Video‐based diagnostics supported by artificial intelligence as an opportunity to address the epilepsy diagnostic gap: A narrative review

Despite advancements in epilepsy care, a substantial diagnostic gap persists, particularly in resource-limited settings. This narrative review explores the potential of video-based diagnostics augmented by artificial intelligence (AI) to address this gap by enabling earlier and more accessible seizure detection and classification. We reviewed literature on the diagnostic utility of video-only seizure recordings, advances in AI-driven video analysis, and existing implementation models. We synthesized clinical, technological, and health-economic perspectives to propose a framework for integrating video-based diagnostics into epilepsy care. Smartphone-recorded videos provide diagnostically relevant semiological data across age groups and seizure types. Manual expert video review establishes a high diagnostic baseline; a meta-analysis of 13 studies (n = 682) demonstrated a pooled sensitivity of 82.2% and specificity of 84.7% for differentiating epileptic events. Advancements in AI and computer vision are effectively automating this process; our review of eight pivotal validation studies indicates that deep learning algorithms now achieve sensitivities of 82%-100% for convulsive seizures in controlled settings. However, performance varies significantly in real-world environments, with false detection rates ranging from .05 to >12 per night depending on the setting and seizure type. Implementation challenges include data scarcity, generalizability, regulatory frameworks, and reimbursement gaps. Widespread adoption requires standardized protocols, validated algorithms, secure data infrastructure, and economic incentives. Overall, video-based diagnostics, particularly when enhanced by AI, represent an underutilized and scalable opportunity to close the epilepsy diagnostic gap. They offer potential to reduce diagnostic delays, improve seizure classification, and increase access to expert care across clinical settings, including homes, emergency departments, and low-resource regions. Strategic investment in research, infrastructure, and policy reform is needed to fully realize this vision.