OBJECTIVE: To evaluate the predictive value of hematological biomarkers in assessing the risk of immune-related adverse events (irAEs) in non-small cell lung cancer (NSCLC) patients undergoing immunotherapy and to identify potential risk factors for personalized treatment optimization. METHODS: Clinical data of 274 NSCLC patients who received immunotherapy between April 2018 and January 2021 were retrospectively analyzed. Patients were divided into irAEs and non-irAEs groups based on the occurrence of irAEs. Peripheral blood indices within one week before treatment initiation were assessed and compared, including absolute neutrophil count (ANC), lymphocyte count (LYM), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), albumin-to-alkaline phosphatase ratio (AAPR), and albumin-to-fibrinogen ratio (AFR). Kaplan-Meier analysis compared overall survival (OS) and progression-free survival (PFS), while logistic regression identified independent risk factors for irAEs. Receiver operating characteristic (ROC) curve analysis evaluated predictive performance. RESULTS: Among the 274 patients, 116 (42.2%) developed irAEs. Compared to the non-irAEs group, the irAEs group exhibited significantly higher ANC, NLR, PLR, and SII, along with lower LYM, AAPR, and AFR as well as lower OS and PFS rates (all P < 0.05). Logistic regression showed that all hematological indicators were independent risk factors for irAEs (P < 0.05). ROC analysis showed an AUC of 0.722 for NLR and 0.829 for the combined model. CONCLUSION: Pretreatment assessment of ANC, LYM, NLR, PLR, SII, AAPR, and AFR provides valuable predictive utility for irAEs risk in NSCLC patients undergoing immunotherapy. Integrating these biomarkers into clinical practice may enhance risk stratification and guide personalized treatment strategies to improve safety and therapeutic outcomes.