Machine Learning driven by MRI for the classification of Alzheimer's disease progression: systematic review and meta-analysis (Preprint)

Abstract

BACKGROUND To diagnose Alzheimer's disease (AD), individuals are classified according to the severity of their cognitive impairment. There are currently no specific causes or conditions for this disease. OBJECTIVE The purpose of this systematic review and meta-analysis was to assess AD prevalence across different stages using machine learning (ML) approaches comprehensively. METHODS The selection of articles was conducted in three phases, as per PRISMA 2020 guidelines: identification, screening, and final inclusion. The final analysis included 24 articles that met the criteria. The selection of ML approaches for AD diagnosis was rigorously based on their relevance to the investigation. The prevalence of AD subjects at two, three, four, and six stages was illustrated through the use of forest plots. RESULTS The prevalence rate for both Cognitively Normal [CN] and AD across six studies was 49.28% (95% CI: 46.12-52.45%, p=0.32). The prevalence estimate for the three stages of cognitive impairment (CN, MCI, and AD) is 29.75% (95% CI: 25.11-34.84%, p<0.01). Among five studies with 14,839 subjects, the analysis of four stages (ND, MoD, MD, and AD) found an overall prevalence of 13.13 percent (95% CI: 3.75-36.66%, p<0.01). In addition, four studies involving 3,819 subjects estimated the prevalence of six stages (CN, SMC, EMCI, MCI, LMCI, and AD), yielding a prevalence of 23.75 % (95% CI: 12.22-41.12%, p<0.01). CONCLUSIONS The significant heterogeneity observed across studies reveals that demographic and setting characteristics are responsible for the impact on AD prevalence estimates. This study shows how ML approaches can be used to describe AD prevalence across different stages, which provides valuable insights for future research. CLINICALTRIAL