The overall objective of our work is to predict more accurately
the presence of heart disease. In this paper, two more input
attributes obesity and smoking are used to get more accurate
results. Three data mining classification techniques were
applied namely Decision trees, Naive Bayes & Neural
Networks. From results it has been seen that Neural Networks
provides accurate results as compare to Decision trees &
Naive Bayes.
This system can be further expanded. It can use more number
of input attributes listed above in table 1 and 2. Other data
mining techniques can also be used for predication e.g.
Clustering, Time series, Association rules. The text mining
can be used to mine huge amount of unstructured data
available in healthcare industry database.