Search

Predicting cardiorespiratory fitness levels can be useful for measuring progress in an exercise program as well as for stratifying cardiovascular risk in asymptomatic adults. This study proposes a model to predict fitness level in terms of maximal oxygen uptake using anthropometric, heart rate, and step count data. The model was trained on a diverse cohort of 3115 healthy subjects (1035 women and 2080 men) aged 42 ± 10.6 years and tested on a cohort of 779 healthy subjects (260 women and 519 men) aged 42 ± 10.18 years. The developed model is capable of making accurate and reliable predictions with the average test set error of 3.946 ml/kg/min. The maximal oxygen uptake labels were obtained using wearable devices (Apple Watch and Garmin) during recorded workout sessions. Additionally, the model was validated on a sample of 10 subjects with maximal oxygen uptake determined directly using a treadmill protocol in a laboratory setting and showed an error of 4.982 ml/kg/min. Unlike most other models, which use accelerometer readings as additional input data, the proposed model relies solely on heart rate and step counts—data readily available on the majority of fitness trackers. The proposed model provides a point estimation and a probabilistic prediction of cardiorespiratory fitness level, thus it can estimate the prediction's uncertainty and construct confidence intervals. [ABSTRACT FROM AUTHOR]

Predicting cardiorespiratory fitness levels can be useful for measuring progress in an exercise program as well as for stratifying cardiovascular risk in asymptomatic adults. This study proposes a model to predict fitness level in terms of maximal oxygen uptake using anthropometric, heart rate, and step count data. The model was trained on a diverse cohort of 3115 healthy subjects (1035 women and 2080 men) aged 42 ± 10.6 years and tested on a cohort of 779 healthy subjects (260 women and 519 men) aged 42 ± 10.18 years. The developed model is capable of making accurate and reliable predictions with the average test set error of 3.946 ml/kg/min. The maximal oxygen uptake labels were obtained using wearable devices (Apple Watch and Garmin) during recorded workout sessions. Additionally, the model was validated on a sample of 10 subjects with maximal oxygen uptake determined directly using a treadmill protocol in a laboratory setting and showed an error of 4.982 ml/kg/min. Unlike most other models, which use accelerometer readings as additional input data, the proposed model relies solely on heart rate and step counts—data readily available on the majority of fitness trackers. The proposed model provides a point estimation and a probabilistic prediction of cardiorespiratory fitness level, thus it can estimate the prediction's uncertainty and construct confidence intervals. [ABSTRACT FROM AUTHOR]

This study looked at novel data sources for cardiovascular risk prediction including detailed lifestyle questionnaire and continuous blood pressure monitoring, using ensemble machine learning algorithms (MLAs). The reference conventional risk score compared against was the Framingham Risk Score (FRS). The outcome variables were low or high risk based on calcium score 0 or calcium score 100 and above. Ensemble MLAs were built based on naive bayes, random forest and support vector classifier for low risk and generalized linear regression, support vector regressor and stochastic gradient descent regressor for high risk categories. MLAs were trained on 600 Southeast Asians aged 21 to 69 years free of cardiovascular disease. All MLAs outperformed the FRS for low and high-risk categories. MLA based on lifestyle questionnaire only achieved AUC of 0.715 (95% CI 0.681, 0.750) and 0.710 (95% CI 0.653, 0.766) for low and high risk respectively. Combining all groups of risk factors (lifestyle survey questionnaires, clinical blood tests, 24-h ambulatory blood pressure and heart rate monitoring) along with feature selection, prediction of low and high CVD risk groups were further enhanced to 0.791 (95% CI 0.759, 0.822) and 0.790 (95% CI 0.745, 0.836). Besides conventional predictors, self-reported physical activity, average daily heart rate, awake blood pressure variability and percentage time in diastolic hypertension were important contributors to CVD risk classification. [ABSTRACT FROM AUTHOR]