[Study on medical diagnosis decision support system for heart diseases based on hybrid genetic algorithm].

In this study, a medical diagnosis decision support system based on hybrid genetic algorithm has been established to support the diagnosis of five common heart diseases (coronary heart disease, rheumatic valvular heart disease, hypertensive heart disease, chronic cor pulmonale and congenital heart disease). A heart disease database consisting of 352 samples was used for constructing and testing the performance of system. Cross-validation of the experimental results indicate that the system we established shows high capability of classifying these five kinds of heart diseases, the mean accuracy of classification is as high as 90.6%, and the user accuracy and procedure accuracy of each disease are both above 85.0%, showing great application prospect of supporting heart diseases diagnosis in clinics.