Predicting VO2max by machine learning models before volitional fatigue during incremental exercise

Beltrame, Thomas; Pereira, Luiz Haroldo; Góis, Mariana de Oliveira; Frade, Maria Cecília Moraes; Linares, Stephanie Nogueira; Petronilho, Ariane; Hughson, R. L.; Catai, Aparecida Maria; Torres, Ricardo Silva

doi:10.1183/13993003.congress-2019.pa4132

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean difference was very close to 0, which is −0.31, and most of the points are scattered in the ±1.96 SD (above −8.59 ml/kg/min and below 7.97 mm/kg/min). The coefficient of determination between the true and predicted VO 2 max in the validation and test datasets (Figure 5A) Previous studies assessed and predicted VO 2 max using different predictors and test protocols (34)(35)(36)(37)(38), but no study classifies the aerobic capacity into subcategories in the previous work. SVM exhibited outstanding performance in the classification tasks (36,38,40,41).…”

Section: The Linear Regression Modelmentioning

confidence: 99%

“…Predicting VO 2 max by machine learning approaches is emerging recently. Anthropometric parameters, time of exercise, workload, and HR self-reported rating of perceived exertion (RPE) are commonly used variables or predictors (34)(35)(36). Beltrame et al (35) revealed that machine learning algorithms successfully predicted VO 2 max of forty-five health participants during the early stages of the test at maximal cardiopulmonary exercise testing.…”

Section: Introductionmentioning

confidence: 99%

“…Anthropometric parameters, time of exercise, workload, and HR self-reported rating of perceived exertion (RPE) are commonly used variables or predictors ( 34 – 36 ). Beltrame et al ( 35 ) revealed that machine learning algorithms successfully predicted VO 2 max of forty-five health participants during the early stages of the test at maximal cardiopulmonary exercise testing. Machine learning methods can also predict VO 2 max based on a 20 m shuttle run test with root mean square error (RMSE) <5.5 ml/kg/min with a sample size of 308 ( 37 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Population and Age-Based Cardiorespiratory Fitness Level Investigation and Automatic Prediction

Xiang

Deng

Mei

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Maximal oxygen consumption (VO2max) reflects aerobic capacity and is crucial for assessing cardiorespiratory fitness and physical activity level. The purpose of this study was to classify and predict the population-based cardiorespiratory fitness based on anthropometric parameters, workload, and steady-state heart rate (HR) of the submaximal exercise test. Five hundred and seventeen participants were recruited into this study. This study initially classified aerobic capacity followed by VO2max predicted using an ordinary least squares regression model with measured VO2max from a submaximal cycle test as ground truth. Furthermore, we predicted VO2max in the age ranges 21–40 and above 40. For the support vector classification model, the test accuracy was 75%. The ordinary least squares regression model showed the coefficient of determination (R2) between measured and predicted VO2max was 0.83, mean absolute error (MAE) and root mean square error (RMSE) were 3.12 and 4.24 ml/kg/min, respectively. R2 in the age 21–40 and above 40 groups were 0.85 and 0.75, respectively. In conclusion, this study provides a practical protocol for estimating cardiorespiratory fitness of an individual in large populations. An applicable submaximal test for population-based cohorts could evaluate physical activity levels and provide exercise recommendations.

show abstract