Comparing the Artificial Intelligence Detection Models to Standard Diagnostic Methods and Alternative Models in Identifying Alzheimer's Disease in At-Risk or Early Symptomatic Individuals: A Scoping Review

Alzheimer's disease (AD) and other neurodegenerative illnesses place a heavy strain on the world's healthcare systems, particularly among the aging population. With a focus on research from January 2022 to September 2023, this scoping review, which adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews (PRISMA-Scr) criteria, examines the changing landscape of artificial intelligence (AI) applications for early AD detection and diagnosis. Forty-four carefully chosen articles were selected from a pool of 2,966 articles for the qualitative synthesis. The research reveals impressive advancements in AI-driven approaches, including neuroimaging, genomics, cognitive tests, and blood-based biomarkers. Notably, AI models focusing on deep learning (DL) algorithms demonstrate outstanding accuracy in early AD identification, often even before the onset of clinical symptoms. Multimodal approaches, which combine information from various sources, including neuroimaging and clinical assessments, provide comprehensive insights into the complex nature of AD. The study also emphasizes the critical role that blood-based and genetic biomarkers play in strengthening AD diagnosis and risk assessment. When combined with clinical or imaging data, genetic variations and polygenic risk scores help to improve prediction models. In a similar vein, blood-based biomarkers provide non-invasive instruments for detecting metabolic changes linked to AD. Cognitive and functional evaluations, which include neuropsychological examinations and assessments of daily living activities, serve as essential benchmarks for monitoring the course of AD and directing treatment interventions. When these evaluations are included in machine learning models, the diagnosis accuracy is improved, and treatment monitoring is made more accessible. In addition, including methods that support model interpretability and explainability helps in the thorough understanding and valuable implementation of AI-driven insights in clinical contexts. This review further identifies several gaps in the research landscape, including the need for diverse, high-quality datasets to address data heterogeneity and improve model generalizability. Practical implementation challenges, such as integrating AI systems into clinical workflows and clinician adoption, are highlighted as critical barriers to real-world application. Moreover, ethical considerations, particularly surrounding data privacy and informed consent, must be prioritized as AI adoption in healthcare accelerates. Performance metrics (e.g., sensitivity, specificity, and area under the curve (AUC)) for AI-based approaches are discussed, with a need for clearer reporting and comparative analyses. Addressing these limitations, alongside methodological clarity and critical evaluation of biases, would strengthen the credibility of AI applications in AD detection. By expanding its scope, this study highlights areas for improvement and future opportunities in early detection, aiming to bridge the gap between innovative AI technologies and practical clinical utility.