Model

Holtercare-Bench

multimodal long-term dynamic ECG QA benchmark (Holtercare-23K)

Year
2026
Form factor
Holter
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
Venue listedCatalog paper date: 2026Added to atlas: Nov 6, 2026Source

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

Holtercare-Bench is a multimodal benchmark for long-term Holter ECG, paired with Holtercare-23K (22,980 question-answer pairs from 788 clinical Holter records with signal-video-text alignment). It evaluates temporal localization, clinical diagnosis and global summarization. The authors report a large zero-shot gap for leading multimodal LLMs on ultra-long pathological sequences and substantial gains after fine-tuning. Code: https://github.com/ZJU4HealthCare/Holtercare-Bench.

Signals
ECG, Video, Text
Form factor
Holter
License
No LICENSE in repo
Year
2026
Architecture

Benchmark + dataset only (QA over Holter signal-video-text); evaluates MLLMs; not a pretrained FM

At a glance
Type
Task model
Modalities
ECGVideoText
Form factor
Holter
Parameters
Not reported
Architecture
Benchmark + dataset only (QA over Holter signal-video-text); evaluates MLLMs; not a pretrained FM
Venue
ACM MM 2026
Year
2026
arXiv
Not reported
Weights
Not released
Licence
No LICENSE in repo
Caveats
Not reported
Datasets
Not reported
Added
Nov 6, 2026
Updated
Nov 6, 2026

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 fromOpenAlex· Abstract via OpenAlex (publisher-deposited); © the authors/publisher

How it works

How Holtercare-Bench works: Input signals → Model → Downstream tasksInput signals: ECG (Electrocardiogram); Video; Text (Language). Model: Holtercare-Bench (Language-aligned).Input signalsECG: ElectrocardiogramECGElectrocardiogramVideoVideoText: LanguageTextLanguageModelHoltercare-BenchLanguage-aligned
Architecture
Benchmark + dataset only (QA over Holter signal-video-text); evaluates MLLMs; not a pretrained FM
Inputs
ECG, Video, Text
Approach
ECG · Holter · benchmark · MLLM · ACM MM · no licence

Datasets used

No public datasets linked yet.

Papers· 1

Cite this model

Cite the publication recorded for this model. Check it against the publisher before submitting.

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 MM 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 MM 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 MM 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 MM 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 MM 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 MM 2026},
  doi           = {10.1145/3767308.3838648}
}

History

  1. Added to the ChatPPG research hub