Expert system for the diagnosis of neonatal jaundice for use by medical field personnel

The main objective of this project is to develop an expert system module that uses the clinical decision criteria of experts in the neonatology field to advice paramedical and semi-skilled personnel who require guidance to diagnose the etiology of neonatal jaundice. The project was developed with a commercially available software package EXSYS (Multilogic Inc.). In this project, we have used a rule-based system to build the decision tree that would aid the paramedical personnel to arrive at a appropriate etiology for hyperbilirubinemia in a neonate. The project is field tested in India, where the residents are asked to come up with the correct diagnosis given the clinical tests. The disadvantage of this model is that there is the problem of it becoming obsolete in a few years time unless it is constantly being updated by developers. There is also the problem that this system cannot train or learn by itself unlike an artificial neural network.