An Improved Model for Clinical Decision Support System

Misguided information in health care has caused much havoc that have led to the death of millions of people as a result of misclassification, and inconsistent health care records; hence the objective of this paper is to develop an improved clinical decision support system. This system incorporated hybrid system of non-knowledge based and knowledge based decision support system for the diagnosis of diseases and proper health care delivery records using prostate cancer and diabetes datasets to train and validate the model. The min-max method was adopted in normalizing the datasets, while genetic algorithm was deployed in initiating the training weights of the MLP. The result obtained in this paper yielded a classification accuracy of 98%, sensitivity of 0.98 and specificity of 100 for prostate cancer and accuracy of 94%, sensitivity of 0.94 and specificity of 0.67 for diabetes.