Welcome to the VIE CaDDiS. CaDDiS is designed to serve as a component of a larger
decision support system which will provide information to decision makers within the African
agricultural community on the relative likelihood of a cow having different diseases given
that you have observed that it exhibits particular clinical signs. The objective of this decision support module is to facilitate better
differential diagnosis of tropical diseases. The linking together of different types of techniques
such as expert systems, mathematical models, statistical analysis systems, hypertextualised media
systems and databases to handle different types of information will produce a system which has
analytical and advisory potential.
CaDDiS is a Windows application consisting
of an expert system which uses the Bayesian
Belief Networks methodology. It will run under Windows 3.1, 3.11 and
95. It was designed and developed by Dr.
Yiqun Gu using Microsoft Visual C++. The system is parameterised
using data collected from 41 veterinary
experts. This data was analysed and converted into a suitable
format for use in the belief network by Dr.
Iain McKendrick. Two different analyses were carried out, giving subtly
different parameter values. These have both been implemented within this
system, since we are interested in evaluating whether
either or both are capable of generating
accurate diagnoses. The user interface is identical for each system.
The system uses the Bayesian
Belief Network methodology described in Lauritzen and Spiegelhalter (1988). The
project team gratefully acknowledge the contributions of the 41 veterinary experts whose expert opinions are codified in the system. The system
was developed within the Veterinary
Informatics and Epidemiology group of the Universities of Glasgow and
Strathclyde.
The properties of the system and advice on how to use it are described
in the Guide to CaDDiS,
while a simple introduction to the principles which underlie its operation
is provided in the Dummy''s
Guide to Belief Networks.
We hope that you will enjoy using CaDDiS and will take part in the evaluation exercise. We will be interested to hear whether veterinarians agree
with the findings of the system.
|
The link will always bring you back to this Home Page.
University of Strathclyde Home Page