用注意力机制精准预测癫痫发作，提前15分钟预警
Spatio-Temporal Attention Network for Epileptic Seizure Prediction
- 通过时空注意力网络捕捉脑电图的动态关联模式
- 在两个数据集上达到94%以上敏感度，误报率极低
- 支持个体化预警窗口，最长可提前45分钟
本研究提出一种深度学习框架——时空注意力网络（STAN），通过建模脑电图信号的复杂时空相关性，实现对癫痫发作前兆的精准预测。与现有方法不同，该方法无需人工特征工程，也不假设固定的发作前期时长，而是通过联合学习时空相关性并利用对抗判别器区分发作期与发作间期的注意力模式，实现患者个性化建模。在CHB-MIT和MSSM数据集上的评估显示，该方法在CHB-MIT上达到96.6%敏感度、0.011次/小时误报率，在MSSM上达94.2%敏感度、0.063次/小时误报率，显著优于现有技术。系统可在发作前至少15分钟可靠检测到发作前状态，部分患者预警窗口可达45分钟，为临床干预提供充足时间。
原文摘要 · Abstract (English)
In this study, we present a deep learning framework that learns complex spatio-temporal correlation structures of EEG signals through a Spatio-Temporal Attention Network (STAN) for accurate predictions of onset of seizures for Epilepsy patients. Unlike existing methods, which rely on feature engineering and/or assume fixed preictal durations, our approach simultaneously models spatio-temporal correlations through STAN and employs an adversarial discriminator to distinguish preictal from interictal attention patterns, enabling patient-specific learning. Evaluation on CHB-MIT and MSSM datasets demonstrates 96.6\% sensitivity with 0.011/h false detection rate on CHB-MIT, and 94.2% sensitivity with 0.063/h FDR on MSSM, significantly outperforming state-of-the-art methods. The framework reliably detects preictal states at least 15 minutes before an onset, with patient-specific windows extending to 45 minutes, providing sufficient intervention time for clinical applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。