Article

A unified 12-lead ECG-language model for interpretation and clinical-endpoint prediction

2026-07-24

Abstract excerpt

Automated electrocardiogram (ECG) interpretation has advanced, yet most systems remain narrow classifiers that emit fixed labels rather than the narratives or endpoint-specific answers clinicians need. Generative approaches could instead produce rich narratives, but are constrained by the gap between continuous biosignals and discrete language tokens. Here we present DeepECG-Tok, which reframes ECG interpretation...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: d8d5acf8-069e-5492-a32c-1c1ba66cafc7
DOI: 10.64898/2026.07.22.26358591

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

A unified 12-lead ECG-language model for interpretation and clinical-endpoint predictionDOI 10.64898/2026.07.22.26358591Read

ECG-LLM: Foundation Model for ECG-Based Cardiac ReasoningSemantic proximity Read

Artificial Intelligence-Based Automated Interpretation of Images of Electrocardiograms: Development and Multinational Validation of ECG-GPTSemantic proximity Read

Foundation models for generalizable electrocardiogram interpretation: comparison of supervised and self-supervised electrocardiogram foundation modelsSemantic proximity Read

Beyond Text: The Impact of Clinical Context on GPT-4’s 12-lead ECG Interpretation AccuracySemantic proximity Read

A Comparative Study of Predictive model (ECG Buddy) and ChatGPT-4o for Myocardial Infarction Diagnosis via ECG image Analysis: Performance, Accuracy, and Clinical FeasibilitySemantic proximity Read

Multimodal Integration of Ambulatory ECG and Clinical Features for Sudden Cardiac Death and Pump Failure Death PredictionSemantic proximity Read

A Reproducible Clinical Decision-Support Suite on MIMIC-IVSemantic proximity Read

Ensemble Post-hoc Explainable AI for Multilead ECG: Identifying Disease-Relevant Features in Single-Lead InterpretationsSemantic proximity Read

Agentic Autodiscovery of Diastolic Dysfunction Phenotypes from Surface ElectrocardiogramSemantic proximity Read

<i>TARGET-AI</i> : a foundational approach for the targeted deployment of artificial intelligence electrocardiography in the electronic health recordSemantic proximity Read

Deep Learning of Electrocardiograms Enables Scalable Human Disease ProfilingSemantic proximity Read

Advances in Interpretation of Electrocardiogram by Artificial IntelligenceSemantic proximity Read