Abstract: Objective: To investigate the prognostic value of the albumin-corrected anion gap (ACAG) in advanced lung cancer patients receiving immune checkpoint inhibitors (ICIs). Methods: A total of 637 patients with advanced lung cancer who received ICIs treatment at two medical centers between January 2019 and October 2024 were enrolled. Baseline clinical data and laboratory parameters were collected, and the ACAG was calculated. The optimal prognostic cut-off value for ACAG (11.58 mmol/L) was determined using X-Tile software, and patients were divided into a low ACAG group (≤11.58 mmol/L) and a high ACAG group (>11.58 mmol/L). The primary endpoint was overall survival (OS), and the secondary endpoint was progression-free survival (PFS). Propensity score matching was performed to control for confounding factors. Survival curves were plotted using the Kaplan-Meier method. A Cox proportional hazards regression model was used to analyze prognostic factors, and subgroup analyses were conducted. Results: A total of 637 patients were included, and 440 patients remained in the matched cohort. Multivariate Cox analysis showed that after adjusting for clinical and laboratory parameters, ACAG >11.58 mmol/L was an independent risk factor for OS (HR=1.74, 95% CI: 1.02-2.98, P=0.044), but not an independent predictor for PFS. Stratified analysis further confirmed that ACAG >11.58 mmol/L was consistently associated with significantly shorter OS after adjusting for different sets of covariates. Survival curves demonstrated that the median OS in the high ACAG group (47.0 months) was significantly lower than that in the low ACAG group. Subgroup analysis indicated that the adverse predictive value of ACAG for OS was more pronounced in males, patients aged <65 years, and those with squamous cell carcinoma. Conclusion: In advanced lung cancer patients treated with ICIs, a higher baseline ACAG level (>11.58 mmol/L) is an independent risk factor for shorter OS, but it is not significantly associated with PFS. ACAG may serve as a simple and effective biological marker for assessing overall survival prognosis in advanced lung cancer patients undergoing immunotherapy.