Development and validation of algorithms to predict left ventricular ejection fraction class from healthcare claims data
Related Experiment Video
Updated: May 8, 2026
Evaluation of Left Ventricular Structure and Function using 3D Echocardiography
Published on: October 28, 2020
Damien Logeart1, Maxime Doublet2, Margaux Gouysse2
1Department of Cardiology, Paris Cité University, AP-HP Hôpital Lariboisière, Inserm U942, 2 rue Ambroise Paré, Paris, France.
Insights
New algorithms can identify left ventricular ejection fraction (LVEF) in heart failure (HF) patients using healthcare claims data. This advances population-based HF studies by providing crucial LVEF information where it was previously missing.
Area of Science:
- Cardiology
- Health Informatics
- Machine Learning
Background:
- Large healthcare claims databases are vital for population-based heart failure (HF) studies.
- Identifying left ventricular ejection fraction (LVEF) is crucial as HF management differs by LVEF category.
- LVEF data is frequently absent in large healthcare claims databases.
Purpose of the Study:
- To develop and validate algorithms for identifying LVEF in HF patients within healthcare claims databases.
- To address the data gap concerning LVEF in population-based HF research.
- To enable more precise HF patient stratification using administrative data.
Main Methods:
- Machine learning, specifically a random forest approach, was employed to build the algorithms.
- Algorithms were trained and validated using the French national claims database (SNDS) and an HF registry.
- Key variables included demographics, comorbidities, medication use (ATC codes), diagnoses (ICD-10), and laboratory tests (natriuretic peptides).
Main Results:
- The developed algorithms demonstrated strong performance in identifying LVEF categories.
- Area under the curve (AUC) values were 0.84 for LVEF ≤40% and 0.79 for LVEF <50% and ≥50%.
- The reinforced algorithm for LVEF ≤40% achieved a positive predictive value of 0.88 and specificity of 0.96.
Conclusions:
- The algorithms accurately identify reduced or preserved LVEF in HF patients within nationwide claims data.
- High positive predictive values and low false-positive rates were achieved.
- These algorithms enhance the utility of healthcare claims databases for HF research and clinical insights.
Aims:
The use of large medical or healthcare claims databases is very useful for population-based studies on the burden of heart failure (HF). Clinical characteristics and management of HF patients differ according to categories of left ventricular ejection fraction (LVEF), but this information is often missing in such databases. We aimed to develop and validate algorithms to identify LVEF in healthcare databases where the information is lacking.
Methods And Results:
Algorithms were built by machine learning with a random forest approach. Algorithms were trained and reinforced using the French national claims database [Système National des Données de Santé (SNDS)] and a French HF registry. Variables were age, gender, and comorbidities, which could be identified by medico-administrative code-based proxies, Anatomical Therapeutic Chemical codes for drug delivery, International Classification of Diseases (Tenth Revision) coding for hospitalizations, and administrative codes for any other type of reimbursed care. The algorithms were validated by cross-validation and against a subset of the SNDS that includes LVEF information. The areas under the receiver operating characteristic curve were 0.84 for the algorithm identifying LVEF ≤ 40% and 0.79 for the algorithms identifying LVEF < 50% and ≥50%. For LVEF ≤ 40%, the reinforced algorithm identified 50% of patients in the validation dataset with a positive predictive value of 0.88 and a specificity of 0.96. The most important predictive variables were delivery of HF medication, sex, age, hospitalization, and testing for natriuretic peptides with different orders of positive or negative importance according to the LVEF category.
Conclusions:
The algorithms identify reduced or preserved LVEF in HF patients within a nationwide healthcare claims database with high positive predictive value and low rates of false positives.
