The health care field provides huge amounts of data that contain hidden pattern that can be useful for decisions. It is perplexing to orchestrate in an appropriate manner. Nature of the information association has been influenced because of improper administration of the information. Improvement in the measure of information needs some appropriate ways to concentrate and procedure information adequately and proficiently. This paper intended to develop a Decision Support System (DSS) for diagnosing cardiovascular diseases. The system used datamining technique, the Naïve Bayes Classification algorithm. This paper used Rapid Application Development (RAD) Software Life Cycle in designing and developing the system. The system was simulated, and its performance was evaluated in terms of accuracy using synthetic datasets namely, Cleveland and Statlog. Results showed that the system provided the adequate features for predicting heart diseases with an accuracy of 91% using the Cleveland dataset, 89% using the Statlog dataset and 90% using the combined instances of the two datasets.

Keywords: Data Mining, Decision Support System. Heart Disease, Naive Bayes

Thesis (Master in Information Technology)

Includes appendices and bibliographical references