Machine learning predicts peak oxygen uptake and peak power output for customizing cardiopulmonary exercise testing using non-exercise features

• Published in: European journal of applied physiology 2024-11, Vol.124 (11), p.3421-3431
• Main Authors: Wenzel, Charlotte, Liebig, Thomas, Swoboda, Adrian, Smolareck, Rika, Schlagheck, Marit L., Walzik, David, Groll, Andreas, Goulding, Richie P., Zimmer, Philipp
• Format: Article
• Language: English
• Subjects: Adult; Biomedical and Life Sciences; Biomedicine; Body composition; Cardiorespiratory fitness; Cardiorespiratory Fitness - physiology; Cross-Sectional Studies; Exercise Test - methods; Exercise Test - standards; Female; Human Physiology; Humans; Learning algorithms; Machine Learning; Male; Mathematical models; Maximum oxygen consumption; Occupational Medicine/Industrial Medicine; Original; Original Article; Oxygen Consumption - physiology; Physical characteristics; Predictions; Regression analysis; Skeletal muscle; Sports Medicine; Young Adult
• ISSN: 1439-6319; 1439-6327; 1439-6327
• DOI: 10.1007/s00421-024-05543-x

Purpose Cardiopulmonary exercise testing (CPET) is considered the gold standard for assessing cardiorespiratory fitness. To ensure consistent performance of each test, it is necessary to adapt the power increase of the test protocol to the physical characteristics of each individual. This study aimed to use machine learning models to determine individualized ramp protocols based on non-exercise features. We hypothesized that machine learning models will predict peak oxygen uptake ( V ˙ O 2peak ) and peak power output (PPO) more accurately than conventional multiple linear regression (MLR). Methods The cross-sectional study was conducted with 274 (♀168, ♂106) participants who performed CPET on a cycle ergometer. Machine learning models and multiple linear regression were used to predict V ˙ O 2peak and PPO using non-exercise features. The accuracy of the models was compared using criteria such as root mean square error (RMSE). Shapley additive explanation (SHAP) was applied to determine the feature importance. Results The most accurate machine learning model was the random forest (RMSE: 6.52 ml/kg/min [95% CI 5.21–8.17]) for V ˙ O 2peak prediction and the gradient boosting regression (RMSE: 43watts [95% CI 35–52]) for PPO prediction. Compared to the MLR, the machine learning models reduced the RMSE by up to 28% and 22% for prediction of V ˙ O 2peak and PPO, respectively. Furthermore, SHAP ranked body composition data such as skeletal muscle mass and extracellular water as the most impactful features. Conclusion Machine learning models predict V ˙ O 2peak and PPO more accurately than MLR and can be used to individualize CPET protocols. Features that provide information about the participant's body composition contribute most to the improvement of these predictions. Trial registration number DRKS00031401 (6 March 2023, retrospectively registered).