ObjectiveTo evaluate the efficacy of different non-pharmacological interventions on cognitive function in elderly patients with mild cognitive impairment by the network meta-analysis. MethodsThe PubMed, Embase, Cochrane Library, CINAHL, CNKI, WanFang Data, VIP and CBM databases were electronically searched to collect randomized controlled trials (RCTs) related to the objectives from inception to November 2022. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. The network meta-analysis was then performed by using Stata 16.0 and Open BUGS 3.2.3 software. ResultsA total of 43 RCTs involving 2 986 patients were included, which involved 8 non-drug intervention methods. The best probability ranking results of the network meta-analysis showed that on the simple mental state scale (MMSE) scores: rTMS > acupressure > acupuncture therapy > exercise therapy > cognitive training > multicomponent intervention > VR > conventional care > health education, and on the Montreal cognitive assessment scale (MoCA) scores: VR > exercise therapy > rTMS > acupuncture therapy > acupressure > cognitive training > health education > conventional care. Conclusion Current evidence shows that rTMS, acupressure, VR, exercise therapy and acupuncture may be effective interventions to improve cognitive function in elderly patients with mild cognitive impairment. Due to the limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion.