Characteristics and Outcomes of Over One Million Veterans with Heart Failure Phenotyped Using Artificial Intelligence Approaches: The National DCVA-HF Registry

Authors

• Sijian Zhang, Veterans Affairs Medical Center, Washington, DC.
• Venkatesh K. Raman, Veterans Affairs Medical Center, Washington, DC; Georgetown University, Washington, DC.
• Yijun Shao, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Samir Patel, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Yan Cheng, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Terri E. Workman, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Helen M. Sheriff, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Gregg C. Fonarow, University of California, Los Angeles, CA.
• Phillip H. Lam, Georgetown University, Washington, DC; Medstar Washington Hospital Center, Washington, DC.
• Paul A. Heidenreich, Veterans Affairs Medical Center, Palo Alto, CA; Stanford University, Stanford, CA.
• Charity J. Morgan, Veterans Affairs Medical Center, Washington, DC; University of Alabama at Birmingham, Birmingham, AL.
• Hans J. Moore, Veterans Affairs Medical Center, Washington, DC; Georgetown University, Washington, DC; George Washington University, Washington, DC; Uniformed Services University, Washington, DC.
• Jose D. Vargas, Veterans Affairs Medical Center, Washington, DC; Georgetown University, Washington, DC.
• Natalie M. Vassall, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Cherinne Arundel, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Pamela E. Karasik, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Charles Faselis, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC; Uniformed Services University, Washington, DC.
• Michael S. Heimall, HealthWell Foundation, Germantown, MD.
• David Atkins, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Stefan D. Anker, Charité Universitätsmedizin, Berlin, Germany; Wroclaw Medical University, Wroclaw, Poland.
• Javed Butler, Baylor Scott and White Research Institute, Dallas, TX; University of Mississippi, Jackson, MS.
• Gerasimos S. Filippatos, National and Kapodistrian University of Athens, Athens, Greece; Attikon University Hospital, Athens Greece.
• Wen-Chih Wu, Veterans Affairs Medical Center, Providence, RI; Brown University, Providence, RI.
• Qing Zeng-Treitler, Veterans Affairs Medical Center, Washington, DC; George Washington University, Washington, DC.
• Ali Ahmed, Veterans Affairs Medical Center, Washington, DC; Georgetown University, Washington, DC; George Washington University, Washington, DC. Electronic address: [email protected].

Document Type

Journal Article

Publication Date

4-24-2026

Journal

Journal of cardiac failure

DOI

10.1016/j.cardfail.2026.03.019

Keywords

Artificial Intelligence; Heart Failure; Phenotype; Registry; Veterans

Abstract

BACKGROUND: Major heart failure (HF) registries are limited by manual chart abstraction and to hospitalized patients. Using artificial intelligence (AI) approaches and electronic health record (EHR) data from the Veterans Affairs (VA) healthcare system, we have assembled the National DCVA-HF Registry, which includes both ambulatory and hospitalized HF patients. In the current study, we descriptively compared these patients with those identified using International Classification of Diseases (ICD) codes. METHODS: We identified 1,416,512 Veterans with at least one ICD code for HF in the VA national EHR from 1999 to 2017. The first date of an ICD code for HF was considered the index HF date. We used validated encounter-based AI approaches based on machine learning and natural language processing models, and ICD code-based approaches based on ≥1 hospitalization or ≥2 outpatient encounters due to HF, to assemble the AI-HF and ICD-HF cohorts, respectively. The two cohorts were compared using absolute standardized differences, with values ≥10% indicating clinical significance. All analyses were descriptive, and no inferential or causal claims were made. RESULTS: The AI and ICD approaches assembled 1,031,970 and 614,828 patients, respectively, after a mean of 0.4 and 1.0 years from the index HF date. Patients in the AI-HF (vs. ICD-HF) cohort had a mean age of 71.4 (vs. 70.5) years, 98.1% (vs. 98.0%) were men, 13.9% (vs. 16.1%) were African American, and 7.7% (vs. 13.4%) had index HF hospitalization, with absolute standardized differences of 8%, 1%, 6%, and 18%, respectively, which were <10% for 66 other baseline characteristics. One-year post-index HF hospitalization occurred in 10.7% and 15.6% of patients in the AI-HF and ICD-HF cohorts, respectively. One‑year mortality was lower in the ICD-HF cohort, reflecting expected immortal‑time bias due to later cohort qualification. CONCLUSIONS: The findings from this descriptive study demonstrate that the AI approach assembled a substantially larger cohort that included most patients identified using the ICD code approach, suggesting broad consistency between the two approaches. Future external validation is needed to determine its potential utility as a robust tool for improving patient care, health services operations, and clinical research in HF.

APA Citation

Zhang, Sijian; Raman, Venkatesh K.; Shao, Yijun; Patel, Samir; Cheng, Yan; Workman, Terri E.; Sheriff, Helen M.; Fonarow, Gregg C.; Lam, Phillip H.; Heidenreich, Paul A.; Morgan, Charity J.; Moore, Hans J.; Vargas, Jose D.; Vassall, Natalie M.; Arundel, Cherinne; Karasik, Pamela E.; Faselis, Charles; Heimall, Michael S.; Atkins, David; Anker, Stefan D.; Butler, Javed; Filippatos, Gerasimos S.; Wu, Wen-Chih; Zeng-Treitler, Qing; and Ahmed, Ali, "Characteristics and Outcomes of Over One Million Veterans with Heart Failure Phenotyped Using Artificial Intelligence Approaches: The National DCVA-HF Registry" (2026). GW Authored Works. Paper 9018.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/9018

Department

Medicine