November 10, 2026 · Journal of cardiac failure · DOI: 10.1016/j.cardfail.2026.08.013

Explainable Machine Learning for Predicting Incident Heart Failure from Routine Electronic Health Record Data.

Listen to this summary

This study asks whether an interpretable machine learning model built from routine electronic health record data can predict 5-year incident heart failure as accurately as established risk equations. The authors developed AIHF models using over 2,000 EHR predictors at Stanford and validated them in a national Veterans Affairs cohort, finding AUCs of roughly 0.74–0.85 with discrimination comparable to PREVENT-HF and PCP-HF. The results suggest that transparent, EHR-based models using longitudinal data could offer a scalable way to identify at-risk patients for HF prevention.

Michael Van Ness, Alexander T Sandhu, Tomas M Bosschieter, Natasha Din, Andrew Ambrosy, Minh Nguyen, Madeleine Udell

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play