提出PECS框架，用多模态生理信号判断心脏AI模型何时该信任预测
CFD-Guided Detection of Concept Drift in Multimodal Physiologic Signals
- 通过对比模型内部变化与真实信号变化来检测概念漂移
- 在MIMIC数据集上达到0.956的漂移分类准确率
- 提醒应按不同场景选信号，别盲目加数据
心血管AI模型能准确识别干净的心电图（ECG）信号，但可穿戴设备的真实信号会因运动、呼吸、体位、传感器接触及真实临床恶化而改变。本文探讨模型应在何时维持预测、修改预测或标记不确定性。提出一种生理稳定性框架PECS，通过比较模型内部变化与信号中可测量的变化来实现判断。以心电图（ECG）为主导心脏信号，光电容积脉搏波（PPG）补充脉搏与血管信息，仅在ECG与PPG不一致时引入呼吸信号。在PTB-XL数据集进行小规模和全规模测试，并在同步的BIDMC与MIMIC波形队列上验证。结果显示，PTB-XL的试点与全规模分析选择了不同的域对，且在BIDMC与MIMIC中最强跨模态组合也发生变化，表明并非所有可用信号叠加都最优。PECS优于所评估的漂移检测基线，于扩展后的BIDMC上取得0.8786的漂移分类准确率（DCA），在MIMIC上达0.9560。此外，呼吸信号在不一致情况下有帮助，但应选择性使用而非自动覆盖。整体结果支持PECS作为可穿戴心血管AI监测的候选框架，同时强调需考虑规模的域选择与可解释的信任路由。
原文摘要 · Abstract (English)
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
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。