Implementation of a learning procedure for multiple observations in a Diabetes Advisory System based on causal probabilistic networks
Ole Kristian Hejlesen, Steen Andreassen, Stig Kjær Andersen · Studies in health technology and informatics · 1993
An extension of a causal probabilistic network, modelling the humane glucose metabolism, making it possible to estimate patient specific parameters from data from multiple days, is presented. The importance of preserving information on both the patient specific means and standard deviations of the parameters is described. The approach is illustrated by examples of the role of the patient specific insulin sensitivity.