ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
This work addresses a critical flaw in medical AI for clinicians and researchers by exposing that current MLLMs bypass actual visual interpretation in ECG diagnosis, though it is incremental as it focuses on evaluation rather than solving the reasoning issue.
The authors tackled the problem of evaluating whether Multimodal Large Language Models (MLLMs) perform genuine step-by-step reasoning in ECG interpretation, and found that these models have near-zero success rates (6% completion) in maintaining complete reasoning chains despite possessing medical knowledge.
While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they genuinely perform actual step-by-step reasoning or just rely on superficial visual cues. To investigate this, we introduce \textbf{ECG-Reasoning-Benchmark}, a novel multi-turn evaluation framework comprising over 6,400 samples to systematically assess step-by-step reasoning across 17 core ECG diagnoses. Our comprehensive evaluation of state-of-the-art models reveals a critical failure in executing multi-step logical deduction. Although models possess the medical knowledge to retrieve clinical criteria for a diagnosis, they exhibit near-zero success rates (6% Completion) in maintaining a complete reasoning chain, primarily failing to ground the corresponding ECG findings to the actual visual evidence in the ECG signal. These results demonstrate that current MLLMs bypass actual visual interpretation, exposing a critical flaw in existing training paradigms and underscoring the necessity for robust, reasoning-centric medical AI. The code and data are available at https://github.com/Jwoo5/ecg-reasoning-benchmark.