Combined Effects of Physical Behavior Compositions and Psychosocial Resources on Perceived Exertion Among Eldercare Workers

Abstract

Objectives: High perceived physical exertion is common in eldercare workers and a strong predictor for impaired health. However, little is known on how physical behaviors at work associate with physical exertion in this group. The aim of this study was to determine the extent to which the composition of physical behaviors at work is associated with perceived physical exertion in nursing home eldercare workers, and the extent to which these associations are modified by psychosocial resources.

Methods: Our population consisted of 399 female eldercare workers from 126 wards in 20 different nursing homes. We evaluated time spent in physical behaviors at work [sitting, standing still, light activities (LAs), and moderate to vigorous activities (MVAs)] using triaxial accelerometers worn, on average, for three working days. We accounted for inherent codependency between the behaviors using compositional data analysis. We used multilevel linear mixed regression models to determine associations between the behaviors and perceived exertion, measured on a numeric rating scale (0-10), and included interactions between each behavior and psychosocial resources (influence at work, social support, and quality of leadership) to determine a possible moderating effect of resources. Regression results were illustrated using isotemporal substitution.

Results: Sitting was negatively (β: -0.64; P < 0.01) while MVA was positively (β: 0.95; P = 0.02) associated with perceived exertion. According to isotemporal substitution, replacing 30 min of MVA by sitting would, for an average worker, be associated with a decrease in physical exertion by -0.14 on the 0-10 scale. Job resources marginally moderated the association between LA and exertion. Thus, among workers with low influence and low social support, we found a positive association between LA and exertion, while that was not found for workers with medium or high influence and support (interactions for influence and support: P = 0.08 and P = 0.10).

Conclusions: Our findings suggest that reallocating time from MVA to sitting can mitigate perceived physical exertion in eldercare workers. More time in LA increased physical exertion only for workers with low psychosocial resources, supporting a positive effect of a better psychosocial work environment in elderly care.

Keywords: compositional data analysis; healthcare; physical exertion; psychosocial factors; triaxial accelerometers.

Figure 1.

Estimated change in perceived physical exertion when reallocating time to a specific behavior from all other behaviors (one-to-many method), relative to the average composition of the sample. Diagrams show the estimated change in exertion, with 95% CI, from the mean score (6.9 on the 0–10 scale) of all participants, according to model 2.

Figure 2.

Estimated change in perceived physical exertion when reallocating time to sitting from MVAs (one-to-one method), relative to the average composition of the sample. Diagram shows the estimated change in exertion, with 95% CI, from the mean score (6.9 on the 0–10 scale) of all participants, according to model 2.

Figure 3.

Moderating effects of psychosocial resources (stratified by lower, middle, and upper tertile), illustrated by the estimated change in perceived physical exertion when reallocating time to LAs from all other behaviors (one-to-many method), relative to the average composition of the sample. Diagrams show the estimated change in exertion, with 95% CI, from the mean score (6.9 on the 0–10 scale) of all participants.