Pattern Recognition 39 (2006) 2186 – 2193 www.elsevier.com/locate/patcog Diagnosis of heart disease using artificial immune recognition system and fuzzy weighted pre-processing Kemal Polat a , ∗ , Salih Güne¸ s a , Sülayman Tosun b a Electrical and Electronics Engineering Department, Selcuk University, 42035 Konya, Turkey b Computer Engineering Department, Selcuk University, 42035 Konya, Turkey Received 23 October 2005; received in revised form 18 April 2006; accepted 25 May 2006 Abstract This paper presents a novel method for diagnosis of heart disease. The proposed method is based on a hybrid method that uses fuzzy weighted pre-processing and artificial immune recognition system (AIRS). Artificial immune recognition system has showed an effective performance on several problems such as machine learning benchmark problems and medical classification problems like breast cancer, diabetes, liver disorders classification. The robustness of the proposed method is examined using classification accuracy, k-fold cross-validation method and confusion matrix. The obtained classification accuracy is 96.30% and it is very promising compared to the previously reported classification techniques.  2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved. Keywords: Heart disease; Artificial immune system; AIRS; Fuzzy weighted pre-processing; k-fold cross validation; Medical diagnosis 1. Introduction Heart disease is any disorder that influences the heart’s ability to function normally. The most common cause of heart disease is narrowing or blockage of the coronary ar- teries, which supply blood to the heart itself. This happens slowly over time [1]. Extensive clinical and statistical studies have identified several factors that increase the risk of coronary heart disease and heart attack. Major risk factors (e.g., tobacco smoke, high blood cholesterol, high blood pressure, physical in- activity, obesity and overweight and diabetes mellitus) can significantly increase the risk of heart and blood vessel (cardiovascular) disease as the previous research have shown [2]. Other factors, called contributing risk factors, (e.g., stress and alcohol) may increase the risk of cardiovascular disease, however, their significance and prevalence have not yet been precisely determined. While some of the risk factors ∗ Corresponding author. Tel.: +90 332 223 2056; fax: +90 332 241 0635. E-mail addresses: kpolat@selcuk.edu.tr (K. Polat), sgunes@selcuk.edu.tr (S. Güne¸ s), stosun@selcuk.edu.tr (S. Tosun). 0031-3203/$30.00  2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved. doi:10.1016/j.patcog.2006.05.028 can be modified, treated or controlled, some cannot. The more risk factors you have, the greater the chance of devel- oping a coronary heart disease. The level of each risk fac- tor may also increase the chance of having coronary heart disease [2]. Having so many factors to analyze to diagnose the heart disease of a patient makes the physician’s job difficult. A physician usually makes decisions by evaluating the cur- rent test results of a patient and by referring to the previous decisions she made on other patients with the same con- dition. The former method depends strongly on the physi- cian’s knowledge. On the other hand, the latter depends on the physician’s experience to compare her patient with her earlier patients. This job is not easy considering the number of factors she has to evaluate. In this crucial step, she may need an accurate tool that lists her previous decisions on the patient having same (or close to same) factors. Motivated by the need of such an important classification method, in this study, we propose a method to diagnose the heart disease. The proposed method uses AIRS classifi- cation system and a weighting process, which is based on fuzzy weighted pre-processing method. In our method, we