Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif, Samer Ellaham, Cedric Schmitz|September 10, 2026arXiv

Key Takeaway

High accuracy in medical AI often reflects leaky data rather than model sophistication. Simpler, interpretable models can match complex ones while being faster and more auditable for fairness and safety issues.

Summary

This paper audits cardiovascular screening models trained on health survey data, revealing that their reported high accuracy (AUROC ~0.89) comes from data leakage rather than genuine learning. By systematically removing leaky features and testing multiple model types—from simple classifiers to advanced foundation models—the authors show all models collapse to similar performance.

evaluation safety applications

Key Terms

target-leakage auroc conformal-prediction fairness-audit calibration