Key result
Machine learning models using submaximal CPET predict VO2peak with ~11% error.
Why the study?
This study evaluated the accuracy of machine learning models to predict peak oxygen consumption from warmup and submaximal treadmill CPET parameters and assessed the importance of respiratory parameters.
Can machine learning models using cardiorespiratory parameters from submaximal treadmill exercise tests accurately predict peak oxygen consumption (VO2peak) in young adults?
Cross-Sectional (n=369)
No
Can machine learning models using cardiorespiratory parameters from submaximal treadmill exercise tests accurately predict peak oxygen consumption (VO2peak) in young adults?
Machine learning models incorporating respiratory rate and pulmonary ventilation from submaximal exercise tests can predict VO2peak with reasonable accuracy, offering a feasible alternative to maximal CPET.
May support submaximal CPET with ML for VO2peak estimation in young adults; leaves open prospective validation before clinical adoption.
This study investigates the quality of peak oxygen consumption (VO 2peak ) prediction based on cardiac and respiratory parameters calculated from warmup and submaximal stages of treadmill cardiopulmonary exercise test (CPET) using machine learning (ML) techniques and assesses the importance of respiratory parameters for the prediction outcome. The database consists of the following parameters: heart rate (HR), respiratory rate (RespRate), pulmonary ventilation (VE), oxygen consumption (VO 2 ) and carbon dioxide production (VCO 2 ) obtained from 369 treadmill CPETs. Combinations of features calculated based on the HR, VE and RespRate time-series from different stages of CPET were used to create 11 datasets for VO 2peak prediction. Thirteen ML algorithms were employed, and model performances were evaluated using cross-validation with mean absolute percentage error (MAPE), R 2 score, mean absolute error (MAE), and root mean squared error (RMSE) calculated after each iteration of the validation. The results demonstrated that incorporating respiratory-based features improves the prediction of VO 2peak . The best results in terms of R 2 score (0.47) and RMSE (5.78) were obtained for the dataset which included both cardiac- and respiratory-based features from CPET up to 85% of age-predicted HR max , while the best results in terms of MAPE (10.5%) and MAE (4.63) were obtained for the dataset containing cardiorespiratory features from the last 30 seconds of warmup. The study showed the potential of using ML models based on cardiorespiratory features from submaximal tests for prediction of VO 2peak and highlights the importance of the monitoring of respiratory signals, enabling to include respiratory parameters into the analysis. Presented approach offers a feasible alternative to direct VO 2peak measurement, especially when specialized equipment is limited or unavailable.
No takes yet. Share an insight, caveat, or question.
Rosoł et al. (2023) conducted a cross-sectional in Healthy amateur and professional athletes (n=369). Machine learning prediction using cardiorespiratory features from submaximal CPET vs. Direct VO2peak measurement (maximal CPET) was evaluated on Mean absolute percentage error (MAPE) of VO2peak prediction. Machine learning models incorporating cardiac and respiratory features from submaximal cardiopulmonary exercise tests predicted peak oxygen consumption with a mean absolute percentage error of 10.51%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: