Background: Regulatory T cells (Tregs) researches in systemic lupus erythematosus (SLE) have floundered over the years, reports on the numbers and function of Tregs in SLE present quite contradictory results. We therefore conducted a meta-analysis to verify the changes of Tregs in active SLE. Methods: We systematically searched PubMed, Embase, and ISI web of knowledge databases for eligible articles. In total, 628 active SLE patients and 601 controls from 18 studies were included. Due to a high degree of heterogeneity, a random effects model was used to assess the mean differences in Treg percentages, absolute numbers, and suppression capacities of Tregs between active SLE and controls. Further, subgroup analysis was performed to identify potential sources of heterogeneity. Results: The pooled percentages of Tregs in active SLE patients were found to be lower than those in controls (-0.864 +/- 0.308, p = 0.005), with great heterogeneity (I-2 = 95.01). The discrepancy of published results might result from the following differences among studies: gating strategies for Tregs, diagnostic criteria for SLE, and thresholds of SLEDAI chosen to differentiate between active and inactive SLE. In active SLE, Tregs gated based on CD25 alone showed lower pooled frequency than those gated by Foxp3(+) or CD127(low/(SIC)). The percentages of Tregs in active SLE was significantly lower than that in controls when the enrolled SLE patients were diagnosed according to the 1997 modified criteria, whereas they were comparable to controls when diagnosed by the 1982 criteria; the higher threshold of SLEDAI score used to define active SLE tended to achieve a lower percentage of Tregs. The pooled absolute numbers of Tregs in active SLE were significantly decreased compared to those in controls (-1.328 +/- 0.374, p < 0.001), but seemed to be unaffected by gating strategies. Suppression capacities of Tregs from active SLE patients showed no abnormalities based on the limited pooled data. Longitudinal monitoring of active SLE showed a significant decrease in Treg percentage at remission. Conclusions: This study implies that loss of Tregs may play a role in the pathogenesis of active SLE and help clarify contradictory Treg results in SLE.