发表机构
Morgan State University; Fisk University; University of Houston（摩根州立大学; 菲斯克大学; 休斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出PECS生理稳定性框架，将模型内部变化与信号可测量变化对比，在多生理信号数据集上验证其性能优于基线，可用于可穿戴心血管AI的概念漂移监测。
AI 中文摘要
心血管AI模型可对干净的心电图（ECG）信号进行分类，但真实可穿戴设备采集的信号会因运动、呼吸、姿势、传感器接触以及真实临床恶化情况而发生变化。本文研究模型应在何时保留自身预测、何时更改预测、何时标记不确定性。我们提出了一种名为PECS的生理稳定性框架，该框架将模型内部的变化与信号中的可测量变化进行比较。其中，心电图（ECG）被视为主心脏信号，光体积描记法（PPG）补充脉搏和血管信息，仅当ECG和PPG意见不一致时才使用呼吸信号。我们在PTB-XL的试点规模和全规模数据集、同步的BIDMC和MIMIC波形队列上测试了该框架。PTB-XL的试点规模与全规模分析选择了不同的域对，而BIDMC和MIMIC中最强的跨模态对也发生了变化，表明添加所有可用信号并非总是最佳选择。PECS的表现优于所评估的漂移检测基线实现，在扩展的BIDMC上达到漂移分类准确率（DCA）0.8786，在MIMIC上达到0.9560。MIMIC的结果还显示，在意见不一致的情况下呼吸信号可提供帮助，但应选择性使用而非自动覆盖。总体而言，结果支持PECS作为可穿戴心血管AI的候选监测框架，同时强调需要具备规模感知的域选择和可解释的信任路由。
英文摘要
Cardiovascular AI models can classify clean elec- trocardiogram (ECG) signals, but real wearable signals change because of motion, breathing, posture, sensor contact, and true clinical deterioration. This paper asks when a model should keep its prediction, change it, or flag uncertainty. We propose a physiologic stability framework, called PECS, that compares changes inside the model with measurable changes in the signal. ECG is treated as the main cardiac signal, photoplethysmography (PPG) adds pulse and vascular information, and respiration is used only when ECG and PPG disagree. We test the framework on PTB-XL at pilot and full scales and on synchronized BIDMC and MIMIC waveform cohorts. The PTB-XL pilot and full- scale analyses selected different domain pairs, and the strongest cross-modal pair also changed across BIDMC and MIMIC, showing that adding every available signal is not always the best choice. PECS outperformed the evaluated drift-detection baseline implementations, reaching drift classification accuracy (DCA) of 0.8786 on expanded BIDMC and 0.9560 on MIMIC. The MIMIC results also showed that respiration can help during disagreement cases, but it should be used selectively rather than as an automatic override. Overall, the results support PECS as a candidate monitoring framework for wearable cardiovascular AI while highlighting the need for scale-aware domain selection and interpretable trust routing
