Leveraging Machine Learning For Predictive Modelling in Alzheimer´s Disease

Abstract

"Alzheimer’s disease (AD)’s complex aetheology results in a lack of effective therapies. Studies have suggested the possible involvement of infectious agents and dysregulated inflammation in its pathogenesis. Advances in Machine Learning (ML) permitted the integration and analysis of high-dimensional heterogenous data, uncovering intricate relationships and new disease biomarkers. In this dissertation ML models- including linear and logistic regression, Decision Trees (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Extreme Gradient Boosting (XGB), were deployed to predict AD, using Trained Immunity (TI), Infectious Burden (IB), and serum cytokine data, as well as to model TI data itself, predicting levels of TNF𝛼, IL-6, IL-10, IL-1𝛽 and IL-1RA in response to different infectious stimuli.(...)"