Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification
For ECG classification, this work addresses the lack of clinically aligned, interpretable reasoning in existing black-box models by introducing a structured reasoning framework that improves both accuracy and clinical validity.
CardioThink, a physician-inspired MLLM, explicitly models ECG diagnostic reasoning through intermediate stages (rhythm, conduction, morphology, impression) and uses SSPO to optimize structured reasoning and accuracy, achieving superior diagnostic accuracy and interpretable clinical reasoning on diverse benchmarks.
Electrocardiogram (ECG) diagnosis in clinical practice relies on structured reasoning over multiple hierarchical aspects, including cardiac rhythm, conduction properties, waveform morphology, and overall diagnostic impression. However, most existing approaches predict labels directly from ECG signals without explicit clinical reasoning, resulting in opaque decisions that lack clinical alignment. To bridge this gap, we propose CardioThink, a physician-inspired multimodal large language model (MLLM) framework that explicitly models the diagnostic reasoning process through human-interpretable intermediate stages (rhythm, conduction, morphology, and impression) to derive final classification results. Furthermore, we introduce Structured Set Policy Optimization (SSPO) to jointly optimize adherence to this structured reasoning format and the accuracy of variable-size diagnostic sets, without requiring manually annotated reasoning traces. Extensive experiments on diverse ECG benchmarks demonstrate the significant superiority of our approach in diagnostic accuracy, while simultaneously providing interpretable clinical reasoning. Notably, reasoning quality evaluations confirm that SSPO substantially enhances the clinical validity of the generated rationales. These findings reveal that moving beyond direct label prediction toward structured reasoning offers a more clinically aligned direction for future ECG modeling.