Clinical risk prediction models for worsening heart failure events and all-cause mortality in adults with mild-to-moderate chronic kidney disease
Electronic health record-based machine-learning models accurately predicted WHF and mortality in mild-to-moderate CKD with strong calibration across key subgroups. These models are positioned for EHR deployment to support risk-stratified cardiovascular-kidney-metabolic care-prioritizing guideline-directed therapies and care pathways for those at highest risk.
Authors
- Jane Y. Liu
- Emily S. Lee
- Harshith R. Avula (ORCID: https://orcid.org/0000-0002-1645-1936)
- Rishi Parikh (ORCID: https://orcid.org/0000-0002-1115-844X)
- Jana Svetlichnaya
- K L Lee
- Alexander T. Sandhu (ORCID: https://orcid.org/0000-0003-3208-1143)
- P Goyal
- Jesse K. Fitzpatrick (ORCID: https://orcid.org/0000-0002-1545-6399)
- David W. Ouyang
- A.S. Go
- Leonid Pravoverov
- Ankeet S. Bhatt
- Thida C Tan
- Michael P Girouard
- Kaiwen Sun
- Andrew P Ambrosy
- Sijie Zheng
- Sirtaz Adatya
- Soham Patel
- Rami Halaseh
Institutions
- Kaiser Permanente (US)
- Palo Alto University (US)
- University of California, San Francisco (US)
- Cornell University (US)
- Kaiser Permanente Oakland Medical Center (US)
- Kaiser Permanente Walnut Creek Medical Center (US)
- Kaiser Permanente San Francisco Medical Center (US)
- Kaiser Permanente Santa Clara Medical Center (US)
- Weill Cornell Medicine (US)
Publication Details
- Journal
- ESC Heart Failure
- Published
- 2026-01-06
- DOI
- https://doi.org/10.1093/eschf/xvaf037
- Primary Topic
- Heart Failure Treatment and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00