Prediction of oxygen uptake dynamics by machine learning analysis of wearable sensors during activities of daily living

Currently, oxygen uptake ([Image: see text]) is the most precise means of investigating aerobic fitness and level of physical activity; however, [Image: see text] can only be directly measured in supervised conditions. With the advancement of new wearable sensor technologies and data processing approaches, it is possible to accurately infer work rate and predict [Image: see text] during activities of daily living (ADL). The main objective of this study was to develop and verify the methods required to predict and investigate the [Image: see text] dynamics during ADL. The variables derived from the wearable sensors were used to create a [Image: see text] predictor based on a random forest method. The [Image: see text] temporal dynamics were assessed by the mean normalized gain amplitude (MNG) obtained from frequency domain analysis. The MNG provides a means to assess aerobic fitness. The predicted [Image: see text] during ADL was strongly correlated (r = 0.87, P < 0.001) with the measured [Image: see text] and the prediction bias was 0.2 ml·min(−1)·kg(−1). The MNG calculated based on predicted [Image: see text] was strongly correlated (r = 0.71, P < 0.001) with MNG calculated based on measured [Image: see text] data. This new technology provides an important advance in ambulatory and continuous assessment of aerobic fitness with potential for future applications such as the early detection of deterioration of physical health.