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

Abstract

Currently, oxygen uptake () is the most precise means of investigating aerobic fitness and level of physical activity; however, 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 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 dynamics during ADL. The variables derived from the wearable sensors were used to create a predictor based on a random forest method. The 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 during ADL was strongly correlated (r = 0.87, P < 0.001) with the measured and the prediction bias was 0.2 ml·min−1·kg−1. The MNG calculated based on predicted was strongly correlated (r = 0.71, P < 0.001) with MNG calculated based on measured 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.

Mean Normalized Gain: A New Method for the Assessment of the Aerobic System Temporal Dynamics during Randomly Varying Exercise in Humans

“…The applicability of our findings may extend beyond controlled exercise protocols as shown with simulated activities of daily living (Beltrame et al, 2017a) and in freely moving daily life (Beltrame et al, 2017b). Indeed, MNG has the potential importance to rehabilitation programs, exercise prescription and fitness evaluation where the temporal dynamics of the aerobic response might be related to aerobic power (Beltrame and Hughson, 2017b).…”

Estimating an individual’s oxygen uptake during cycling exercise with a recurrent neural network trained from easy-to-obtain inputs: A pilot study

“…al. [49] for the prediction of _ VO 2 from wearable sensors. The ability of neural networks to model complex data was already known and other more basic learners could have been used (e.g.…”

“…Both studies only used current inputs and not past values. Beltrame et al [49] used only 1 sec of lag to include "dynamic changes" of heart rate. Very recently, Borror et.…”

Review of the big data technology use in the medical prognosis

“…To reveal the dynamics of oxygen consumption by a human, a forecasting method based on the random forest algorithm was applied [18]. This technique will allow forecasting the deviation of human health from the norm at an early stage.…”

“…The comparison results of the predicted dynamics and the real dynamics are shown in Figure 4. The concept of the oxygen consumption forecast system [13] Figure 4: Correlation between the predicted MNG and the real MNG [18] In this work, the data was obtained as a result of medical measurements using body sensors. Despite the relatively small amount of data analyzed, due to the applied technique, a practically signifi cant result was obtained.…”