Extracting aerobic system dynamics during unsupervised activities of daily living using wearable sensor machine learning models

Physical activity levels are related through algorithms to the energetic demand with no information regarding the integrity of the multiple physiological systems involved in the energetic supply. Longitudinal analysis of the oxygen uptake (VO₂) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., VO₂ kinetics). This study evaluated aerobic system dynamics based on predicted VO₂ data obtained from wearable sensors during unsupervised activities of daily living (uADL). Thirteen healthy men performed a laboratory controlled moderate protocol and were monitored for 6 hrs per day, during four days (uADL data). Variables derived from hip accelerometer (ACC_HIP), heart rate monitor and respiratory bands during uADL were extracted and proceeded by a validated random forest regression model to predict VO₂. The aerobic system analysis was based on the frequency-domain analysis of ACC_HIP and predicted VO₂ data obtained during uADL. Optimal samples for frequency domain analysis (constrained to ≤0.01 Hz) were selected when ACC_HIP was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted VO₂ data during uADL correlated with the temporal characteristics of measured VO₂ data during laboratory controlled protocol (r=0.82, p<0.001, n=13). In conclusion, aerobic system dynamics can be investigated during unsupervised activities of daily living by wearable sensors. Although speculative, these algorithms have the potential to be incorporated into wearable systems for early detection of changes in health status in realistic environments by detecting changes in aerobic response dynamics.

from Physiology via xlomafota13 on Inoreader http://ift.tt/2s270Ck
via IFTTT