Building a Risk Scoring Model for ARDS in Lung Adenocarcinoma Patients Using Machine Learning Algorithms

ABSTRACT

Lung adenocarcinoma (LUAD), the predominant form of non‐small‐cell lung cancer, is frequently complicated by acute respiratory distress syndrome (ARDS), which increases mortality risks. Investigating the prognostic implications of ARDS‐related genes in LUAD is crucial for improving clinical outcomes. Data from TCGA, GEO and GTEx were used to identify 276 ARDS‐related genes in LUAD via differential expression analysis. Univariate Cox regression, consensus clustering and machine learning algorithms were used to develop a prognostic risk scoring model. Functional enrichment, immune infiltration analyses, copy number variations and mutational burdens were examined, and the results were validated at the single‐cell level. ARDS‐related genes significantly impact the prognosis of LUAD patients. A machine learning‐based risk scoring model accurately predicted survival rates. Functional enrichment and immune infiltration analyses revealed that these genes are primarily involved in cell cycle regulation and immune cell infiltration. Single‐cell expression data supported these findings, and the assessments of copy number variations and mutational burdens highlighted distinct genetic characteristics. This study establishes the prognostic relevance of ARDS‐associated genes in LUAD and provides potential biomarkers for personalized therapy and prognosis. Future studies will validate these findings and explore their clinical applications.