Signal or noise? Evaluating commonly used attribution methods for explaining deep neural networks in electrocardiogram classification

Attribution methods demonstrated limited reliability, instability across model variants and incomplete dependence on learned parameters, constraining their utility in high-stakes settings such as healthcare. These findings suggest that attribution techniques should be used cautiously and supported by task-specific sanity checks. Approaches grounded in rigorous validation, inherently interpretable modelling or counterfactual explanations may better support clinically meaningful insight.