An artificial neural network algorithm using heart rate and treadmill inputs strongly predicted measured V̇o2 during walking (r = 0.97 ± 0.0) with a low bias (~0.2%).
Observational (n=10)
Does an artificial neural network approach accurately predict V̇o2 dynamics from heart rate and treadmill inputs in healthy young participants?
An artificial neural network can accurately predict oxygen uptake dynamics during treadmill walking using heart rate and treadmill inputs, offering a practical alternative to direct gas exchange measurements.
Effect estimate: r = 0.97 ± 0.0
The study of oxygen uptake (V̇o 2 ) dynamics during walking exercise transitions adds valuable information regarding fitness. However, direct V̇o 2 measurements are not practical for general population under realistic settings. Devices to measure V̇o 2 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 V̇o 2 dynamics from heart rate and inputs from the treadmill ergometer by a novel artificial neural network approach. To accomplish this, 10 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 V̇o 2 response at the gas exchange threshold estimated during the incremental exercise. The measured V̇o 2 was used to train an artificial neural network to create an algorithm able to predict the V̇o 2 based on easy-to-obtain inputs. The dynamics of the V̇o 2 response during exercise transition were evaluated by exponential modeling. Within each participant, the predicted V̇o 2 was strongly correlated to the measured V̇o 2 ( = 0.97 ± 0.0) and presented a low bias (~0.2%), enabling the characterization of the V̇o 2 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.
Beltrame et al. (Fri,) conducted a observational in Healthy (n=10). Artificial neural network algorithm vs. Measured V̇o2 was evaluated on Correlation between predicted and measured V̇o2 (r = 0.97 ± 0.0). An artificial neural network algorithm using heart rate and treadmill inputs strongly predicted measured V̇o2 during walking (r = 0.97 ± 0.0) with a low bias (~0.2%).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: