Artificial Intelligence models in autoimmune disease prediction: Current applications, challenges, and future perspectives

Autoimmune diseases are heterogeneous immune-mediated disorders characterized by loss of immunological tolerance, autoantibody production, variable clinical manifestations, and unpredictable disease progression. These features make early diagnosis, risk stratification, and treatment-response prediction challenging using conventional clinical assessment alone. Artificial intelligence has emerged as a promising approach for improving autoimmune disease prediction through the analysis of complex and multidimensional healthcare data. This narrative review summarizes current applications of artificial intelligence models in autoimmune disease prediction, with emphasis on machine learning, deep learning, natural language processing, computer-aided diagnosis, and predictive modeling. Relevant literature was reviewed to describe major AI models, data sources, disease-specific applications, image-based diagnostic systems, challenges, and future perspectives. AI-based prediction in autoimmune diseases commonly uses clinical data, electronic health records, genomic and proteomic profiles, imaging data, and wearable-device outputs. These approaches have been applied in rheumatoid arthritis, systemic lupus erythematosus, multiple sclerosis, type 1 diabetes, autoimmune liver diseases, Sjögren’s syndrome, and celiac disease to support diagnosis, patient stratification, disease monitoring, treatment-response prediction, and personalized management. However, clinical implementation remains limited by small datasets, disease heterogeneity, lack of external validation, privacy concerns, interpretability issues, and integration barriers. Overall, artificial intelligence may strengthen precision medicine in autoimmune diseases, but its routine clinical use requires validated, explainable, and ethically implemented models supported by multidisciplinary collaboration.