Related Experiment Video
Updated: Jul 11, 2025
05:56
Author Spotlight: Enhancing Diagnostic Strategies and Biomarker Development for Comprehensive Lung Function Analysis
Published on: August 9, 2024
1.3K
Development of Machine Learning Model for VO2max Estimation Using a Patch-Type Single-Lead ECG Monitoring Device in
Hyun Ah Lee1, Woosik Yu2, Jong Doo Choi3
1Department of Pulmonary and Critical Care Medicine, Ajou University School of Medicine, Suwon 16499, Republic of Korea.
Healthcare (Basel, Switzerland)
|November 14, 2023
Summary
A new machine learning model estimates maximal oxygen consumption (VO2max) using ECG patches, offering a simpler alternative to cardiopulmonary exercise tests (CPET) for lung resection candidates.
Area of Science:
- Cardiology
- Pulmonology
- Medical Technology
Background:
- Cardiopulmonary exercise testing (CPET) is crucial for assessing lung resection candidates.
- CPET can be challenging to perform, necessitating alternative assessment methods.
Purpose of the Study:
- To develop a machine learning model for estimating maximal oxygen consumption (VO2max).
- To utilize data from a single-lead electrocardiogram (ECG) patch for VO2max estimation.
- To assess the model's utility in lung resection candidates.
Main Methods:
- Prospective, single-center study involving 42 lung resection candidates.
- Application of a patch-type single-lead ECG monitoring device during CPET.
- Comparison of machine learning algorithm results with standard CPET measurements.
Main Results:
- The machine learning model demonstrated a low bias (-0.33 mL·kg-1·min-1) in estimating VO2max, comparable to the FRIEND equation (0.30 mL·kg-1·min-1).
- The model showed consistent performance across different maximal effort levels and sexes.
- The developed model provided a closer estimation of VO2max than existing equations.
Conclusions:
- The developed machine learning model offers a promising, non-invasive method for VO2max estimation.
- This tool can aid in assessing cardiopulmonary reserve when CPET is not feasible for lung resection candidates.
