Effects of Exercise Training Interventions on Executive Function in Older Adults: A Systematic Review and Meta-Analysis

Abstract

Background: Chronic exercise training has been shown be to positively associated with executive function (EF) in older adults. However, whether the exercise training effect on EF is affected by moderators including the specific sub-domain of EF, exercise prescription variables, and sample characteristics remains unknown.

Objectives: This systematic and meta-analytic review of randomized controlled trials (RCTs) investigated the effects of exercise training on EF in older adults and explored potential moderators underlying the effects of exercise training on EF.

Methods: In accordance with the PRISMA guidelines, the electronic databases MEDLINE (PubMed) and EMBASE (Scopus) were searched from January 2003 to November 2019. All studies identified for inclusion were peer-reviewed and published in English. To be included, studies had to report findings from older (> 55 years old), cognitively normal adults or adults with mild cognitive impairment (MCI) randomized to an exercise training or a control group. The risk of bias in each study was appraised using the Cochrane risk-of-bias tool. Fixed-effects models were used to compare the effects of exercise training and control conditions on EF assessed at baseline and post-intervention. In addition, subgroup analyses were performed for three moderators (i.e., the specific sub-domain of EF, exercise prescription variables, and sample characteristics).

Results: Thirty-three RCTs were included. Overall, exercise training was associated with a significant small improvement in EF [Q(106) = 260.09, Hedges' g = 0.21; p < 0.01]. The EF sub-domain moderator was not significant [Q(2) = 4.33, p > 0.05], showing that the EF improvement in response to exercise is evident for measures of inhibition, updating, and shifting. Regarding exercise prescription variables, results were significantly moderated by frequency of exercise training [Q(1) = 10.86, p < 0.05], revealing that effect sizes (ESs) were larger for moderate frequency (g = 0.31) as compared to low frequency exercise (g = 0.15). The results also showed type of exercise training moderated the ESs [Q(4) = 26.18, p < 0.05], revealing that ESs were largest for other forms of exercise (g = 0.44), followed by Tai Chi and yoga (g = 0.38), resistance exercise (g = 0.22), aerobic exercise (g = 0.14), and combined exercise (g = 0.10). In addition, The results showed moderated length of training the ESs [Q(2) = 16.64, p < 0.05], revealing that ESs were largest for short length (g = 0.32), followed by mid length (g = 0.26) and long length (g = 0.09). No significant difference in effects was observed as a function of exercise intensity [Q(1) = 2.87 p > 0.05] and session time [Q(2) = 0.21, p > 0.05]. Regarding sample characteristics, the results were significantly moderated by age [Q(2) = 20.64, p < 0.05], with significant benefits for young-old (55-65 years old) (g = 0.30) and mid-old (66-75 years old) (g = 0.25), but no effect on EF for old-old (more than 75 years old). The results were also significantly moderated by physical fitness levels [Q(1) = 10.80, p < 0.05], revealing that ESs were larger for sedentary participants (g = 0.33) as compared to physically fit participants (g = 0.16). In addition, results were also significantly moderated by cognitive status [Q(1) = 11.44, p < 0.05], revealing that ESs were larger for participants with cognitively normal (g = 0.26) as compared to those with mild cognitive impairment (g = 0.08). No significant differences in effects were observed as a function of sex [Q(2) = 5.38, p > 0.05].

Conclusions: Exercise training showed a small beneficial effect on EF in older adults and the magnitude of the effect was different across some moderators.

Fig. 1

PRISMA flow chart of the study selection process

Fig. 2

Summary of risk of bias for each item presented as a percentage across all included studies

Fig. 3

Funnel plot for visual inspection of study bias