The increased incidence of Alzheimer's disease (AD) and diabetes mellitus (DM) are emerging as major public health problems worldwide. Both sufferings share pathophysiological characteristics and have no cure. Inflammation of the central and peripheral nervous system has been shown to be the link between DM and AD. Oxidative stress is also associated with AD and DM. The increasing complexity of the problems and the continuous growth of information creates the need for the use of Decision Suport System (DSS) driven by the use of new technologies such as big data and machine learning. In this context, the objective of this work is to use decision trees and Bayesian networks as mechanisms of classification of AD gene expression levels, DM, inflammation and oxidative stress, MMSE (Mini-Mental State Examination) score and the number of neurofibrillary tangles to classify 31 individuals (9 healthy controls and 22 AD patients in three different stages of disease) that could be key in the development of AD. Our results allowed us to generate classification models of different states of AD severity, according to the MMSE and we found that the level of expression of the ADIPOQ gene could play an important role in the onset of AD. Our predictive model can contribute knowledge that could be incorporated into a personalized medical DSS in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.