Paperdoi:10.1145/3767308.3838648
Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)
ACM Multimedia 2026 (proceedings DOI 10.1145/3767308.3838648)
(opens in a new tab)Yihan Xie et al., "Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis", doi:10.1145/3767308.3838648, CC BY 4.0
TL;DR
Introduces Holtercare-23K (22,980 QA pairs from 788 clinical Holter records with signal–video–text alignment) and Holtercare-Bench covering 12 sub-tasks across Closed-QA, Open-QA, and Report Generation. Zero-shot leading MLLMs show a large gap on ultra-long pathological sequences; fine-tuning improves substantially (per OpenAlex abstract).
- Form factor: Holter (long-term ambulatory ECG)
Abstract
While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic electrocardiograms (ECG), models struggle with complex temporal reasoning and diagnostic report generation due to a lack of high-quality datasets and benchmarks. To address this, we introduce (i) Holtercare-23K, a large-scale multimodal dynamic ECG dataset comprising 22,980 QA pairs derived from 788 clinical Holter records and featuring a novel signal-video-text tri-modal alignment. Based on this dataset, we present (ii) Holtercare-Bench, a multimodal benchmark that evaluates models on temporal localization, clinical diagnosis, and global summarization. Zero-shot evaluations of leading MLLMs reveal a significant performance gap in processing ultra-long pathological sequences. However, fine-tuning representative models yields substantial improvements. This work illuminates the limitations of current MLLMs in electrophysiology and provides a foundational benchmark for long-term medical MLLMs. Our project is available at https://github.com/ZJU4HealthCare/Holtercare-Bench.
Verbatim from OpenAlex (opens in a new tab) · Abstract via OpenAlex (publisher-deposited); © the authors/publisher
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Signals
Keywords
How it works
Cite this paper
Xie, Y., Cui, H., Ye, R., Lin, J., Wang, H., Mao, J., Zhang, B., Guo, X., Xiao, J., & Zhang, L. (2026). Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026). ACM Multimedia 2026. https://doi.org/10.1145/3767308.3838648
Xie, Yihan, Hanwen Cui, Runze Ye, Juekai Lin, Haoyang Wang, Jinhao Mao, Bo Zhang, Xiaogang Guo, Jun Xiao, and Lei Zhang. 2026. "Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)." ACM Multimedia 2026. https://doi.org/10.1145/3767308.3838648.
Xie, Y., Cui, H., Ye, R., Lin, J., Wang, H., Mao, J., Zhang, B., Guo, X., Xiao, J. and Zhang, L. (2026) 'Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)', ACM Multimedia 2026. doi: 10.1145/3767308.3838648.
Xie, Yihan, et al. "Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)." ACM Multimedia 2026, 2026. https://doi.org/10.1145/3767308.3838648.
Y. Xie et al., "Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)," ACM Multimedia 2026, 2026, doi: 10.1145/3767308.3838648.
@article{xie2026holtercarebench,
title = {{Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis (Xie et al., ACM MM 2026)}},
author = {Xie, Yihan and Cui, Hanwen and Ye, Runze and Lin, Juekai and Wang, Haoyang and Mao, Jinhao and Zhang, Bo and Guo, Xiaogang and Xiao, Jun and Zhang, Lei},
year = {2026},
journal = {ACM Multimedia 2026},
doi = {10.1145/3767308.3838648}
}Added to the ChatPPG research hub
