Artificial intelligence-driven multiple sclerosis diagnosis using genomic and medical imaging data: a review

Abstract

Multiple Sclerosis (MS) is an immune-mediated central nervous system condition with heterogeneous clinical manifestations, progressive neurodegeneration, and considerable variability in disease trajectory. Recent advances in artificial intelligence (AI), particularly machine learning (ML) methods, have improved MS diagnosis and risk prediction. However, comprehensive review studies emphasizing the potential of existing AI-powered MS diagnosis remain limited. Thus, this study investigates the utilization of multimodal data by AI models to enhance diagnostic accuracy, evaluate disease progression, and optimize personalized care strategies. By adhering to PRISMA guidelines, this review included 26 studies encompassing MRI-based analysis, retinal OCT imaging, blood transcriptomics, SNP genotyping, and multimodal clinical datasets. An additional classification of these studies by modality was performed, and they were assessed with respect to dataset size, performance metrics, biomarkers, methodological robustness, and model interpretability. The findings indicate a consistent trend toward outstanding diagnostic performance, with some AI models achieving accuracies exceeding 95% using medical imaging and genomic data. However, limited external validation and interpretability procedures create a gap in clinical applicability and trustworthiness. This review highlights AI's growing potential to revolutionize MS diagnosis.