用双分支注意力与神经记忆，提升长时程癫痫发作预测准确率
EEG-Titans: Long-Horizon Seizure Forecasting via Dual-Branch Attention and Neural Memory
- 双分支结构融合短时异常捕捉与长期趋势记忆
- 在CHB-MIT数据集上达99.46%段级敏感度
- 适合临床高噪声环境下低误报的癫痫预警
从脑电图（EEG）中准确预测癫痫发作仍具挑战，因发作前动态可能跨越长时间窗，而临床相关信号往往微弱且短暂。许多深度学习模型在处理超长序列时，难以兼顾局部时空模式与长距离上下文信息。本文提出EEG-Titans，一种融合现代神经记忆机制的双分支架构。该模型结合滑动窗口注意力以捕捉短期异常，同时通过循环记忆路径持续总结随时间演化的缓慢趋势。在CHB-MIT头皮EEG数据集上，采用时间顺序留出验证协议，EEG-Titans在18名受试者上平均段级敏感度达到99.46%。进一步分析在含伪迹记录中的安全优先工作点发现，对高噪声受试者采用扩展感受野的分层上下文策略，可显著降低误报率（极端个案降至0.00 FPR/h），且不牺牲敏感度。结果表明，增强记忆的长上下文建模可在临床约束条件下实现稳健的癫痫发作预测。
原文摘要 · Abstract (English)
Accurate epileptic seizure prediction from electroencephalography (EEG) remains challenging because pre-ictal dynamics may span long time horizons while clinically relevant signatures can be subtle and transient. Many deep learning models face a persistent trade-off between capturing local spatiotemporal patterns and maintaining informative long-range context when operating on ultralong sequences. We propose EEG-Titans, a dualbranch architecture that incorporates a modern neural memory mechanism for long-context modeling. The model combines sliding-window attention to capture short-term anomalies with a recurrent memory pathway that summarizes slower, progressive trends over time. On the CHB-MIT scalp EEG dataset, evaluated under a chronological holdout protocol, EEG-Titans achieves 99.46% average segment-level sensitivity across 18 subjects. We further analyze safety-first operating points on artifact-prone recordings and show that a hierarchical context strategy extending the receptive field for high-noise subjects can markedly reduce false alarms (down to 0.00 FPR/h in an extreme outlier) without sacrificing sensitivity. These results indicate that memory-augmented long-context modeling can provide robust seizure forecasting under clinically constrained evaluation
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。