SEP 9, 2026 · PREPRINT
In Medical Claims Data, Enhancing Predictive Performance for Major Adverse Cardiovascular Events Using Cross Attention
arXiv
This is an early-stage methodological study demonstrating a machine-learning approach to MACE prediction using claims data, with no clinical validation, prospective testing, or comparison to clinical outcomes.
Reported
ROC-AUC (proposed model)0.7720