Construction of Regulatory Network for Alopecia Areata Progression and Identification of Immune Monitoring Genes Based on Multiple Machine-Learning Algorithms

The study aimed to improve early identification and intervention for patients with alopecia areata (AA) at risk of progressing to severe forms such as total alopecia (AT) or generalized alopecia (AU). Researchers analyzed two AA-related datasets, identified 150 differentially expressed genes (DEGs) associated with severe AA, and used weighted gene co-expression network analysis to find module genes linked to severe AA. They conducted functional enrichment analysis, built a protein-protein interaction network, and analyzed immune cell infiltration to understand the biological mechanisms of severe AA. Multiple machine-learning algorithms were employed to identify four pivotal immune monitoring genes (IMGs)—LGR5, SHISA2, HOXC13, and S100A3—with good diagnostic efficiency. LGR5, a gene associated with hair follicle stem cell stemness, was found to be downregulated in severe AA. These findings offer a comprehensive understanding of AA pathogenesis and present four potential IMGs that could aid in the early diagnosis of severe AA.