Key result
MEETI dataset provides ~785,000 multimodal ECG records integrating raw signals, images, parameters, and LLM interpretations.
Why the study?
Development of clinically deployable multimodal AI systems is limited by the lack of public datasets integrating raw ECG signals, diagnostic images, and interpretation text.
The MEETI dataset provides a comprehensive, multimodal ECG resource integrating signals, images, features, and text to support the development of explainable cardiovascular AI systems.
Answers are grounded in this paper and cite their sources.
May enable multimodal ECG AI development; leaves open clinical utility pending prospective validation.
Electrocardiograms (ECGs) are essential for diagnosing arrhythmias, myocardial ischemia, and conduction disorders. While machine learning has achieved expert-level performance in ECG interpretation, the development of clinically deployable multimodal artificial intelligence (AI) systems is limited by the lack of public datasets that integrate raw signals, diagnostic images, and interpretation text. Most existing ECG datasets are single-modality or include, at most, signal-text pairs, restricting real-world applicability. To address this gap, we present MEETI (MIMIC-IV-Ext ECG-Text-Image), the first large-scale dataset that synchronizes raw ECG waveforms, high-resolution plotted images, and detailed textual interpretations generated by large language models. MEETI also includes beat-level quantitative parameters extracted from each lead, enabling fine-grained analysis and improving model interpretability. Built on the MIMIC-IV-ECG database of about 800,000 recordings, MEETI aligns each record across four components using unique identifiers: (1) raw signals, (2) plotted images, (3) per-beat parameters, and (4) interpretation text. This structure enables multimodal transformer learning and supports explainable, integrated analysis. MEETI provides a robust foundation and benchmark for next-generation cardiovascular AI research.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied Cardiovascular diseases (n=160,597). The MEETI dataset provides a large-scale, multimodal collection of 784,680 ECG records from 160,597 patients, integrating raw signals, plotted images, extracted parameters, and LLM interpretations.
Synapse has enriched 10 related papers. Consider them for comparative context: