Identification of mitophagy-related biomarkers in human rheumatoid arthritis using machine learning models

Rheumatoid arthritis (RA) is a systemic immune-mediated disease characterized by synovitis and joint cartilage destruction. Although many studies have shown that mitophagy is crucial in the development of bone metabolism disorders, its exact function in rheumatoid arthritis (RA) is still not well understood. This study analysed the GSE77298 dataset from the Gene Expression Omnibus (GEO) to identify differentially expressed genes (DEGs) between rheumatoid arthritis (RA) patients and healthy controls. Mitophagy-related genes (MRGs) were extracted from the literature and screened using bioinformatics techniques, resulting in differentially expressed MRGs (DE-MRGs). The diagnostic value of these genes was assessed using receiver operating characteristic (ROC) curves, and an ANN model was constructed. In the GSE77298 dataset, 267 differentially expressed genes (DEGs) were identified. Weighted gene co-expression network analysis (WGCNA) identified 2191 key module genes, leading to 63 DE-MRGs. Two MRGs, TMEM45A and ZBTB25, were identified as hub genes with areas under the curve (AUC) of 0.991 and 0.911, respectively. The nomogram model demonstrated high diagnostic value. Mitophagy plays a critical role in the progression of rheumatoid arthritis (RA). Identifying two genes associated with mitophagy may aid in the early diagnosis, mechanistic understanding, and treatment of RA.