Artificial neural networks model: Neuropsychological variables and their relationship with body fat percentage in adults

Abstract

There is a growing interest to understand the neural functions and substrates of complex cognitive processes related to Obesity (OB). Artificial Intelligence (AI) is being applied, specifically the perceptron model of Artificial Neural Networks (ANN) in non-communicable chronic diseases, to identify with greater certainty the connective factors (synaptic networks) between the input variables and the output variables associated. Objective : Identify the synaptic weights of the ANN whose input variables are the executive functions (EF) and healthy lifestyles as predictors of Body Fat Percentage (BFP) in a group of adult subjects with different levels of BFP. Methods : It was an exploratory, is a nonlinear variables with a Backpropagation allows for to based on least squares correction, and its main objective is that the networks to 40 participants aged between 18-38 years. BFP was measured using a RENPHO ES-24M Smart Body Composition Scale. The perceptron ANN model with ten trials was applied with a multila-yer-perceptron. Results : The ANN showed that the sensory variables with greater synaptic weight for BFP were Stroop A and B Errors and Successes of BANFE-2, and OQ scales Rationalizations and Healthy Habits. Conclusions : ANN proved to be important in the simultaneous analysis of neuropsychological and healthy lifestyle data for the analysis of OB prevention and treatment by identifying the variables that are closely related. These findings open the door for the use of non-li-near analysis models, which allow the identification of relationships of different weights, between input and output variables, to more effectively direct interventions to modify obesity habits.