A comparison of data mining methods for diagnosis and prognosis of heart disease

Heart disease is the leading cause of death for people in both men and women. Medical distinction is very important and it is a complicated task that should be performed properly and efficiently. Some doctors unfortunately not sufficiently adept in every sub specialty and they are in many places a scarce resource. The need for new tools able to help doctors in predicting and diagnosis heart disease is highly recognized. Here, this paper compare data mining algorithm fordiagnosis and prognosis heat disease as an automatic intelligent heart disease prediction system. Accordingly firstly we use data set with 14 attributes. Secondly, we develop a prediction model using Naïve Bayes, Neural Networks, Random forest, and c4.5 Decision Tree. Data set used in this research is obtained from several medical center and hospital in Tehran-Iran containing total instances 439 and 8 nominal and 7 numeric attributes. From the experimental result it is observed that the random forest algorithm with 94.53 % classification rate (accuracy score) produce a higher performance for our classification model when compared with other algorithms.

کلیدواژه ها:

heart disease ، data mining techniques ، classification ، weka ،