用睡眠数据自监督学习，预测心血管病风险
Multimodal Cardiovascular Risk Profiling Using Self-Supervised Learning of Polysomnography
- 从脑电、心电、呼吸信号中自监督提取特征
- 结合弗雷明汉评分，预测准确率最高达0.965
- 适合心血管风险筛查与个性化健康管理
我们开发了一种自监督深度学习模型，从多模态信号（脑电图(EEG)、心电图(ECG)和呼吸信号）中提取有意义的模式。模型在4,398名参与者的数据上训练，通过对比有无心血管疾病(CVD)结局个体的嵌入向量生成投影得分。在1,093名参与者的独立队列中进行了外部验证。结果表明，各模态的投影得分呈现显著且具有临床意义的模式：ECG特征对既存及新发心脏疾病，尤其是CVD死亡率具有预测力；EEG特征可预测新发高血压和CVD死亡率；呼吸信号提供互补预测价值。将这些投影得分与弗雷明汉风险评分结合，预测性能持续提升，不同结局的受试者工作特征曲线下面积(AUC)范围为0.607至0.965。研究结果在外部测试队列中稳健复现。结论：该框架可直接从多导睡眠图(PSG)数据生成个体化心血管风险评分，具备临床整合潜力，有助于风险评估与个性化诊疗。
原文摘要 · Abstract (English)
Methods: We developed a self-supervised deep learning model that extracts meaningful patterns from multi-modal signals (Electroencephalography (EEG), Electrocardiography (ECG), and respiratory signals). The model was trained on data from 4,398 participants. Projection scores were derived by contrasting embeddings from individuals with and without CVD outcomes. External validation was conducted in an independent cohort with 1,093 participants. The source code is available on https://github.com/miraclehetech/sleep-ssl. Results: The projection scores revealed distinct and clinically meaningful patterns across modalities. ECG-derived features were predictive of both prevalent and incident cardiac conditions, particularly CVD mortality. EEG-derived features were predictive of incident hypertension and CVD mortality. Respiratory signals added complementary predictive value. Combining these projection scores with the Framingham Risk Score consistently improved predictive performance, achieving area under the curve values ranging from 0.607 to 0.965 across different outcomes. Findings were robustly replicated and validated in the external testing cohort. Conclusion: Our findings demonstrate that the proposed framework can generate individualized CVD risk scores directly from PSG data. The resulting projection scores have the potential to be integrated into clinical practice, enhancing risk assessment and supporting personalized care.
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。