SleepXAI 框架对比五种 XAI 方法提升睡眠分期可解释性
Towards Explainable Sleep Stage Classification using Single-Channel Electroencephalogram
搞医疗AI或睡眠监测的值得看:研究在 Sleep-EDF 和 DREAMT 两个数据集上实测了五种解释方法,发现 Integrated Gradients 的归因和 AASM 频段最吻合,直接告诉你该选哪个方法。
一项新研究将 SleepXAI 睡眠分期框架扩展到系统性对比五种 XAI 解释方法,聚焦单通道脑电(EEG)输入,相比完整多导睡眠图更易在临床落地。
归因保真度采用 Spearman 秩相关与 AASM 定义的 EEG 频段对照评估,实验覆盖 Sleep-EDF 和 DREAMT 两个基准数据集,后者按睡眠呼吸暂停的呼吸暂停低通气指数(AHI)将受试者分为四个严重度组。结果显示 Integrated Gradients(IG)在 Sleep-EDF 全部五个睡眠分期和 DREAMT 所有 AHI 组上均取得最高平均归因保真度。
对临床开发者而言,这项工作说明归因方法的选择是构建可解释自动睡眠分期系统的关键变量,而非仅追求分类准确率。
Towards Explainable Sleep Stage Classification using Single-Channel Electroencephalogram
Automated sleep staging has achieved strong bench- mark accuracy; however, clinical adoption remains limited due to a lack of interpretability. In this work, we fill the research gap by extending the SleepXAI sleep staging framework to systematically compare five different XAI methods. Further, attribution fidelity is evaluated using Spearman rank correlation with AASM-defined EEG frequency bands, serving as clinically grounded reference signals. In this paper, we focus on single- channel Electroencephalogram (EEG), which is more amenable to practical clinical deployment compared to full polysomnography setups. Experiments are conducted on the Sleep-EDF benchmark dataset and the DREAMT dataset. In DREAMT, we stratified subjects based on OSA into four Apnea-Hypopnea Index (AHI) severity groups. We observed that the SleepXAI model achieves strong classification performance on both datasets. Among the evaluated methods, Integrated Gradients (IG) consistently achieves the highest mean attribution fidelity across all five sleep stages on Sleep-EDF and across all AHI groups on DREAMT, outperforming all other evaluated methods under the Spearman rank correlation metric. These findings highlight the importance of attribution method selection as a key factor for ensuring reliable and clinically interpretable automated sleep staging systems.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:SleepXAI、Integrated Gradients、EEG、睡眠分期,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Gurinder Kaur Sandhu, Jude Koenig, Ankita Shukla, Shruti Kshirsagar),经 AITOP 多维评分管线结构化提炼。