Objectives This systematic review aimed to evaluate the current literature regarding the importance of discontinuing or not discontinuing direct oral anticoagulants (DOACs) before invasive oral procedures, and to establish the frequency and type of postoperative bleeding events in patients. Material and Methods We searched PubMed, Embase, Scopus, Web of Science, and the Cochrane Library up until November 5, 2018. Selection of the studies, extraction of data, qualitative, and bias assessment was performed independently by two authors. Results Twenty-one studies were included. No randomized controlled studies were identified. Six studies reported a direct comparison between patients taking DOACs and those who discontinued DOACs. The meta-analysis of these studies resulted in an OR of 0.92 (95% CI = 0.37-2.27, I-2 = 9%) for postoperative bleeding events for patients taking DOACs. We found that 59/497 (11.8%) postoperative bleeding events occurred in patients who continued DOACs, while 27/200 (13.5%) events were reported for patients who discontinued treatment. All postoperative bleeding events were controlled with local measures. Conclusion Results from the included studies did not discern any important differences in postoperative bleeding events in patients who continued versus patients who discontinued DOACs. Furthermore, no thromboembolic events were recorded. However, the low quality of the studies must be considered.