Advancing Diagnosis and Therapy of Rare Monogenic Disorders through AI: Insights from Adrenoleukodystrophy

Background: Adrenoleukodystrophy (ALD) is a rare X-linked monogenic disorder caused by mutations in the ABCD1 gene, resulting in severe neurologica and adrenal dysfunction. Its phenotypic variability and diagnostic complexity hinder timely intervention. Objective: This review examines the role of artificial intelligence (AI) in improving the diagnosis, patient stratification, and therapeutic management of ALD, highlighting recent advances and challenges. Methods: We discuss AI models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Random Forest classifiers, focusing on their application to biomarker discovery, multi-omics integration, pathogenic variant identification, and disease modeling. The utility of AI in accelerating drug repurposing and enhancing CRISPRbased gene-editing strategies is also considered. Results: AI-driven approaches have enabled earlier and more accurate diagnosis of ALD, improved patient stratification, identified potential therapeutic targets, and optimized gene-editing techniques. Integration of clinical and high-throughput multi-omics data enhances predictive modeling and personalized intervention strategies. Challenges: Despite these advancements, limitations include small datasets, phenotypic heterogeneity, algorithmic opacity, and ethical concerns regarding AI deployment in rare disease management. Conclusion: AI has transformative potential for ALD and other rare monogenic disorders, providing tools for early diagnosis, precision therapy, and drug development. Future work should focus on expanding datasets, improving interpretability, and addressing ethical considerations to maximize clinical impact.