European journal of neurology · 2026
Artificial Intelligence for Improving the Management of People With Epilepsy in Low-and-Middle Income Countries.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Ryvlin Philippe, Beniczky Sándor, Aurlien Harald, Bernini Adriano, Jones Gabriel Davis, Kariuki Symon M, Spahr Antoine, Tveit Jesper, Sen Arjune
Аннотация
BACKGROUND: About 80% of people with epilepsy live in low-and-middle-income countries (LMICs) where the treatment gap is high. Limited access to neurologists, diagnostic tools, and antiseizure medications, combined with persistent stigma, contribute to poor outcomes, including premature mortality. Artificial intelligence (AI) offers potential to address these gaps through scalable, low-cost solutions for diagnosis, investigation, management, and monitoring.
METHODS: This review examines three recent and complementary AI applications in epilepsy care for LMICs: a smartphone-based diagnostic tool for convulsive epilepsy developed using population-based data from five sub-Saharan African countries; an automated EEG interpretation system based on a deep learning model (SCORE-AI) validated across multicenter datasets; and a wearable-based deep learning model for detecting generalized convulsive seizures using low-cost smartwatches.
RESULTS: The smartphone diagnostic tool achieved area under the curve (AUC) 0.92-0.95 with sensitivity 85.0%-97.5% for identifying epilepsy with convulsive seizures using eight binary clinical features. SCORE-AI demonstrated expert-level performance (AUC 0.89-0.96, accuracy 85%-92%) for automated EEG classification across multiple validation datasets. The wearable seizure detection algorithm achieved 96% sensitivity with approximately one false alarm per 8 days. All three solutions were designed for deployment on widely accessible platforms.
CONCLUSIONS: AI-driven approaches demonstrate feasibility for addressing diagnostic and monitoring gaps in resource-limited settings. However, implementation faces substantial challenges including infrastructure constraints, limited digital literacy, ethical considerations, and sociocultural factors. Successful deployment requires validation with large locally relevant datasets, context-adapted solutions, task-sharing strategies, implementation research, appropriate regulatory frameworks/certification, and community engagement to reduce the global epilepsy care gap.
METHODS: This review examines three recent and complementary AI applications in epilepsy care for LMICs: a smartphone-based diagnostic tool for convulsive epilepsy developed using population-based data from five sub-Saharan African countries; an automated EEG interpretation system based on a deep learning model (SCORE-AI) validated across multicenter datasets; and a wearable-based deep learning model for detecting generalized convulsive seizures using low-cost smartwatches.
RESULTS: The smartphone diagnostic tool achieved area under the curve (AUC) 0.92-0.95 with sensitivity 85.0%-97.5% for identifying epilepsy with convulsive seizures using eight binary clinical features. SCORE-AI demonstrated expert-level performance (AUC 0.89-0.96, accuracy 85%-92%) for automated EEG classification across multiple validation datasets. The wearable seizure detection algorithm achieved 96% sensitivity with approximately one false alarm per 8 days. All three solutions were designed for deployment on widely accessible platforms.
CONCLUSIONS: AI-driven approaches demonstrate feasibility for addressing diagnostic and monitoring gaps in resource-limited settings. However, implementation faces substantial challenges including infrastructure constraints, limited digital literacy, ethical considerations, and sociocultural factors. Successful deployment requires validation with large locally relevant datasets, context-adapted solutions, task-sharing strategies, implementation research, appropriate regulatory frameworks/certification, and community engagement to reduce the global epilepsy care gap.