Non-small cell lung cancer (NSCLC) is one of the most common life-threatening malignant tumors. A test for early diagnosis of NSCLC needs to be not too invasive and not too heavy a burden for weakened patients. A series of studies reported various microRNAs (miRNAs) could be novel serum biomarkers for NSCLC. However, the diagnostic ability of different miRNA biomarkers varies among the reports. The goal of this study was to perform a systematic review to examine the effect of miRNAs on NSCLC-related outcomes. We systematically searched The Cochrane Central Register of Controlled Trials, MEDLINE, Pub Med, EMBASE, the Chinese Biomedical Literature Database, the China Academic Journals Full-text Database, and the Chinese Scientific Journals Database for potential studies. Studies were included if they were related to miRNAs, NSCLC, and reported diagnostic outcomes. Diagnostic values analysis was used to summarize the overall test performance of miRNAs. 13 studies were included in this systematic review. The ranges of sensitivity (SEN) and specificity (SPE) of diagnosis model with miRNAs as identifying NSCLC were 0.69˜1.00 and 0.66˜1.00, respectively. The overall area under the curve (AUC) value of summary receiver operating characteristic (SROC) curve was 0.9151. The ranges of positive likelihood ratio (PLR) and negative likelihood ratio (NLR) were 2.33˜24.75 and 0.010.40, respectively. The range of diagnostic odds ratio (DOR) was 6.52˜983.38. The current evidence indicates that miRNAs in body fluids show high accuracy in identifying NSCLC, and could be a useful screening tool for diagnosing NSCLC patients.