Dynamical Predictive Modelling of Cardiovascular Disease Progression Post-Myocardial Infarction via ECG-Trained Artificial Intelligence Model
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_ | 1866913123402776576 |
|---|---|
| author | Cavarra, Riccardo Lovatelli, Lupo Ogbomo-Harmitt, Shaheim Aziz, Shahid De Vecchi, Adelaide King, Andrew Aslanidi, Oleg |
| author_facet | Cavarra, Riccardo Lovatelli, Lupo Ogbomo-Harmitt, Shaheim Aziz, Shahid De Vecchi, Adelaide King, Andrew Aslanidi, Oleg |
| contents | Myocardial infarction (MI) is a leading cause of death, and its adverse outcomes are urgent to predict. Yet ECG-based prognostic models underperform because deep learning requires large, labelled datasets, which are scarce in medicine. Foundation models can learn from unlabelled ECGs via selfsupervision, but medically relevant training strategies remain underexplored. We propose a pretrained artificial intelligence model that combines patient-specific temporal information using contrastive learning with supervised multitask heads, then fine-tunes on post-MI outcome prediction. The proposed model outperformed a model trained from scratch (0.794 vs 0.608 AUC) showing that clinically structured ECG modelling improves classification in limited data regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13568 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dynamical Predictive Modelling of Cardiovascular Disease Progression Post-Myocardial Infarction via ECG-Trained Artificial Intelligence Model Cavarra, Riccardo Lovatelli, Lupo Ogbomo-Harmitt, Shaheim Aziz, Shahid De Vecchi, Adelaide King, Andrew Aslanidi, Oleg Machine Learning Artificial Intelligence 68T07 (primary), 62P10 (secondary) I.2.6; J.3 Myocardial infarction (MI) is a leading cause of death, and its adverse outcomes are urgent to predict. Yet ECG-based prognostic models underperform because deep learning requires large, labelled datasets, which are scarce in medicine. Foundation models can learn from unlabelled ECGs via selfsupervision, but medically relevant training strategies remain underexplored. We propose a pretrained artificial intelligence model that combines patient-specific temporal information using contrastive learning with supervised multitask heads, then fine-tunes on post-MI outcome prediction. The proposed model outperformed a model trained from scratch (0.794 vs 0.608 AUC) showing that clinically structured ECG modelling improves classification in limited data regimes. |
| title | Dynamical Predictive Modelling of Cardiovascular Disease Progression Post-Myocardial Infarction via ECG-Trained Artificial Intelligence Model |
| topic | Machine Learning Artificial Intelligence 68T07 (primary), 62P10 (secondary) I.2.6; J.3 |
| url | https://arxiv.org/abs/2605.13568 |