This study aims to explore the role of angiogenesis-related genes in chronic lung diseases (ILD and COPD) using bioinformatics methods, with the goal of identifying novel therapeutic targets to slow disease progression and prevent its deterioration into fibrosis or pulmonary artery hypertension. The research methods encompassed differential analysis, WGCNA (Weighted Gene Co-expression Network Analysis), and multiple machine learning approaches to screen for key genes. Gene Set Enrichment Analysis (GSEA), Gene Ontology (GO), and the Kyoto Encyclopedia of Genes and Genomes (KEGG) were utilized to assess related biological functions and pathways. Additionally, immune cell infiltration was analyzed to evaluate the immune status of the disease and the correlation between genes and immunity. COPD and ILD are closely associated with pathways related to angiogenesis, immune responses, and others, with differential genes in both groups linked to inflammation-related signaling pathways. The study established a chronic lung disease-related gene set comprising 171 genes and further screened out 21 genes related to angiogenesis. Ultimately, four key genes-, , , and -were identified through machine learning methods. These four genes are closely related to angiogenesis and immune processes, and clustering analysis based on them can reflect different disease states and variations in immune cell infiltration. , , , and represent potential therapeutic targets for slowing the progression of chronic lung diseases and preventing their deterioration. Furthermore, monocytes exhibited consistent infiltration patterns across disease and control groups, as well as among different subgroups, suggesting their potential significant role in the development of chronic lung diseases.