MEDICAL DECISION SUPPORT SYSTEM FOR HEPATITIS C VIRUS PREDICTION USING DATA MINING TECHNIQUES

Abstract

The healthcare environment is generally perceived as being ‘information rich’ yet ‘knowledgepoor’. Which, unfortunately, are not “mined” to discover hidden information for effective decisionmaking by healthcare practitioners. The health-care knowledge management can be improved throughthe integration of data mining and decision support. In this paper, we present a prototype Hepatitis CVirus Decision Support System (HCVDSS) that uses three data mining classification techniques,namely, Decision Trees, Naive Bayes and Neural Network. Results show that each technique has itsown strength in realizing the objectives of the defined mining goals. HCVDSS can answer complex“what if” queries. Using medical profiles such as gender, residence, Alt and Ast the proposed HCVDSScan predict the likelihood of patients getting HCV disease. It enables significant knowledge, e.g.,patterns, relationships between medical factors related to HCV disease, to be established. The proposedHCVDSS, which is implemented on the .Net platform, is windows application, user-friendly, scalable,reliable and expandable.