What is it about?
This study explores the use of various regression models to estimate left ventricular ejection fraction (LVEF) from 24-hour electrocardiogram (ECG) recordings in heart failure (HF) patients. The research compares support vector machine (SVM), extreme gradient boosting (XGBOOST), gaussian process regression (GPR), and decision tree models across three groups of HF patients with different LVEF levels. Data from 303 patients were analyzed, revealing that GPR and decision tree models provided the most accurate LVEF estimations, with RMSE values of 3.83% and 3.42%, respectively. The study also identifies specific time periods during the day with the lowest RMSE values, suggesting potential applications for automated screening systems in coronary artery disease (CAD) patients.
Featured Image
Photo by Robina Weermeijer on Unsplash
Why is it important?
This study is important because it focuses on finding the best way to measure how well the heart is working in people with heart failure. This measurement, called left ventricular ejection fraction (LVEF), helps doctors decide on the best treatments for patients and assess how serious their condition is. By using data from electrocardiograms (ECGs), which are simple and affordable tests that monitor heart activity, the study aims to figure out which methods give the most accurate LVEF results. This research could lead to better ways of diagnosing and managing heart failure, potentially improving patient care and outcomes.
Perspectives
Read the Original
This page is a summary of: Investigating automated regression models for estimating left ventricular ejection fraction levels in heart failure patients using circadian ECG features, PLoS ONE, December 2023, PLOS,
DOI: 10.1371/journal.pone.0295653.
You can read the full text:
Contributors
The following have contributed to this page