Background: Low bone mineral density (BMD) and subsequent fractures are a major public health problem in postmenopausal women. The purpose of this study was to use the aggregate data meta-analytic approach to examine the effects of ground (for example, walking) and/or joint reaction (for example, strength training) exercise on femoral neck (FN) and lumbar spine (LS) BMD in postmenopausal women. Methods: The a priori inclusion criteria were: (1) randomized controlled trials, (2) exercise intervention >= 24 weeks, (3) comparative control group, (4) postmenopausal women, (5) participants not regularly active, i.e., less than 150 minutes of moderate intensity (3.0 to 5.9 metabolic equivalents) weight bearing endurance activity per week, less than 75 minutes of vigorous intensity (> 6.0 metabolic equivalents) weight bearing endurance activity per week, resistance training < 2 times per week, (6) published and unpublished studies in any language since January 1, 1989, (7) BMD data available at the FN and/or LS. Studies were located by searching six electronic databases, cross-referencing, hand searching and expert review. Dual selection of studies and data abstraction were performed. Hedge's standardized effect size (g) was calculated for each FN and LS BMD result and pooled using random-effects models. Z-score alpha values, 95% confidence intervals (CI) and number-needed-to-treat (NNT) were calculated for pooled results. Heterogeneity was examined using Q and gamma(2). Mixed-effects ANOVA and simple meta-regression were used to examine changes in FN and LS BMD according to selected categorical and continuous variables. Statistical significance was set at an alpha value <= 0.05 and a trend at >0.05 to <= 0.10. Results: Small, statistically significant exercise minus control group improvements were found for both FN (28 g's, 1632 participants, g = 0.288, 95% CI = 0.102, 0.474, p = 0.002, Q = 90.5, p < 0.0001, gamma(2) = 70.1%, NNT = 6) and LS (28 g's, 1504 participants, g = 0.179, 95% CI = -0.003, 0.361, p = 0.05, Q = 77.7, p < 0.0001, gamma(2) = 65.3%, NNT = 6) BMD. Clinically, it was estimated that the overall changes in FN and LS would reduce the 20-year relative risk of osteoporotic fracture at any site by approximately 11% and 10%, respectively. None of the mixed-effects ANOVA analyses were statistically significant. Statistically significant, or a trend for statistically significant, associations were observed for changes in FN and LS BMD and 20 different predictors. Conclusions: The overall findings suggest that exercise may result in clinically relevant benefits to FN and LS BMD in postmenopausal women. Several of the observed associations appear worthy of further investigation in well-designed randomized controlled trials.
