Peak Oxygen Uptake Prediction From Resting and Submaximal Variables of Cardiopulmonary Exercise Testing

Area of Science:

• Exercise Physiology
• Cardiopulmonary Diagnostics
• Biostatistics

Background:

• Cardiorespiratory fitness, indicated by peak oxygen uptake (VO2 max), is a key prognostic marker.
• Assessing VO2 max typically requires maximal exertion during cardiopulmonary exercise testing (CPET).
• Maximal exertion may not be achievable for all individuals, necessitating alternative assessment methods.

Purpose of the Study:

• To develop and evaluate predictive models for peak oxygen uptake (VO2 max) using submaximal variables from CPET.
• To enable cardiorespiratory fitness assessment when maximal exertion is not possible.

Main Methods:

• Utilized data from 13,535 CPETs, stratifying patients into normal (NG) and other (OG) groups.
• Trained and evaluated regression models (Bayesian Ridge, Light Gradient Boosting Machine) using demographic, resting, and submaximal variables.
• Employed stratified 5-fold cross-validation for robust model assessment.

Main Results:

• Models incorporating demographic, resting, and submaximal variables significantly improved prediction accuracy (R² increased substantially across all groups).
• Key predictors included oxygen consumption at the first ventilatory threshold, minute ventilation at the second ventilatory threshold, and forced expiratory volume in 1 second.
• Exploratory analysis indicated improved performance with the inclusion of the chronotropic index.

Conclusions:

• A robust model for predicting peak oxygen uptake using submaximal CPET variables was developed.
• This methodology provides a valuable tool for assessing cardiorespiratory fitness and prognostic markers in individuals unable to achieve maximal exertion.