Estimating mental states of a depressed person with Bayesian Networks

Studies in Computational Intelligence Volume 489, 2013, pp 163-168



In this work in progress paper we present an approach based on Bayesian Networks to model the relationship between mental states and empirical observations in a depressed person. We encode relationships and domain expertise as a Hierarchical Bayesian Network. Mental states are represented as latent (hidden) variables and the measurements found in the data are encoded as a probability distribution generated by such latent variables; we provide examples of how the network can be used to estimate mental states.