用于癫痫发作预测的时空注意力网络
Spatio-Temporal Attention Network for Epileptic Seizure Prediction
AI总结:
提出基于时空注意力网络(STAN)的深度学习框架,通过对抗判别器区分发作前与发作间期注意力模式实现患者特异性学习,在CHB-MIT和MSSM数据集上分别达到96.6%和94.2%的灵敏度,能提前15至45分钟预测癫痫发作。
摘要:
本研究提出一种深度学习框架,通过时空注意力网络(STAN)学习脑电信号的复杂时空相关结构,以准确预测癫痫患者的发作。与依赖特征工程或假设固定发作前持续时间的现有方法不同,该方法通过STAN同时建模时空相关性,并采用对抗判别器区分发作前与发作间期的注意力模式,从而实现患者特异性学习。在CHB-MIT和MSSM数据集上的评估表明,在CHB-MIT上灵敏度为96.6%,误报率为0.011/h;在MSSM上灵敏度为94.2%,误报率为0.063/h,显著优于现有最先进方法。该框架能在发作前至少15分钟可靠检测出发作前状态,患者特异性窗口可延长至45分钟,为临床应用提供了充足的干预时间。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。