Saved in:
Bibliographic Details
Main Authors: Lan, Xiang, Wu, Feng, He, Kai, Zhao, Qinghao, Hong, Shenda, Feng, Mengling
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912656245391360
author Lan, Xiang
Wu, Feng
He, Kai
Zhao, Qinghao
Hong, Shenda
Feng, Mengling
author_facet Lan, Xiang
Wu, Feng
He, Kai
Zhao, Qinghao
Hong, Shenda
Feng, Mengling
contents While recent multimodal large language models (MLLMs) have advanced automated ECG interpretation, they still face two key limitations: (1) insufficient multimodal synergy between time series signals and visual ECG representations, and (2) limited explainability in linking diagnoses to granular waveform evidence. We introduce GEM, the first MLLM unifying ECG time series, 12-lead ECG images and text for grounded and clinician-aligned ECG interpretation. GEM enables feature-grounded analysis, evidence-driven reasoning, and a clinician-like diagnostic process through three core innovations: a dual-encoder framework extracting complementary time series and image features, cross-modal alignment for effective multimodal understanding, and knowledge-guided instruction generation for generating high-granularity grounding data (ECG-Grounding) linking diagnoses to measurable parameters ($e.g.$, QRS/PR Intervals). Additionally, we propose the Grounded ECG Understanding task, a clinically motivated benchmark designed to comprehensively assess the MLLM's capability in grounded ECG understanding. Experimental results on both existing and our proposed benchmarks show GEM significantly improves predictive performance (CSN $7.4\% \uparrow$), explainability ($22.7\% \uparrow$), and grounding ($24.8\% \uparrow$), making it more suitable for real-world clinical applications. GitHub repository: https://github.com/lanxiang1017/GEM.git
format Preprint
id arxiv_https___arxiv_org_abs_2503_06073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
Lan, Xiang
Wu, Feng
He, Kai
Zhao, Qinghao
Hong, Shenda
Feng, Mengling
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
While recent multimodal large language models (MLLMs) have advanced automated ECG interpretation, they still face two key limitations: (1) insufficient multimodal synergy between time series signals and visual ECG representations, and (2) limited explainability in linking diagnoses to granular waveform evidence. We introduce GEM, the first MLLM unifying ECG time series, 12-lead ECG images and text for grounded and clinician-aligned ECG interpretation. GEM enables feature-grounded analysis, evidence-driven reasoning, and a clinician-like diagnostic process through three core innovations: a dual-encoder framework extracting complementary time series and image features, cross-modal alignment for effective multimodal understanding, and knowledge-guided instruction generation for generating high-granularity grounding data (ECG-Grounding) linking diagnoses to measurable parameters ($e.g.$, QRS/PR Intervals). Additionally, we propose the Grounded ECG Understanding task, a clinically motivated benchmark designed to comprehensively assess the MLLM's capability in grounded ECG understanding. Experimental results on both existing and our proposed benchmarks show GEM significantly improves predictive performance (CSN $7.4\% \uparrow$), explainability ($22.7\% \uparrow$), and grounding ($24.8\% \uparrow$), making it more suitable for real-world clinical applications. GitHub repository: https://github.com/lanxiang1017/GEM.git
title GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06073