Identifying Effective Immune Biomarkers in Alopecia Areata Diagnosis Based on Machine Learning Methods

This study utilized machine learning to identify three key immune biomarkers, SKAP1, PIK3CG, and CD8A, for diagnosing alopecia areata (AA), an autoimmune disorder causing patchy hair loss. These biomarkers were found to be highly expressed in AA patients and are associated with immune responses, particularly T cell activation and differentiation. The study achieved high diagnostic accuracy (AUC = 0.941) with a nomogram model, highlighting CD8A's significant role in AA pathogenesis due to its high specificity and sensitivity. The findings, validated with additional datasets and clinical samples, suggest these biomarkers can improve early diagnosis and treatment strategies for AA, despite limitations such as limited clinical data and the need for further validation.