Alzheimer’s disease is a neurodegenerative disorder and the most common form of dementia. Early diagnosis may assist interventions to delay onset and reduce the progression rate of the disease. We systematically reviewed the use of machine learning algorithms for predicting Alzheimer’s disease using single nucleotide polymorphisms and instances where these were combined with other types of data. We evaluated the ability of machine learning models to distinguish between controls and cases, while also assessing their implementation and potential biases. Articles published between December 2009—June 2020 were collected using Scopus, PubMed and Google Scholar. These were systematically screened for inclusion leading to a final set of 12 publications. Eighty-five percent of the included studies used the Alzheimer's Disease Neuroimaging Initiative dataset. In studies which reported area under the curve, discrimination varied (0.49–0.97). However, more than half of the included manuscripts used other forms of measurement such as accuracy, sensitivity and specificity. Model calibration statistics were also found to be reported inconsistently across all studies. The most frequent limitation in the assessed studies was sample size, with the total number of participants often numbering less than a thousand, whilst the number of predictors usually ran into the many thousands. In addition, key steps in model implementation and validation were often not performed or unreported, making it difficult to assess the capability of machine learning models.

Background: The rate of cognitive decline in Alzheimer’s disease (AD) has been found to vary widely between individuals, with numerous factors driving this heterogeneity. Objective: This study aimed to compute a measure of cognitive decline in patients with AD based on clinical information and to utilize this measure to explore the genetic architecture of cognitive decline in AD. Methods: An in-house cohort of 616 individuals, hereby termed the Cardiff Genetic Resource for AD, as well as a subset of 577 individuals from the publicly available ADNI dataset, that have been assessed at multiple timepoints, were used in this study. Measures of cognitive decline were computed using various mixed effect linear models of Mini-Mental State Examination (MMSE). After an optimal model was selected, a metric of cognitive decline for each individual was estimated as the random slope derived from this model. This metric was subsequently used for testing the association of cognitive decline with apolipoprotein E (APOE) genotype. Results: No association was found between the number of APOE ɛ2 or ɛ4 alleles and the rate of cognitive decline in either of the datasets examined. Conclusion: Further exploration is required to uncover possible genetic variants that affect the rate of decline in patients with AD.

No abstract