Cardio fusion

Cardio fusion improves cardiovascular disease prediction in silico (AUC-ROC 80.57% (95% CI: 79.96–81.14), accuracy 73.95%).

“the fused model achieves an accuracy of 73.95% and an AUC-ROC of 80.57% (95% CI: 79.96–81.14)”

In silicoon the Kaggle cardiovascular cohort (cardio_train.csv)n = 68,612

Cardio Fusion: A Dual-Stream Regularized Fusion Architecture for Generalizable Cardiovascular Disease Prediction Under Dataset Heterogeneity

Research Square·11 Sep 2026Preprint