Objectives The associations between the neutrophil-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) with the responses of non-small cell lung cancer (NSCLC) patients receiving immune checkpoint inhibitors (ICI) and the NLR/PLR predictive potential were evaluated via meta-analysis. Methods A systematic review was conducted using the PubMed, Embase, and The Cochrane Library databases until October 2021. The relationship between NLR/PLR and overall survival (OS) and progression-free survival (PFS) was evaluated using pooled hazard ratios (HR). The relationship between NLR/PLR and overall response rate (ORR) and disease control rate (DCR) was assessed via pooled odds ratios (OR). Heterogeneity between studies, publication bias, subgroup and sensitivity analyses, trim and fill meta-analysis, and the contour-enhanced funnel plot were performed using the R software. Results A total of 44 (out of 875) studies met the eligibility criteria, providing a sample size of 4597 patients. Patients with a high NLR were statistically significantly associated with worse outcomes, including OS (pooled HR = 2.44; P < 0.001), PFS (pooled HR = 2.06; P < 0.001), DCR (pooled OR = 0.71; P < 0.001), and ORR (pooled OR = 0.33; P < 0.001). Similarly, a high PLR was associated with poorer outcomes in response to ICI drugs, including OS (pooled HR = 2.13; P < 0.001) and PFS (pooled HR = 1.61; P < 0.001). Conclusion High NLR and PLR were associated with a statistically significant reduction in the efficacy of ICI drugs in NSCLC patients. Thereby, it is possible to use NLR and PLR as potential and available biomarkers in the clinical practice to predict the outcome of ICI treatment in NSCLC patients.