Identification of Lipid Metabolism-Related Genes in Rheumatoid Arthritis Using Bioinformatics and Machine Learning

Background Rheumatoid arthritis (RA) is a common autoimmune inflammatory joint disease. Recent studies suggest that lipid metabolism dysregulation plays a crucial role in RA pathogenesis; however, its precise mechanisms remain unclear. This study aims to identify lipid metabolism-related diagnostic biomarkers in RA and analyze their potential pathogenic mechanisms and clinical significance. Methods Multiple RA-related microarray datasets (GSE206848, GSE77298, GSE55235, GSE55584, and GSE55235) were obtained from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) were identified using the “limma” R package. Weighted gene co-expression network analysis (WGCNA) was performed to identify key module genes associated with RA. Two machine learning algorithms, least absolute shrinkage and selection operator (LASSO) and random forest (RF), were used to screen hub genes closely related to synovial lipid metabolism in RA. A nomogram and receiver operating characteristic (ROC) curve were constructed to predict RA risk. Additionally, immune cell infiltration was analyzed, followed by single-sample gene set enrichment analysis (ssGSEA) and validation in an independent dataset. Results PIK3CD was identified as a key gene with strong diagnostic value for RA. Abnormal immune cell infiltration was observed in RA patients and was positively correlated with PIK3CD expression. Conclusion These findings suggest that PIK3CD is involved in RA-related lipid metabolism and may serve as a reliable diagnostic biomarker and potential therapeutic target for RA.