Wang Chenxi, Yuan Xinyue, Jing Wei
Shanxi Medical University, Taiyuan, Shanxi, China.
Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan, China.
Front Neurol. 2025 Aug 18;16:1615120. doi: 10.3389/fneur.2025.1615120. eCollection 2025.
Epilepsy is a prevalent chronic neurological disorder primarily diagnosed using electroencephalography (EEG). Traditional EEG interpretation relies on manual analysis, which suffers from high misdiagnosis rates and inefficiency.
This review systematically evaluates the integration of artificial intelligence (AI), particularly deep learning (DL) and machine learning (ML), into EEG analysis for epilepsy management. We focus on two dominant AI-EEG application models: supportive AI (augmenting clinical decisions) and predictive AI (anticipating seizures or outcomes).
AI-based EEG analysis demonstrates significant potential in improving epilepsy detection, monitoring, and therapeutic evaluation. Key advancements include enhanced precision, efficiency, and capabilities for multimodal data fusion and personalized diagnosis. However, challenges persist, such as limited model interpretability, data quality constraints, and barriers to clinical translation. Crucially, AI outputs require clinician verification alongside multidimensional clinical data.
Future research must prioritize algorithm optimization, data quality improvement, and enhanced AI transparency. Interdisciplinary collaboration is essential to bridge the gap between technical innovation and clinical implementation. This review highlights both the transformative potential and current limitations of AI-EEG in epilepsy care, providing a roadmap for future developments.
癫痫是一种常见的慢性神经系统疾病，主要通过脑电图（EEG）进行诊断。传统的脑电图解读依赖于人工分析，存在误诊率高和效率低的问题。
本综述系统评估了人工智能（AI），特别是深度学习（DL）和机器学习（ML）在癫痫管理的脑电图分析中的整合。我们重点关注两种主要的人工智能 - 脑电图应用模型：支持性人工智能（增强临床决策）和预测性人工智能（预测癫痫发作或结果）。
基于人工智能的脑电图分析在改善癫痫检测、监测和治疗评估方面显示出巨大潜力。关键进展包括提高了精度、效率以及多模态数据融合和个性化诊断的能力。然而，挑战依然存在，如模型可解释性有限、数据质量限制以及临床转化障碍。至关重要的是，人工智能输出需要临床医生结合多维临床数据进行验证。
未来的研究必须优先考虑算法优化、数据质量改进和提高人工智能透明度。跨学科合作对于弥合技术创新与临床应用之间的差距至关重要。本综述强调了人工智能 - 脑电图在癫痫护理中的变革潜力和当前局限性，为未来发展提供了路线图。
