Estimating absolute and relative physical activity intensity across age via accelerometry in adults

Abstract

This study examined the predictive validity of accelerometers (ACC) to estimate physical activity intensity (PAI) across age and differences in intensity predictions when expressed in relative and absolute PAI terms. Ninety adults categorized into 3 age groups (20-29, 40-49, and 60-69 yr) completed a treadmill calibration study with simultaneous ACC (7164 Actigraph) and oxygen-consumption assessment. Results revealed strong linear relations between ACC output and measured PAI (R2 = .62-.89) across age and similar ACC cut-point ranges across age delineating absolute PAI ranges compared with previous findings. Comparing measured metabolic equivalents (METs) with estimated METs derived from previously published regression equations revealed that age did not affect predictive validity of ACC estimates of absolute PAI. Comparing ACC output expressed in relative vs. absolute terms across age revealed substantial differences in PAI ACC count ranges. Further work is warranted to increase the applicability ofACC use relative to PAI differences associated with physiological changes with age.

Figure 1

Box plot summarizing medians, 25th and 75th percentiles, and range of accelerometer counts per minute across speed by age group. *Statistically different from 60- to 69-year group, p < .05. Note. The 60- to 69-year group was omitted from 11.3 km/hr because only 1 participant finished that speed.