CFD-Guided Detection of Concept Drift in Multimodal Physiologic Signals
Not on the map. Why?
Abstract (arXiv)
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
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 7 Aug 2026.
Builds on
12 of 33 references.
References · 12
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2020Learning under Concept Drift: A Reviewcited by 470
- 2019Automatic diagnosis of the 12-lead ECG using a deep neural networkcited by 164
- 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
- 2022From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectorscited by 82
- 2025Rethinking Multimodality: Optimizing Multimodal Deep Learning for Biomedical Signal Classificationcited by 7
- 2025PPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detectioncited by 7
- 2025Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate vs Late Fusioncited by 6
- 2023PPG-to-ECG Signal Translation for Continuous Atrial Fibrillation Detection via Attention-based Deep State-Space Modelingcited by 4
- 2026When Should a Model Change Its Mind? An Energy-Based Theory and Regularizer for Concept Drift in Electrocardiogram (ECG) Signalscited by 3
- 2026Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approachcited by 2
- 2026Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Modelcited by 1
Built on by
Not cited yet.