Hybrid Technique for Associative Classification of Heart Diseases

Over the past few years healthcare industry collects huge amounts of healthcare data which unfortunately, are not extracted to discover hidden information for effective decision making. Medical services today have come a long way to treat patients with various diseases. Among the most fatal one is the heart disease problem, which cannot be seen with a naked eye and comes instantly. The mortality rates has increased due to poor clinical decisions. To achieve reliable and cost effective treatment computer-based information or decision support systems can be developed to do the task. Data mining provides the solution for knowledge discovery from these large and complex databases. The author work involves the development of a framework based on associative classification techniques on heart dataset. Implementation of work is done on heart dataset from the UCI Machine Learning Repository to test and evaluate on different for better results. Experimental results show that most of the associative classification rules help in the best prediction of heart disease and helps in making reliable decision support system.