Related Experiment Video
Updated: Jul 15, 2025
Author Spotlight: Workflow for Integrating POCUS Data into EHR for Managing Heart Failure Patients
Published on: July 12, 2024
Development and Optimization of the Veterans Affairs' National Heart Failure Dashboard for Population Health
Nicholas Brownell1, Chad Kay2, David Parra3
1Division of Cardiology, David Geffen School of Medicine at University of California, Los Angeles, Los Angeles, CA.
Insights
The VA national heart failure (HF) dashboard was optimized for accuracy using natural language processing and an imaging model. This improved identification of HF subtypes, enhancing patient care.
Area of Science:
- Cardiovascular Medicine
- Health Informatics
- Data Science in Healthcare
Background:
- The Veterans Affairs (VA) deployed a national heart failure (HF) dashboard in 2020.
- The initial dashboard lacked precision in identifying HF subtypes.
- This study details the optimization process for the VA's national HF dashboard.
Purpose of the Study:
- To describe the development and optimization of the VA national HF dashboard.
- To improve the accuracy and reliability of HF subtype identification within the VA system.
- To enhance the utility of the dashboard for population health management.
Main Methods:
- Stepwise refinement of the VA national HF dashboard.
- Improved case definitions and patient identification using natural language processing (NLP).
- Incorporation of an imaging-quality hierarchy and evaluation of imaging modalities and ICD-code requirements.
Main Results:
- Dashboard accuracy for HF with reduced ejection fraction (HFrEF) improved from 54.1% to 89.2%.
- Accuracy for HF with preserved ejection fraction (HFpEF) increased from 53.9% to 88.0%.
- HF with mildly reduced ejection fraction (HFmrEF) was added with 88.0% accuracy.
Conclusions:
- An imaging-quality hierarchy model and NLP algorithm significantly enhanced VA HF dashboard accuracy.
- The revised dashboard demonstrates improved reliability and higher utilization for population health management.
- Optimized informatics algorithms support better health management for patients with heart failure.
Background:
In 2020, the Veterans Affairs (VA) health care system deployed a heart failure (HF) dashboard for use nationally. The initial version was notably imprecise and unreliable for the identification of HF subtypes. We describe the development and subsequent optimization of the VA national HF dashboard.
Materials And Methods:
This study describes the stepwise process for improving the accuracy of the VA national HF dashboard, including defining the initial dashboard, improving case definitions, using natural language processing for patient identification, and incorporating an imaging-quality hierarchy model. Optimization further included evaluating whether to require concurrent ICD-codes for inclusion in the dashboard and assessing various imaging modalities for patient characterization.
Results:
Through multiple rounds of optimization, the dashboard accuracy (defined as the proportion of true results to the total population) was improved from 54.1% to 89.2% for the identification of HF with reduced ejection fraction (HFrEF) and from 53.9% to 88.0% for the identification of HF with preserved ejection fraction (HFpEF). To align with current guidelines, HF with mildly reduced ejection fraction (HFmrEF) was added to the dashboard output with 88.0% accuracy.
Conclusions:
The inclusion of an imaging-quality hierarchy model and natural-language processing algorithm improved the accuracy of the VA national HF dashboard. The revised dashboard informatics algorithm has higher use rates and improved reliability for the health management of the population.
Related Concept Videos
01:30Heart Failure V: Medical Management
01:30Heart Failure VII: Nursing Interventions
01:27Heart Failure I: Introduction
01:30Heart Failure IV: Classification and Diagnostic Evaluation
01:29Heart Failure II: Pathophysiology
01:26Heart Failure III: Clinical Manifestations