Detection of dementia progression from functional activities data using machine learning techniques

Abstract

Early screening for Alzheimer’s disease (AD) is crucial for disease management, intervention, and healthcare resource accessibility. Medical assessments of AD diagnosis include the utilisation of biological markers (biomarkers), positron emission tomography (PET) scans, magnetic resonance imaging (MRI) images, and cerebrospinal fluid (CSF). These methods are resource intensive as well as physically invasive, whereas neuropsychological tests are fast, cost effective, and simple to administer for providing early AD diagnosis. However, neuropsychological assessments contain elements related to executive functions, memory, orientation, learning, judgment, and perceptual motor function (among others) that overlap, making it difficult to identify the key elements that trigger the progression of dementia or mild cognitive impairment (MCI). This research investigates the elements of the Functional Activities Questionnaire (FAQ) an early screening method using a data driven approach based on feature selection and classification. The aim is to determine the key items in the FAQ that may trigger AD advancement. To achieve the aim, real data observations of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) project have been processed using the proposed data driven approach. The results derived by the machine learning techniques in the proposed approach on data subsets of the FAQ items with demographics show models with accuracy, sensitivity, and specificity all exceeding 90%. In addition, FAQ elements including Administration and Shopping related activities showed correlations with the progression class; these elements cover four out of the six Diagnostic and Statistical Manual’s (DSM-5’s) neurocognitive domains.