An Epidemiological-based Regression Analysis of Alzheimer’s disease and Mild Cognitive Impairment Converts in the Female Population

Abstract

Detection and prediction of Alzheimer's Disease (AD) conversion from the stage of Mild Cognitive Impairment (MCI) have remained a challenging task. Regression analysis is a method that sorts those essential features/biomarkers that have a strong impact on the overall prediction. This study centres on delivering an individualized regression analysis of cognitively normal and MCI converts over the twenty independent biomarkers that leverage clinical data. Out of the 1713 male and female subjects, 768 female subjects were studied to investigate the prevalence of AD and MCI, those diagnosed with AD and MCI and their associated risk factors. The study data were gathered from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Twenty potential clinical features were included; comprised of a combination of demographic, cerebral spinal fluid, cognitive, diffusion tensor imaging, electroencephalography, genetic, magnetic resonance imaging, and positron emission tomography testing variables. The regression analysis metrics R-squared, F-statistic, Omnibus, Durbin-Watson, Coefficient and Standard error, were used to evaluate the model. Our results showed that cognitive assessment metrics were highly significant among the other testing biomarkers. Additionally, we determined the significance of each clinical variable. Our performed analysis could impact the clinical setting as a means to further develop a machine learning model in predicting the conversion of MCI to AD or to detect principle subjects for clinical trials.