Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification

TL;DR

This paper introduces CardioThink, a multimodal large language model that explicitly models clinical reasoning in ECG diagnosis through interpretable intermediate stages, improving accuracy and interpretability.

Contribution

It proposes a novel framework that incorporates structured reasoning stages and a new optimization method, SSPO, to enhance ECG classification accuracy and interpretability.

Findings

CardioThink outperforms existing methods on diverse ECG benchmarks.

SSPO improves the clinical validity of generated rationales.

The approach provides interpretable reasoning aligned with clinical practice.

Abstract

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.