Application of Artificial Intelligence on Neurodegenerative Disorder Care: A Scoping Review

Introduction: Neurodegenerative Disorders (NDs), which are progressive conditions characterized by the gradual loss of structure or function of neurons, including Alzheimer’s disease, Parkinson’s disease, Huntington’s disease, and amyotrophic lateral sclerosis, present escalating global health challenges. Traditional diagnostic and therapeutic approaches are often delayed, subjective, and insufficiently personalized. The rapid development of Artificial Intelligence (AI) offers new opportunities to enhance early detection, treatment personalization, and care support through advanced data-driven methods. This review aimed to explore the current applications of AI in ND diagnosis and management.    
Methods: A scoping review was conducted following Arksey and O’Malley’s framework, and reported in line with PRISMA-ScR guidelines. Literature searches were performed across PubMed, ScienceDirect, and Google Scholar, limited to English-language publications from 2015 to 2025. Eligible studies focused on AI applications in ND. A two-stage screening and thematic synthesis were employed, and findings were validated through expert consultation.  
Results:  Out of 333 articles identified, 15 studies met the inclusion criteria. Three main application domains emerged: (1) diagnostic applications using neuroimaging, biomarkers, and wearable data, achieving high accuracy in early disease detection; (2) treatment personalization and progression modeling, including digital twin frameworks and physics-informed neural networks; and (3) AI-driven assistive technologies, such as memory companions and augmented reality–based care support systems. Despite promising results, challenges remain in data standardization, interpretability, and clinical integration. 
Conclusion: AI demonstrates transformative potential in ND care, especially in diagnostics and personalized interventions. However, translation into routine clinical practice requires rigorous validation, ethical considerations, and interdisciplinary collaboration. Future research should prioritize multimodal data integration, transparent models, and patient-centered applications to ensure scalable and equitable adoption.