Several recent studies have highlighted the potential benefits of using off-pump coronary artery bypass (OPCAB) surgery, particularly in high-risk patients. The aim of this meta-analysis is to assess the effect of OPCAB on the incidence of stroke compared with coronary artery bypass grafting using cardiopulmonary bypass (CPB) in elderly patients. We performed a meta-analysis of all observational studies, published in MEDLINE between 1999 and 2002 and a comparison between the OPCAB and CPB techniques in elderly patients was performed with the outcome of interest being the incidence of stroke. Elderly patients were defined as those aged 70 years or older. Nine studies are included in the meta-analysis. The total number of subjects included was 4,475 patients, of which, 1,253 underwent OPCAB (28%) and 3,222 (72%) underwent CPB. The meta-analysis showed that the OPCAB technique was associated with significantly lower incidence of stroke in elderly patients compared with the CPB technique (1% vs 3%), with an odds ratio of 0.38% to 95% (CI, 0.22 to 0.65). We did not identify any significant heterogeneity and funnel plot asymmetry between the studies included in the meta-analysis. Meta-regression analysis including variables predicting stroke, mortality, and study characteristics did not show any associations affecting the calculated odds ratio of stroke. Despite the fact that this is a meta-analysis of observational studies and adjustment for differences in baseline risk factors between OPCAB and CPB patients was not possible, we believe that this study suggests that the OPCAB technique might be associated with reduced incidence of stroke in the elderly patients undergoing coronary artery bypass grafting.