Dementia represents a major healthcare challenge, as pathological changes often occur years before overt symptoms. Early manifestations such as mild cognitive impairment (MCI) and subjective cognitive decline (SCD) represent critical transitional stages between normal aging and dementia. Thus, distinguishing these conditions (i.e., MCI and SCD) and determining their potential evolution into dementia remains crucial. However, current clinical tools, mainly neuroimaging and neuropsychological assessments, are not always clearly interpretable and are often resource-intensive. In recent years, artificial intelligence (AI), including machine learning (ML) and deep learning (DL), has demonstrated promising potential in early detection, progression prediction, and differential diagnosis of neurocognitive disorders. This systematic review aims to synthesize current evidence on the application of AI-based approaches to improve diagnostic accuracy and prognostic assessments in dementia. A comprehensive literature search of studies published between 2015 and 2025 was conducted across PubMed/MEDLINE, Scopus, and Web of Science, following PRISMA 2020 guidelines. Studies were evaluated for data modality, methodological rigor, performance metrics, and clinical applicability. Seventeen (17) studies, of which twelve (12) are primary studies and five (5) are secondary studies, examining AI applications in detecting and diagnosing neurocognitive disorders (NCDs) in adults with dementia, MCI, or SCD were included. Results indicate that AI models, particularly DL applied to neuroimaging, electrophysiological data, speech and language features, biomarkers, and digital behavioral data, achieve high diagnostic accuracy in distinguishing MCI, Alzheimer’s disease, and healthy aging. Predictive models also show potential in forecasting conversion from MCI to dementia and monitoring cognitive trajectories via wearable or smart-home technologies. Nonetheless, heterogeneity, limited external validation, and methodological inconsistencies hinder clinical translation. In conclusion, AI represents a rapidly evolving and promising tool for early detection and monitoring of neurocognitive disorders. Collectively, the reviewed studies underscore the need for standardized pipelines, larger multicenter datasets, and explainable AI frameworks to enable effective clinical implementation.
Perna et al. (Wed,) studied this question.