Objective To systematically review the efficacy and safety of immune checkpoint inhibitors combined with chemotherapy in the treatment of triple-negative breast cancer. Methods The PubMed, Cochrane Library, Embase, Web of Science, CNKI, WanFang Data and VIP databases were searched for randomised controlled trials (RCTs) of immune checkpoint inhibitors combined with chemotherapy versus chemotherapy alone for triple-negative breast cancer from inception to 1 April, 2024. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias of the included studies. Meta-analysis was then performed by using RevMan 5.4 software. Results A total of 13 RCTs involving 5 416 patients were included. The results of meta-analysis showed that the pathologic complete response rate (pCR) (OR=2.09, 95%CI 1.37 to 3.19, P<0.01), progression-free survival (PFS) (HR=0.75, 95%CI 0.67 to 0.83, P<0.01) and overall survival (OS) (HR=0.85, 95%CI 0.76 to 0.94, P<0.01) were significantly better than those in the control group. The results of subgroup analysis showed that there were statistically significant differences in PFS (HR=0.79, 95%CI 0.72 to 0.87, P<0.01) and OS (HR=0.88, 95%CI 0.79 to 0.98, P=0.02) between PD-L1-positive and PD-L1-negative patients, but there was no statistically significant difference in pCR (OR=1.63, 95%CI 1.32 to 2.02, P=0.36) between PD-L1-positive patients and PD-L1-negative patients. There was a statistically significant difference in pCR between node-positive patients and node-negative patients (OR=1.81, 95%CI 1.38 to 2.37, P=0.03). There was no statistically significant difference in pCR between patients treated with PD-1 inhibitors and PD-L1 inhibitors (OR=2.09, 95%CI 1.37 to 3.19, P=0.32); and there was no significant difference in PFS (HR=0.75, 95%CI 0.67 to 0.83, P=0.19) and OS (HR=0.87, 95%CI 0.79 to 0.96, P=0.99) between patients treated with PD-1 inhibitors and PD-L1 inhibitors. Compared with the control group, the incidence of serious adverse events (RR=1.36, 95%CI 1.09 to 1.70, P<0.01) and immune-related adverse events (RR=2.98, 95%CI 1.66 to 5.35, P=0.03) was higher in the experimental group, and the common immune-related adverse events were hypothyroidism and hyperthyroidism. Conclusion The existing evidence shows that immune checkpoint inhibitors combined with chemotherapy are more effective than chemotherapy alone in the treatment of triple-negative breast cancer, and the combination therapy has a higher incidence of adverse reactions. Due to the limited quantity and quality of the included studies, more high-quality studies are needed to verify the above conclusion.