The study of oxygen uptake (VO2) dynamics during walking exercise transitions adds valuable information regarding fitness level and energy expenditure. However, direct VO2 measurements are not applicable for measurements in the general population under realistic settings. Devices to measure VO2 are associated with elevated cost, uncomfortable use of a mask, need of trained technicians and impossibility of long-term data collection. The objective of this study was to predict the VO2 dynamics from heart rate and inputs from the treadmill ergometer by a novel artificial neural network approach. To accomplish this, ten healthy young participants performed one incremental and three moderate constant work rate treadmill walking exercises. The speed and grade used for the moderate intensity protocol was related to 80 % of the VO2 response at the gas exchange threshold estimated during the incremental exercise. The measured VO2 was used to train an artificial neural network to create an algorithm able to predict the VO2 based on easy-to-obtain inputs. The dynamics of the VO2 response during exercise transition were evaluated by exponential modelling. Within each participant, the predicted VO2 was strongly correlated to the measured VO2 (r=0.97±0.0) and presented a low bias (~0.2%), enabling the characterization of the VO2 dynamics during treadmill walking exercise. The proposed algorithm could be incorporated into smart devices and fitness equipment, making them suitable for tracking changes in aerobic fitness and physical health beyond the infrequent monitoring of patients during clinical interventions and rehabilitation programs.
- machine learning
- oxygen uptake kinetics
- aerobic fitness
- Copyright © 2016, Journal of Applied Physiology