| Summary: | 碩士 === 國立成功大學 === 工程科學系 === 104 === Heart disease is one of the top ten causes of death in global, and coronary artery disease (CAD) is the main form of heart disease. Cardiac catheterization gives accurate results, but it is expensive and may be harmful to patients. Non-invasive methods can reduce damage risk but have lower accuracy and other problems like time-consuming and expensive. Therefore, a diagnosis method that is accurate, cost-effective, and time-saving is desirable.
In this thesis, a model that uses an adaptive neural fuzzy inference system (ANFIS) is presented, which is able to build a diagnosis system with self-correction by training data. An expert system for heart diseases that follows doctor judgement from limited linguistic information given by patients is applied. There are two phases in the system. In the first phase, input features are obtained, checking if input features have defect. If so, the system has to correct the defect. In second phase, an ANFIS algorithm is used for classification.
The ANFIS model is trained by using the back propagation method which combines with the least squares method. Four levels of CAD results which are classified by the severity of the disease, are used by the diagnosis system to help doctors choose the most appropriate treatment for patients. The training performance and classification accuracies are used to evaluate the performance of the ANFIS model. The performance of ANFIS model is compared with the fuzzy diagnosis system. The results shows that the accuracy of the ANFIS model (80.6%) is better than the accuracy of the fuzzy model (72.7%).
|
|---|
