Background: Gastrointestinal bleeding (GIB) commonly complicates anticoagulant therapy for patients with atrial fibrillation (AF). However, AF patients with prior GIB were excluded from most randomized controlled trials on anticoagulation therapy. Therefore, we conducted a systematic review and meta-analysis to assess the effect of oral anticoagulant (OAC) therapy in this specific population. Methods: Randomized trials and observational studies reporting the data about the resumption of OAC therapy among AF patients with prior GIB were included. The search was performed in the PubMed and Embase databasesup to March 2022. The adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) were pooled by a random-effects model with an inverse variance method. Results: A total of 7 studies involving 57,623 patients were included. Compared with no anticoagulant therapy, OAC therapy was associated with decreased risks of stroke or systemic embolism (HR = 0.71, 95% CI: 0.59-0.84) and all-cause death (HR = 0.66, 95% CI: 0.60-0.72), but there was no significant difference in the risk of recurrent GIB (HR = 1.22, 95% CI: 0.94-1.59). Compared with vitamin K antagonists, non-vitamin K antagonist oral anticoagulants (NOACs) were associated with reduced risks of stroke or systemic embolism (HR = 0.61, 95% CI: 0.54-0.68), all-cause mortality (HR = 0.86, 95% CI: 0.75-0.99), major bleeding (HR = 0.75, 95% CI: 0.66-0.84), and GIB recurrence (HR = 0.83, 95% CI: 0.72-0.96). Conclusions: In AF patients with prior GIB, OAC therapy (especially NOACs) demonstrated superior effectiveness compared with no anticoagulant therapy.