发表机构
The Beacom College of Computer and Cyber Sciences, Dakota State University（达科他州立大学比科姆计算机与网络科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对癫痫发作预测中的泛化与误报挑战，提出结合五个深度学习与三个经典机器学习模型的校准混合集成方法，在CHB-MIT上实现74.2%灵敏度与1.24次/小时误报。
AI 中文摘要
癫痫发作预测旨在发作前提供可操作的预警，然而患者无关的泛化能力和误报控制仍然是主要挑战。我们提出了一种校准的混合集成方法用于基于EEG的癫痫发作预测，该方法通过逻辑回归堆叠元学习器结合了五个深度学习模型和三个经典机器学习模型。所提出的流程整合了信号预处理、手工特征提取、类别不平衡处理、概率校准以及临床动机的后处理。我们在CHB-MIT数据集上使用严格的留一患者交叉验证（LOPO）评估该框架，阈值和后处理参数仅在保留的元数据上选择。在过滤后的队列中，排除发作前率低于1%或高于15%的异常患者，该模型在每小时1.24次误报的情况下实现了74.2%的发作级灵敏度，平均预警时间为16.9分钟。一个受限于目标误报警预算的测试调优神谕模型在每小时0.951次误报时实现了60.9%的灵敏度，这突显了在报告灵敏度时同时报告实际误报率的重要性。我们的代码可在以下网址获取：this https URL
英文摘要
Epileptic seizure forecasting aims to provide actionable warnings before seizure onset, yet patient-independent generalization and false-alarm control remain major challenges. We propose a calibrated hybrid ensemble for EEG-based seizure forecasting that combines five deep learning models and three classical machine learning models through a logistic regression stacking meta-learner. The proposed pipeline integrates signal preprocessing, handcrafted feature extraction, class-imbalance handling, probability calibration, and clinically motivated post-processing. We evaluate the framework on CHB-MIT using strict Leave-One-Patient-Out (LOPO) cross-validation, with threshold and post-processing parameters selected only on held-out meta data. On the filtered cohort, excluding patients with anomalous preictal rates below 1\% or above 15\%, the model achieves 74.2\% seizure-level sensitivity at 1.24 false alarms per hour, with an average warning time of 16.9 minutes. A test-tuned oracle constrained to the target false-alarm budget achieves 60.9\% sensitivity at 0.951 false alarms per hour, highlighting the importance of reporting sensitivity together with realized false-alarm rates. Our code is available at: https://github.com/DanaMason/IEEE-CARS-Hybrid-Ensemble-Learning-for-EEG-Based-Epileptic-Seizure-Forecasting
CommentsAccepted at the 2026 IEEE Cyber Awareness Research Symposium (CARS 2026)
