high-dimensional electrophysiological data; (ii) supervised learning for EEG-based seizure detection and prediction; and (iii) multiscale modeling frameworks integrating neuronal and network dynamics. Rather than providing an exhaustive catalog of algorithms, we focus on inferential assumptions underlying ML applications, the methodological pitfalls constraining generalization and clinical relevance, and how ML-derived representations can be interpreted within established neurophysiological theory. We highlight that unsupervised ML facilitates identification of latent excitability phenotypes and trajectories obscured in traditional univariate analyses, while supervised ML has substantially advanced automated seizure detection and prediction, despite persistent challenges related to data leakage, class imbalance, and ambiguous preictal labeling. We argue that the most promising direction lies in embedding ML within multiscale mechanistic models, where data-driven inference facilitates parameter estimation and hypothesis generation rather than black-box prediction. By prioritizing interpretability, rigorous validation, and cross-scale integration, ML-enhanced multiscale frameworks offer a path toward clinically actionable models of epilepsy.

References

1. 1.Pérez-Villavicencio, J., Martínez-Rojas, V. A., Rubio, C., Serrano-García, N., Galván, E. J., & Romo-Parra, H. (2026). Machine learning in epilepsy. Epilepsy Research, 107792. https://doi.org/10.1016/j.eplepsyres.2026.107792