Comparison of Three Decision-Making Models in Differentiating Five Types of Heart Disease: A Case Study in Ghaem Sub-Specialty Hospital

Introduction: cardiovascular diseases are becoming the main cause of mortality and morbidity in most countries. This research goal was to predict the types of heart diseases for more accurate diagnosis by data mining and neural network technics. Method: This research was an applied-survey study and after data preprocessing, three approaches of neural network, decision making tree and Bayes simple algorithm were used to predict and recognize in Rapidminer software and neural artificial network model was used for prediction in Matlab software. Results: Genetic algorithm was used for selection of effective variables and neural artificial network models, decision making tree and Bayes simple algorithm were used to predict types of heart diseases in data mining. AHP model was used to determine a model with the best performance for predicting types of heart diseases. Conclusion: Neural network had much better performance than other data mining models used to diagnose types of heart diseases in this research. Also, in detecting disease by artificial neural network, the model with accuracy of more than 80 percent was verified as good and acceptable