الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 121 |  |  |
| | | from | 121 | | |
Abstract
Medical decisions, especially those related to the diagnosis, are complicated and requires managing a large amount of medical knowledge that could be divided into clinical data and radiological images. Hence, some of intelligent decision support systems could be used to make diagnosis decisions in an accurate manner. The main goal of this study is to develop an intelligent decision support system for the diagnosis of some children’s diseases. The system is used to help novice doctors, working mothers and doctors whom working in remote areas to make a suitable diagnostic decision.The proposed system was developed in three phases: In the first phase, the diagnosis of children’s diseases knowledge was acquired from various sources. In this phase, we collect medical information about children’s diseases from experts (Doctors), and through the internet. In the second phase, the acquired knowledge was represented in the knowledgebase using production rules technique. After that came the third phase, in which the knowledge and inference engine of the proposed system were produced and encoded by using CLIPS language. In addition to, in this study, image processing was developed for the classification of children’s diseases. The image processing was developed in two phases: feature extraction and classification. In the feature extraction, texture features were extracted from radiographic images by using Gray Level Co-occurrence matrix (GLCM) features. Finally, the performance of the classification was evaluated by using precision and recall. The experimental results confirmed that the proposed system provides good classification efficiency.