仅用指尖脉搏波信号，提前一小时预测重症患者心脏骤停
Continuous Cardiac Arrest Prediction in ICU using PPG Foundation Model
- 基于预训练脉搏波大模型，构建两阶段分析网络
- 提前24小时预测平均0.79 AUROC，一小时前达0.82
- 首个仅用单通道脉搏波实现连续心脏骤停预警的研究
无创患者监测以追踪和预测急性不良健康事件正成为研究热点。本文仅使用单通道指端光体积变化图（PPG）信号，实现院内心脏骤停（IHCA）的预测。提出的两阶段特征提取-聚合网络（FEAN）利用大规模预训练PPG基础模型（最大达10亿参数的PPG-GPT）与序列分类模型结合，设计两种变体（"1H"、"FH"），分别基于最近1小时与最多24小时的历史数据进行决策。本研究首次展示了仅使用单模态（连续PPG波形）深度表征在重症监护室患者中进行心脏骤停预测的结果。最佳模型在心脏骤停发生前24小时窗口内平均达到0.79 AUROC，峰值性能出现在一小时前，达0.82。同时通过结构调优与PaCMAP可视化对患者健康轨迹在潜在空间中的演变进行了全面分析。
原文摘要 · Abstract (English)
Non-invasive patient monitoring for tracking and predicting adverse acute health events is an emerging area of research. We pursue in-hospital cardiac arrest (IHCA) prediction using only single-channel finger photoplethysmography (PPG) signals. Our proposed two-stage model Feature Extractor-Aggregator Network (FEAN) leverages powerful representations from pre-trained PPG foundation models (PPG-GPT of size up to 1 Billion) stacked with sequential classification models. We propose two FEAN variants ("1H", "FH") which use the latest one-hour and (max) 24-hour history to make decisions respectively. Our study is the first to present IHCA prediction results in ICU patients using only unimodal (continuous PPG signal) waveform deep representations. With our best model, we obtain an average of 0.79 AUROC over 24~h prediction window before CA event onset with our model peaking performance at 0.82 one hour before CA. We also provide a comprehensive analysis of our model through architectural tuning and PaCMAP visualization of patient health trajectory in latent space.
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。