Abstract: This paper proposes an
adaptive framework for a Knowledge Based Intelligent Clinical Decision Support
System for the prediction of schizophrenia which is one of the most deadly illnesses
that has a monumental effect on the health of people afflicted with it and has
for long remained a persistent health problem affecting a significant number of
people all over the world. In the framework the patient information is fed into the system; the
Knowledge base of the system stores all the information to be used by the
Clinical Decision Support System and the classification algorithm selected
after an exhaustive evaluation of relevant classification algorithms for this
work is the C5.0 Decision Tree Algorithm with its percentage of correctly
classified instances given as 78.4534%; it searches the Knowledge base and
matches the patient information with the related rules that match with each
case and thereafter gives the most
precise prediction as to whether the patient is likely to develop schizophrenia
or not. This approach to the prediction of schizophrenia provides a very
reliable solution to the problem of ascertaining if a person is likely to
develop this illness or is almost not susceptible to the ailment.
Keywords: Schizophrenia, Clinical Decision Support
System (CDSS), Medical Decision Support System (MDSS), Artificial Intelligence
(AI), K Nearest Neighbor (K-NN), Decision Trees (DT),
Support Vector Machine (SVM) and Sequential Minimal Optimization (SMO).