Vision-Based Artificial Intelligence Technologies for Epilepsy Monitoring: Scoping Review and Taxonomy Development Study

Clinical Snapshot

Key Findings

• P Value: Not reported — Delphi consensus method used for taxonomy validation; no inferential statistics reported

• Effect Size: Not applicable — no quantitative pooling performed; descriptive: 40 primary studies included, yielding 16 empirically derived taxonomy dimensions supplemented by 4 expert-added dimensions

• Primary Outcome: Development and expert validation of a taxonomy comprising 23 dimensions and 102 characteristics for classifying vision-based AI technologies in epilepsy monitoring

• Nnt Or Sensitivity: Not applicable — no clinical efficacy or diagnostic accuracy synthesis performed; individual study performance metrics were inconsistently reported across the 40 included studies, precluding pooled sensitivity/specificity estimates

• Confidence Interval: Not applicable — scoping review with no meta-analytic synthesis

Clinical Application

The taxonomy is immediately applicable as a procurement and benchmarking framework for health services evaluating commercial vision-based seizure monitoring systems. Direct clinical implementation of any specific AI monitoring technology cannot be recommended based on this review alone, given the predominance of proof-of-concept studies and inconsistent performance reporting. Clinicians and health technology assessment bodies can use the 23-dimension framework to systematically evaluate vendor claims and identify reporting gaps in product documentation. In Australia, vision-based AI seizure monitoring systems would require TGA registration as a Class IIa or higher medical device under the Therapeutic Goods (Medical Devices) Regulations 2002, particularly if intended for diagnostic or monitoring purposes. No such systems are currently listed on the Australian Register of Therapeutic Goods (ARTG) as standalone AI video monitoring devices for epilepsy, consistent with the authors' finding of a gap between technical feasibility and deployment-ready systems. The RACGP and Epilepsy Action Australia guidelines emphasise carer-assisted seizure monitoring and diary-based documentation; vision-based AI monitoring could complement but not replace these approaches. PBS reimbursement pathways for AI-assisted monitoring devices remain undeveloped. Australian epilepsy centres participating in video-EEG telemetry (available at major tertiary centres including Austin Health, Royal Prince Alfred, and Princess Margaret Hospital) represent the most immediate clinical context for applying this taxonomy in procurement decisions. Privacy considerations under the Australian Privacy Act 1988 and state health records legislation are directly relevant to the data privacy dimensions identified in the taxonomy. Adults and children with epilepsy in clinical (inpatient/outpatient) and home monitoring settings where video-based seizure surveillance is being considered or implemented

Abstract

BACKGROUND: Artificial intelligence (AI) technologies for vision-based epilepsy monitoring are advancing rapidly in health care. Despite growing research using various video data sources and analytical approaches, no comprehensive framework exists to classify these technologies. OBJECTIVE: This scoping review aimed to develop and validate a taxonomy for AI technologies in vision-based epilepsy monitoring and to characterize visual AI approaches in epilepsy care. METHODS: Using an extended taxonomy development framework, we developed the taxonomy in 5 iterative cycles, drawing on theory and practice. We conducted a scoping review, market analysis, and applicability evaluation with market-ready solutions. We searched Scopus, Web of Science, and PubMed, including MeSH (Medical Subject Headings) terms; the final search was completed on January 16, 2026. We included primary studies from 2013 onward on AI-based or machine learning-based monitoring or prediction of epileptic seizures in humans using visual data. We excluded reviews, non-English publications, nonepilepsy studies, studies focused only on electroencephalography or wearables, animal studies, and pre-2013 publications. Evidence was charted through narrative and tabular synthesis and descriptive frequency analysis. In line with scoping review guidance, we did not conduct a meta-analysis or critical appraisal. To assess validity and practical relevance, 9 domain experts evaluated the taxonomy using a Delphi technique. RESULTS: We included 40 original studies. Study analysis yielded 16 dimensions, including data acquisition source, tracking target, image processing, classifier type, performance metrics, environment, seizure classification, data privacy, and user interface. Expert feedback added 4 further dimensions, including communication mode and information purpose. The final taxonomy comprises 23 dimensions with 102 characteristics. The review identified structural evidence gaps across settings, evaluation maturity, and reporting practices. Detection and classification in stationary settings predominated, whereas predictive approaches and real-time feedback were limited. Deep learning detection methods were common, but performance reporting was inconsistent, and patient-facing functionalities were limited. Privacy safeguards and standardized metrics were often incompletely reported, reducing comparability and maturity assessment. The taxonomy translates these patterns into guidance for benchmarking, procurement evaluation, user interface, and explainable AI design. We synthesized 5 main findings and 10 implications for research and practice. Key challenges concern standardization, seizure prediction, and real-time applicability. CONCLUSIONS: Vision-based AI technologies for epilepsy monitoring are still dominated by proof-of-concept and pilot evaluations, indicating a gap between technical feasibility and deployment-ready systems. This scoping review presents an implementation-oriented taxonomy integrating application context, system architecture, visual analysis, AI models, performance reporting, and feedback design into a single classification framework. Unlike prior work that mainly maps methods or data sources, the taxonomy provides a shared structure for consistent system-level characterization and comparison across studies and emerging solutions. It may support benchmarking, implementation-focused evaluation, procurement, and translation into clinical and home settings.

References

1. 1.Irnich, M., Hammer, J., Flok, A., & Teuteberg, F. (2026). Vision-based artificial intelligence technologies for epilepsy monitoring: Scoping review and taxonomy development study. Journal of Medical Internet Research. https://doi.org/10.2196/83895