Abstract: The study aimed to identify reliable prognostic features with immune-related genes that could predict prognosis and aid in the individualized management of patients with LUAD. The mRNA expression profiles of LUAD patients and corresponding clinical data were downloaded from The Cancer Genome Atlas（TCGA） database. One-way COX and LASSO regression models were used to identify prognostic genes. Prognostic features were developed using a risk score-based approach. Overall survival（OS） was compared between high-and low-risk patients by Kaplan-Meier analysis. Independent predictors of OS were determined by univariate and multivariate COX analyses. Single sample gene set enrichment analysis（ssGSEA） was used to assess the degree of immune cell infiltration. Prognostic characteristics were constructed by LASSO and COX regression analysis. Prognostic characteristics significantly stratified patients into high-and low-risk groups in terms of OS, with significantly lower OS in LUAD patients in the high-risk group compared with the low-risk group. The predictive power of prognostic genetic markers was confirmed by ROC curve analysis. Multifactorial COX analysis showed that risk score was an independent predictor of OS. Immunological analysis revealed different immune profiles in the metastatic and non-metastatic groups of lung adenocarcinoma. Inter-mapping with the Coremine Medical database screened 15 herbal medicines such as Niuhuang（Bovis Calculus） and Luohanguo（Siraitia Fructus）. Our study proposed a new prognostic profile of lung adenocarcinoma for estimating overall survival in LUAD. In addition, identified differences in immune profiles between the metastatic and non-metastatic groups of lung adenocarcinoma. This study may be useful for more accurate survival risk stratification and individualized clinical management for patients with LUAD.