Non-exercise Machine Learning Models for Maximal Oxygen Uptake Prediction in National Population Surveys

ABSTRACT Background Maximal oxygen uptake (VO 2 max), an indicator of cardiorespiratory fitness (CRF), requires exercise testing and, as a result, is rarely ascertained in large-scale population-based studies. Non-exercise algorithms are cost-effective methods to estimate VO 2 max, but the existing models have limitations in generalizability and predictive power. This study aims to improve the non-exercise algorithms using machine learning (ML) methods and data from U.S. national population surveys. Methods We used the 1999-2004 data from the National Health and Nutrition Examination Survey (NHANES), in which a submaximal exercise test produced an estimate of the VO 2 max. We applied multiple supervised ML algorithms to build two models: a parsimonious model that used variables readily available in clinical practice, and an extended model that additionally included more complex variables from more Dual-Energy X-ray Absorptiometry (DEXA) and standard laboratory tests. We used Shapley additive explanation (SHAP) to interpret the new model and identify the key predictors. For comparison, existing non-exercise algorithms were applied unmodified to the testing set. Results Among the 5,668 NHANES participants included in the final study population, the mean age was 32.5 years and 49.9% were women. Light Gradient Boosting Machine (LightGBM) had the best performance across multiple types of supervised ML algorithms. Compared with the best existing non-exercise algorithms that could be applied in NHANES, the parsimonious LightGBM model (RMSE: 8.51 ml/kg/min [95% CI: 7.73 -9.33]) and the extended model (RMSE: 8.26 ml/kg/min [95% CI: 7.44 -9.09]) significantly reducing the error by 15% (P <0.01) and 12% (P<0.01 for both), respectively. Conclusion Our non-exercise ML model provides a more accurate prediction of VO 2 max for NHANES participants than existing non-exercise algorithms. What is Known Although cardiorespiratory fitness is recognized as an important marker of cardiovascular health, it is not routinely measured because of the time and resources required to perform exercise tests. Non-exercise algorithms are cost-effective alternatives to estimate cardiorespiratory fitness, but the existing models are restricted in generalizability and predictive power. What the Study Adds We improve non-exercise algorithms for cardiorespiratory fitness prediction using advanced ML methods and a more comprehensive and representative data source from U.S. national population surveys. More health factors that are associated with cardiorespiratory fitness are newly identified. Nationally representative estimates for cardiorespiratory fitness in the U.S. over the recent 20 years are generated.