Abstract
Coronary heart disease is a major cause of death world wide. The diagnosis of heart disease is a tedious task. There is a need for an intelligent decision support system for disease prediction. Data mining techniques are often used to classify whether a patient is normal or having heart disease. Hidden Naive Bayes is a data mining model that relaxes the traditional Naive Bayes conditional independence assumption. Our proposed model claims that the Hidden Naive Bayes (HNB) can be applied to heart disease classification (prediction). Our experimental results on heart disease data set show that the HNB records 100% in terms of accuracy and out performs naive bayes.