ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oh, Jungwoo, Chung, Hyunseung, Lee, Junhee, Kim, Min-Gyu, Yoon, Hangyul, Lee, Ki Seong, Lee, Youngchae, Yeo, Muhan, Choi, Edward
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911517767630848
author Oh, Jungwoo
Chung, Hyunseung
Lee, Junhee
Kim, Min-Gyu
Yoon, Hangyul
Lee, Ki Seong
Lee, Youngchae
Yeo, Muhan
Choi, Edward
author_facet Oh, Jungwoo
Chung, Hyunseung
Lee, Junhee
Kim, Min-Gyu
Yoon, Hangyul
Lee, Ki Seong
Lee, Youngchae
Yeo, Muhan
Choi, Edward
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14326
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
Oh, Jungwoo
Chung, Hyunseung
Lee, Junhee
Kim, Min-Gyu
Yoon, Hangyul
Lee, Ki Seong
Lee, Youngchae
Yeo, Muhan
Choi, Edward
Machine Learning
Artificial Intelligence
Computation and Language
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.
title ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2603.14326