EUVIMEDEUVIMED entdecken
Crossref

ClinFormer: a multi-modal clinical transformer for explainable major adverse cardiovascular event prediction from electronic health records

Dr. Ramesh Murlidhar Bhatawdekar

Journal of Artificial Intelligence Machine Learning and Neural Network · 20.02.2026 · 42

DOI: 10.55529/jaimlnn.61.42.52 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence Machine Learning and Neural Network, online erschienen am 20.02.2026. Verfasst von Dr. Ramesh Murlidhar Bhatawdekar. Die Arbeit nennt 25 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Major adverse cardiovascular events (MACE), including acute myocardial infarction, stroke, and cardiovascular death, account for over 8 million deaths globally each year. Conventional prediction models such as Framingham Risk Score, SCORE2, and Pooled Cohort Equations rely on limited traditional risk factors and linear assumptions, restricting their ability to capture complex temporal and non-linear relationships within longitudinal electronic health records (EHRs).

Methods

We propose ClinFormer, a multi-modal clinical Transformer designed to integrate five EHR modalities: laboratory results, diagnosis codes, medication records, clinical notes, and vital signs. The model employs cross-modal attention mechanisms with 12 attention heads and a model dimension of 512. ClinFormer was pre-trained using contrastive patient similarity learning on 127,438 patients from MIMIC-IV and externally validated on 38,924 patients from the eICU database. Model interpretability was provided through SHAP analysis and calibrated probability outputs.

Results

On external validation, ClinFormer achieved an AUROC of 0.943 (95% CI: 0.937–0.949), significantly outperforming the strongest baseline model, ClinicalBERT (AUROC: 0.912; p < 0.001). Calibration performance was strong with an expected calibration error (ECE) of 0.031. SHAP analysis identified BNP, troponin I, and eGFR as the most influential predictors.

Conclusions

ClinFormer provides accurate, interpretable, and well-calibrated MACE prediction directly from routinely collected EHR data, supporting its potential deployment in both resource-rich and resource-constrained clinical environments.

Zitieren

APA

Bhatawdekar, D. R. M. (2026). ClinFormer: a multi-modal clinical transformer for explainable major adverse cardiovascular event prediction from electronic health records. Journal of Artificial Intelligence Machine Learning and Neural Network, 42. https://doi.org/10.55529/jaimlnn.61.42.52

Vancouver

Bhatawdekar DRM. ClinFormer: a multi-modal clinical transformer for explainable major adverse cardiovascular event prediction from electronic health records. Journal of Artificial Intelligence Machine Learning and Neural Network. 2026:42. doi:10.55529/jaimlnn.61.42.52

BibTeX
@article{Bhatawdekar2026,
  author = {Bhatawdekar, Dr. Ramesh Murlidhar},
  title = {ClinFormer: a multi-modal clinical transformer for explainable major adverse cardiovascular event prediction from electronic health records},
  journal = {Journal of Artificial Intelligence Machine Learning and Neural Network},
  year = {2026},
  pages = {42},
  doi = {10.55529/jaimlnn.61.42.52}
}
Kostenlos starten →