Application of Artificial Neural Network in Assessment Coronary Artery Disease

Background and

Since the human health is an essential issue in medical sciences, accurate predicting the individuals based on the disease status is of great importance. Therefore, models whose prediction ability yields to the minimum error and maximum certainty should be used. Thus, this study used artificial neural network model for predicting coronary artery disease (ÇÂD) because it is believed that in comparison with other models it a more precise model.

Multilayer perceptron (MLP) with error back propagation algorithm (ËBP) for assessing the coronary artery disease was implemented among 150 patients admitted in Mazandaran Heart Çenter, Sari. Then, based on the 80% of the available data, an artificial neural network with NN (14, 12, 1), sigmoid transfer function and 1500 epochs were designed and trained. The data were fed into Ëxcel program and then softwares for artificial neural network designing such as Pythia-Neural Network were employed.

Mean square of the error in training step was decreased to the level of 0.0238 and sensitivity and specificity rates obtained were 0.96 and 1. Ât the end, the model correctly categorized some healthy individuals who didn’t require angiography and the treatment related to coronary artery diseases.Çonclusion: Due to the high specificity index, this model prevents side effects of angiography in patients who do not require such treatments. Moreover, due to high sensitivity, it can diagnose the patients who really need such diagnostic treatments.