Impact of Physical Exercise on Growth and Progression of Cancer in Rodents-A Systematic Review and Meta-Analysis

Abstract

Background: Physical exercise is suspected to reduce cancer risk and mortality. So far, little is known about the underlying mechanisms. Although limited, murine models represent a promising attempt in order to gain knowledge in this field. Objective: A systematic review and meta-analysis examining various treatment protocols was conducted in order to determine the impact of exercise on tumor growth in rodents. Methods: PubMed, Google scholar and System for information on Gray literature in Europe were screened from inception to October 2017. Risk of bias within individual studies was assessed using the Office of Health Assessment and Translation risk of bias rating tool for human and animal trials. The effect of exercise on tumor growth over and above non-exercise control was pooled using random-effects model. Subgroup analyses were conducted to identify potential moderators. Results: The quality of the included 17 articles ranged between "probably low" and "high risk of bias." A significant reduction in tumor growth in exercising animals compared to controls was detected (Hedges' g = -0.40; 95% CI -0.66 to -0.14, p < 0.01) with between-study heterogeneity (τ² = 0.217, I ² = 70.28%, p < 0.001). The heterogeneity was partially explained by three moderators representing the in-between group differences of "maximum daily exercise" R ² = 33% (p < 0.01), "type of cancer administration" R ² = 28% (p < 0.05), and "training initiation" R ² = 27% (p < 0.05). Conclusion: This meta-analysis suggests that physical exercise leads to reduction of tumor size in rodents. Since "maximum daily exercise" was found to have at least modest impact on tumor growth, more clinical trials investigating dose-response relationships are needed.

Keywords: cancer; physical exercise; rodent models; training initiation; tumor growth.

Figure 1

Study selection flow chart according to the PRISMA guidelines.

Figure 2

Funnel Plot of standard error against hedges' g after Duval and Tweedie's trim and fill.

Figure 3

Sensitivity analysis “one study removed” function, of the “comprehensive meta-analysis” program.

Figure 4

Meta-analysis of tumor software output presenting Hedges's g, 95% CI (confidence interval) and p-value of the random effect model of tumor size. The size of the squares and the thickness of the horizontal lines express the weight of the presented study. The total Hedges' g effect size is presented as green diamond. Its width expresses the CI. The vertical line at zero represents no difference in adjusted effect size of exercise on tumor growth. Data on the left from the line stands for a decrease and data on the right stands for an increase of tumor size. The heterogeneity was calculated and was shown to be at the end range of moderate [I² = 70.28%; Q = 60.57; df(Q) = 18; p < 0.00].

Figure 5

Adjusted effect sizes of the investigated groups tested by the predefined moderators, k, number of studies in the subgroup; I², measure of heterogeneity.