Objective Lung cancer is the most common malignancy worldwide and exhibits both high morbidity and mortality. In recent years, scientists have made substantial breakthroughs in the early diagnosis and treatment of lung adenocarcinoma (LUAD), however, patient prognosis still shows vast individual differences. In this study, bioinformatics methods were used to identify and analyze ferroptosis-related genes to establish an effective signature for predicting prognosis in LUAD patients. Methods The gene expression profiles of LUAD patients with complete clinical and follow-up information were downloaded from two public databases, univariate Cox regression and multivariate Cox regression analysis were used to obtain ferroptosis-related genes for constructing the prognos tic risk model, AUC and calibration plot were used to evaluate the predictive accuracy of the FRGS and nomogram. Results A total of 74 ferroptosis-related differentially expressed genes (DEGs) were identi fied between LUAD and normal tissues from The Cancer Genome Atlas (TCGA) database. A five-gene panel for prediction of LUAD prognosis was established by multivariate regression and was verified using the GSE68465 cohort from the Gene Expression Omnibus (GEO) database. Patients were divided into two different risk groups according to the median risk score of the five genes. Based on Kaplan-Meier (KM) analysi, the OS rate of the high-risk group was markedly worse than that of the low-risk group. We also found that risk score was an independent prognostic indicator. The receiver operating characteristic ROC curve showed that the proposed model had good prediction ability. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) functional analyses indicated that risk score was prominently enriched in ferroptosis processes. Moreover, at the score of immune-associated gene sets, significant differences were found between the two risk groups. Conclusions This study demonstrated that ferroptosis-related gene signatures can be used as a potential predictor for the prognosis of LUAD, thus providing a novel strategy for individualized treatment in LUAD patients.