Long-term sickness absence trajectories among ageing municipal employees - the contribution of social and health-related factors

Abstract

Background: The ageing work force is heterogeneous, following distinct development in work ability. This study aims to identify trajectories of long-term sickness absence (SA) in later careers and to examine potentially modifiable factors associated with the development of SA.

Methods: Data comprised of municipal employees of the city of Helsinki aged 50-60 years during 2004-2018 (N = 4729, 80% women). The developmental trajectories of long-term (> 10 working days) SA were examined with Group-based trajectory modelling (GBTM) using SA records of the Social Insurance Institution of Finland during 2004-2018. All-cause and diagnosis-specific (mental disorder- and musculoskeletal disease-related) SA days were analysed. The association of social and health-related factors with trajectory membership was examined using multinomial logistic regression (odds ratios and 95% confidence intervals).

Results: A model with three trajectories was selected for both all-cause and diagnosis-specific SA. Regarding all-cause long-term SA trajectories, 42% had no long-term SA, 46% had low levels of SA, and 12% had a high rate of SA during follow-up. Lower occupational class, reporting smoking, overweight or obesity, moderate or low leisure-time physical activity, and sleep problems were associated with a higher likelihood of belonging to the trajectory with a high rate of SA in both all-cause and diagnosis-specific models.

Conclusions: Most ageing employees have no or little long-term SA. Modifiable factors associated with trajectories with more SA could be targeted when designing and timing interventions in occupational healthcare.

Keywords: Ageing; Cohort study; Health behaviour; Sick leave; Sickness absence; Trajectories; Work arrangements.

Fig. 1

All-cause long-term (> 10 working days) sickness absence (SA) trajectories’ averages and estimates with 95% confidence intervals identified in the group-based trajectory modelling (GBTM) (N = 2747). Follow-up between 50–60 years of age. Sickness absence by age from the model. The ‘No SA’ trajectory group (directly observed from the data) was added after GBTM (N = 4729). ‘No SA’ (42% n = 1982), ‘Low SA’ (46%, n = 2183), and ‘High SA’ (12%, n = 564)

Fig. 2

Mental disorder–related long-term (> 10 working days) sickness absence (SA) trajectories’ averages and estimates with 95% confidence intervals identified in the group-based trajectory modelling (GBTM) (N = 697). Follow-up between 50–60 years of age. Fitted SA rate by age from the GBTM model. The ‘No MD SA’ trajectory group was added after GBTM (N = 4729). ‘‘No MD SA’ (85%, n = 4032), ‘Low MD SA’ (10%, n = 482) and ‘High MD SA’ (5%, n = 215); MD = Mental disorder

Fig. 3

Musculoskeletal disease–related long-term (> 10 working days) sickness absence (SA) trajectories’ averages and estimates with 95% confidence intervals identified in the group-based trajectory modelling (GBTM) (n = 1273). Follow-up between 50–60 years of age. Fitted SA rate by age from the model. The ‘No MSD SA’ trajectory group was added after GBTM (N = 4729). ‘No MSD SA’ (73%, n = 3456), ‘Low MSD SA’ (20%, n = 930), ‘High MSD SA’ (7%, n = 343); MSD = Musculoskeletal disease