JMIR Publications

ABSTRACT

Background:

Alzheimer's Disease (AD) is diagnosed by categorizing individuals based on the severity of cognitive impairment. At the present time, there is no specific cause or condition for this disease.

Objective:

This systematic review and meta-analysis aimed to comprehensively assess AD prevalence across different stages utilizing machine learning (ML) approaches.

Methods:

According to PRISMA 2020 guidelines, articles were selected in three phases: identification, screening, and final inclusion. For the final analysis, we selected 24 articles that met the criteria. ML approaches for AD diagnosis were rigorously selected based on their relevance to the investigation. Forest plots were used to depict the prevalence of AD subjects at two, three, four, and six stages.

Results:

Six studies focused on two stages (Cognitively Normal [CN] and AD) and reported a pooled prevalence of 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 14839 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 3819 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:

AD prevalence estimates are influenced by demographic and setting characteristics, as evidenced by the substantial heterogeneity observed across studies. This study illustrates the efficacy of ML approaches in describing AD prevalence across varied stages, providing valuable insights for future research.