Artificial neural network-based model for predicting VO sub(2)max from a submaximal exercise test

• Published in: Expert systems with applications Vol. 38; no. 3; pp. 2007 - 2010
• Main Authors: Akay, Mehmet Fatih, Zayid, Elrasheed Ismail Mohommoud, Aktuerk, Erman, George, James D
• Format: Journal Article
• Language: English
• Published: 01.03.2011
• Subjects: Adults; Construction; Correlation coefficients; Heart rate; Learning theory; Mathematical models; Neural networks; Treadmills
• DOI: 10.1016/j.eswa.2010.07.135
• ISSN: 0957-4174

The goal of this study is to develop an accurate artificial neural network (ANN)-based model to predict maximal oxygen uptake (VO sub(2)max) of fit adults from a single stage submaximal treadmill jogging test. Participants (81 males and 45 females), aged from 17 to 40 years, successfully completed a maximal graded exercise test (GXT) to determine VO sub(2)max. The variables; gender, age, body mass, steady-state heart rate and jogging speed are used to build the ANN prediction model. Using 10-fold cross validation on the dataset, the average values of standard error of estimate (SEE), Pearson's correlation coefficient (r) and multiple correlation coefficient (R) of the model are calculated as 1.80 ml kg super(-1) min super(-1), 0.95 and 0.93, respectively. Compared with the results of the other prediction models in literature that were developed using Multiple Linear Regression Analysis, the reported values of SEE, r and R in this study are considerably more accurate.