CAMEL: An ECG Language Model for Forecasting Cardiac Events
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915880041971712 |
|---|---|
| author | Velingker, Neelay Solko-Breslin, Alaia Keoliya, Mayank Choi, Seewon Xin, Jiayi Marathe, Anika Oraii, Alireza Deo, Rajat Khatana, Sameed Alur, Rajeev Naik, Mayur Wong, Eric |
| author_facet | Velingker, Neelay Solko-Breslin, Alaia Keoliya, Mayank Choi, Seewon Xin, Jiayi Marathe, Anika Oraii, Alireza Deo, Rajat Khatana, Sameed Alur, Rajeev Naik, Mayur Wong, Eric |
| contents | Electrocardiograms (ECG) are electrical recordings of the heart that are critical for diagnosing cardiovascular conditions. ECG language models (ELMs) have recently emerged as a promising framework for ECG classification accompanied by report generation. However, current models cannot forecast future cardiac events despite the immense clinical value for planning earlier intervention. To address this gap, we propose CAMEL, the first ELM that is capable of inference over longer signal durations which enables its forecasting capability. Our key insight is a specialized ECG encoder which enables cross-understanding of ECG signals with text. We train CAMEL using established LLM training procedures, combining LoRA adaptation with a curriculum learning pipeline. Our curriculum includes ECG classification, metrics calculations, and multi-turn conversations to elicit reasoning. CAMEL demonstrates strong zero-shot performance across 6 tasks and 9 datasets, including ECGForecastBench, a new benchmark that we introduce for forecasting arrhythmias. CAMEL is on par with or surpasses ELMs and fully supervised baselines both in- and out-of-distribution, achieving SOTA results on ECGBench (+7.0% absolute average gain) as well as ECGForecastBench (+12.4% over fully supervised models and +21.1% over zero-shot ELMs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15677 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CAMEL: An ECG Language Model for Forecasting Cardiac Events Velingker, Neelay Solko-Breslin, Alaia Keoliya, Mayank Choi, Seewon Xin, Jiayi Marathe, Anika Oraii, Alireza Deo, Rajat Khatana, Sameed Alur, Rajeev Naik, Mayur Wong, Eric Machine Learning Quantitative Methods Electrocardiograms (ECG) are electrical recordings of the heart that are critical for diagnosing cardiovascular conditions. ECG language models (ELMs) have recently emerged as a promising framework for ECG classification accompanied by report generation. However, current models cannot forecast future cardiac events despite the immense clinical value for planning earlier intervention. To address this gap, we propose CAMEL, the first ELM that is capable of inference over longer signal durations which enables its forecasting capability. Our key insight is a specialized ECG encoder which enables cross-understanding of ECG signals with text. We train CAMEL using established LLM training procedures, combining LoRA adaptation with a curriculum learning pipeline. Our curriculum includes ECG classification, metrics calculations, and multi-turn conversations to elicit reasoning. CAMEL demonstrates strong zero-shot performance across 6 tasks and 9 datasets, including ECGForecastBench, a new benchmark that we introduce for forecasting arrhythmias. CAMEL is on par with or surpasses ELMs and fully supervised baselines both in- and out-of-distribution, achieving SOTA results on ECGBench (+7.0% absolute average gain) as well as ECGForecastBench (+12.4% over fully supervised models and +21.1% over zero-shot ELMs). |
| title | CAMEL: An ECG Language Model for Forecasting Cardiac Events |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2602.15677 |