AI-driven precision medicine for lysosomal storage disorders: Innovations in diagnosis and therapeutics

Lysosomal storage disorders (LSDs) are a diverse group of inherited metabolic diseases characterized by lysosomal dysfunction, leading to progressive multi-systemic complications. Despite advancements in next-generation sequencing, variant interpretation remains a major bottleneck with many mutations classified as variants of uncertain significance. Artificial intelligence (AI) is increasingly applied in rare disease research, diagnosis, and therapy by offering powerful solutions for pathogenicity prediction, multi-omics integration, biomarker discovery, imaging diagnostics, and precision medicine. This review explores AI-driven innovations in LSD research, including machine learning and deep learning models for variant classification, AI-powered electronic health record analysis for early detection, and radiomics for non-invasive disease monitoring. We highlight AI's role in optimizing enzyme replacement therapy, substrate reduction therapy, and drug repurposing, paving the way for personalized treatment strategies. Despite AI's impressive potential, challenges such as data heterogeneity, limited disorder-specific models, and ethical concerns remain. This review highlights key research gaps and proposes AI-driven solutions to revolutionize LSD diagnostics and treatment. By integrating AI with genomics and clinical practice, we aim to advance early detection, therapeutic precision, and patient outcomes in LSDs, setting the stage for the next era of rare disease management.