SleepFM：跨脑活动、心电图和呼吸信号的多模态睡眠表征学习
SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
AI总结：
本文提出首个多模态睡眠基础模型SleepFM，基于超10万小时多导睡眠数据，采用留一法对比学习，在睡眠分期和呼吸障碍检测上优于CNN，并实现跨模态检索。
摘要：
睡眠是一个复杂的生理过程，通过记录脑电、心电和呼吸活动的多种模态进行评估。我们整理了来自超过14,000名参与者的大型多导睡眠图数据集，包含超过100,000小时的多模态睡眠记录。利用这一广泛数据集，我们开发了SleepFM，这是首个用于睡眠分析的多模态基础模型。我们表明，一种新颖的留一法对比学习方法相比标准成对对比学习得到的表征，能显著提升下游任务性能。在SleepFM学习到的嵌入上训练的逻辑回归模型，在睡眠阶段分类（宏AUROC 0.88对0.72，宏AUPRC 0.72对0.48）和睡眠呼吸障碍检测（AUROC 0.85对0.69，AUPRC 0.77对0.61）方面优于端到端训练的卷积神经网络（CNN）。值得注意的是，学习到的嵌入在从90,000个候选中检索其他模态对应记录片段时，实现了48%的top-1平均准确率。这项工作展示了整体多模态睡眠建模在充分捕捉睡眠记录丰富性方面的价值。SleepFM是开源的，可在https://github.com/rthapa84/sleepfm-codebase获取。
英文摘要：
Sleep is a complex physiological process evaluated through various modalities recording electrical brain, cardiac, and respiratory activities. We curate a large polysomnography dataset from over 14,000 participants comprising over 100,000 hours of multi-modal sleep recordings. Leveraging this extensive dataset, we developed SleepFM, the first multi-modal foundation model for sleep analysis. We show that a novel leave-one-out approach for contrastive learning significantly improves downstream task performance compared to representations from standard pairwise contrastive learning. A logistic regression model trained on SleepFM's learned embeddings outperforms an end-to-end trained convolutional neural network (CNN) on sleep stage classification (macro AUROC 0.88 vs 0.72 and macro AUPRC 0.72 vs 0.48) and sleep disordered breathing detection (AUROC 0.85 vs 0.69 and AUPRC 0.77 vs 0.61). Notably, the learned embeddings achieve 48% top-1 average accuracy in retrieving the corresponding recording clips of other modalities from 90,000 candidates. This work demonstrates the value of holistic multi-modal sleep modeling to fully capture the richness of sleep recordings. SleepFM is open source and available at https://github.com/rthapa84/sleepfm-codebase.
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。
