Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study.

TitlePrediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study.
Publication TypeJournal Article
Year of Publication2023
AuthorsAdekkanattu P, Rasmussen LV, Pacheco JA, Kabariti J, Stone DJ, Yu Y, Jiang G, Luo Y, Brandt PS, Xu Z, Vekaria V, Xu J, Wang F, Benda NC, Peng Y, Goyal P, Ahmad FS, Pathak J
JournalSci Rep
Volume13
Issue1
Pagination294
Date Published2023 Jan 06
ISSN2045-2322
KeywordsElectronic Health Records, Heart Failure, Humans, Longitudinal Studies, Machine Learning, Prognosis, Retrospective Studies, Stroke Volume, Ventricular Function, Left
Abstract

Left ventricular ejection fraction (EF) is a key measure in the diagnosis and treatment of heart failure (HF) and many patients experience changes in EF overtime. Large-scale analysis of longitudinal changes in EF using electronic health records (EHRs) is limited. In a multi-site retrospective study using EHR data from three academic medical centers, we investigated longitudinal changes in EF measurements in patients diagnosed with HF. We observed significant variations in baseline characteristics and longitudinal EF change behavior of the HF cohorts from a previous study that is based on HF registry data. Data gathered from this longitudinal study were used to develop multiple machine learning models to predict changes in ejection fraction measurements in HF patients. Across all three sites, we observed higher performance in predicting EF increase over a 1-year duration, with similarly higher performance predicting an EF increase of 30% from baseline compared to lower percentage increases. In predicting EF decrease we found moderate to high performance with low confidence for various models. Among various machine learning models, XGBoost was the best performing model for predicting EF changes. Across the three sites, the XGBoost model had an F1-score of 87.2, 89.9, and 88.6 and AUC of 0.83, 0.87, and 0.90 in predicting a 30% increase in EF, and had an F1-score of 95.0, 90.6, 90.1 and AUC of 0.54, 0.56, 0.68 in predicting a 30% decrease in EF. Among features that contribute to predicting EF changes, baseline ejection fraction measurement, age, gender, and heart diseases were found to be statistically significant.

DOI10.1038/s41598-023-27493-8
Alternate JournalSci Rep
PubMed ID36609415
PubMed Central IDPMC9822934
Grant ListR00 LM013001 / LM / NLM NIH HHS / United States
R01 LM013337 / LM / NLM NIH HHS / United States
R01 GM105688 / GM / NIGMS NIH HHS / United States
UL1 TR001422 / TR / NCATS NIH HHS / United States
K23 HL155970 / HL / NHLBI NIH HHS / United States
Division: 
Institute of Artificial Intelligence for Digital Health
Category: 
Faculty Publication