Early prediction of physical activity level 1 year after stroke: a longitudinal cohort study

Abstract

Objective: To investigate which variables present prior and early after stroke may have an impact on the level of physical activity (PA) 1 year poststroke.

Design: Prospective longitudinal cohort and logistic regression analysis.

Setting: Stroke Unit at Sahlgrenska University Hospital, Gothenburg, Sweden.

Participants: 117 individuals as part of the Stroke Arm Longitudinal Study (SALGOT) admitted to the stroke unit during a period of 18 months were consecutively recruited. The inclusion criteria were: first-time stroke, impaired upper extremity function, admitted to the stroke unit within 3 days since onset, local residency and ≥18 years old. The exclusion criteria were: upper extremity condition or severe multi-impairment prior to stroke, short life expectancy and non-Swedish speaking. 77 participants followed up at 1 year poststroke were included in the analysis.

Primary outcome: PA level 1 year after stroke was assessed using a 6-level Saltin-Grimby Scale, which was first dichotomised into mostly inactive or mostly active and second into low or moderate/high level of PA.

Results: Being mostly inactive 1 year after stroke could be predicted by age at stroke onset (OR 1.07, 95% CI 1.00 to 1.13, p=0.041), functional dependency at discharge (OR 7.01, 95% CI 1.73 to 28.43, p=0.006) and prestroke PA (OR 7.46, 95% CI 1.51 to 36.82, p=0.014). Having a low level of PA 1 year after stroke could be predicted by age at stroke onset (OR 1.13, 95% CI 1.06 to 1.21, p<0.001) and functional dependency at discharge (OR 3.62, 95% CI 1.09 to 12.04, p=0.036).

Conclusions: Previous low level of PA, older age and functional dependency all provided value in predicting low PA 1 year after stroke. These results indicate that age and simple clinical evaluations early after stroke may be useful to help clinicians identify persons at risk of being insufficiently active after stroke. Further research is needed to clarify if these findings may apply to the large population of stroke survivors.

Trial registration number: ClinicalTrials.gov (NCT01115348).

Keywords: motor activity; outcome assessment; physical activity; prognosis; stroke.

Figure 1

Flowchart for inclusion of the study participants.

Figure 2

Predicted probabilities of being mostly inactive 1 year after stroke. The predicted probability increases with higher age, higher degree of functional dependency and being physically inactive prestroke.

Figure 3

Predicted probability for having low PA 1 year after stroke. The predicted probability increases with higher age and higher degree of functional dependency.