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).