Causal Physiological Representation Learning for Robust ECG Analysis

This paper addresses the vulnerability of deep learning models for ECG diagnosis to adversarial attacks, particularly those mimicking biological morphology. It proposes a novel approach, Causal Physiological Representation Learning (CPR), to improve robustness without sacrificing efficiency. The core idea is to leverage a Structural Causal Model (SCM) to disentangle invariant pathological features from non-causal artifacts, leading to more robust and interpretable ECG analysis.

• •Proposes CPR, a novel method for robust ECG analysis.
• •CPR uses a Structural Causal Model (SCM) to disentangle causal and non-causal features.
• •CPR outperforms existing methods in robustness against adversarial attacks while maintaining efficiency.
• •CPR offers a superior trade-off between robustness, efficiency, and clinical interpretability.