Evaluation of the activPAL accelerometer for physical activity and energy expenditure estimation in a semi-structured setting

ObjectivesEvaluate accuracy of the activPAL and its proprietary software for prediction of time spent in physical activity (PA) intensities (sedentary, light, and moderate-to-vigorous) and energy expenditure (EE) and compare its accuracy to that of a machine learning model (ANN) developed from raw activPAL data.DesignSemi-structured accelerometer validation in a laboratory setting.MethodsParticipants (n = 41 [20 male]; age = 22.0 ± 4.2) completed a 90-min protocol performing 13 activities for 3-10 min each and choosing activity order, duration, and intensity. Participants wore an activPAL accelerometer (right thigh) and a portable metabolic analyzer. Criterion measures of time spent in sedentary, light, and moderate-to-vigorous PA were determined using measured MET values of ≤1.5, 1.6-2.9, and ≥3.0, respectively. Estimated times in each PA intensity from the activPAL software and ANN were compared with the criterion using repeated measures ANOVA. Window-by-window EE prediction was assessed using correlations and root mean square error.ResultsactivPAL software-estimated sedentary time was not different from the criterion, but light PA was overestimated (6.2 min) and moderate- to vigorous PA was underestimated (4.3 min). ANN-estimated sedentary time and light PA were not different from the criterion, but moderate- to vigorous PA was overestimated (1.8 min). For EE estimation, the activPAL software had lower correlations (r = 0.76 vs. r = 0.89) and higher error (1.74 vs. 1.07 METs) than the ANN.ConclusionsThe ANN had higher accuracy for estimation of EE and PA than the activPAL software in this semi-structured laboratory setting, indicating potential for the ANN to be used in PA assessment.