The aim of this study was to investigate the prognostic value of the prognostic nutritional index (PNI) on the long-term survival of non-small cell lung cancer (NSCLC) patients who received platinum-based chemotherapy. Data on nutritional parameters and clinicopathological characteristics [e.g., albumin, total protein, body mass index (BMI), eastern cooperative oncology group (ECOG) performance status, stage, pathology, treatment strategy] were analyzed and retrospectively correlated with overall survival (OS). The PNI was calculated based on the concentration of albumin and lymphocyte count [10 × albumin, (g/dl) + 0.005 × lymphocyte (count/mm3)]. A receiver operating characteristic curve (ROC) analysis was used to find the optimal cut-off value of PNI. Univariate and multivariate analyses were used to evaluate the prognostic value of PNI. A total of 186 patients met the inclusion criteria. The optimal cut-off value for PNI was 50.45. Compared with the parameters of the low PNI group (n=76), high PNI was significantly associated with adenocarcinoma type, stage III, better ECOG and comprehensive treatment modality. The univariate analysis demonstrated that OS was superior when PNI ≥50.45, albumin ≥35 g/l, platelet-lymphocyte ratio (PLR) ≥163 and ECOG <2, and when the patient received a comprehensive treatment modality. In the multivariate analysis, PNI, TNM stage and treatment strategy were identified as independent predictors of survival in this study. This retrospective study demonstrated that a low PNI was related to worse overall survival in patients with stage III/IV NSCLC who received platinum-based chemotherapy. These data provided a conceptual basis for further research on the clinical application of the PNI index for patients receiving chemotherapy for intermediate- and advanced-stage NSCLC.