Multivariable network associated with cognitive decline and dementia

Abstract

Data mining of a large data base from the population longitudinal study named "The Conselice Study" has been the focus of the present investigation. Initially, 65 years old or older participants were interviewed, underwent medical and cognitive examination, and were followed up for 5 years: 937 subjects completed the follow-up. Relationships of 35 genetic and/or phenotypic factors with incident cognitive decline and dementia were investigated. The new mathematical approach, called the Auto Contractive Map (AutoCM), was able to show the differential importance of each variables. This new variable processing created a semantic connectivity map that: (a) preserved non-linear associations; (b) showed connection schemes; (c) captured the complex dynamics of adaptive interactions. This method, based on an artificial adaptive system, was able to define the association strength of each variable with all the others. Few variables resulted to be aggregation points and were considered as major biological hubs. Three hubs were identified in the hydroxyl-methyl-gutaryl-CoA reductase (HMGCR) enzyme, plasma cholesterol levels and age. Gene variants and cognate phenotypic variables showed differential degrees of relevance to brain aging and dementia. This data analysis method was compared with another mathematical model called mutual information relevance network and results are presented and discussed.