الفهرس 
chapter 1 introductionOnly 14 pages are availabe for public view
 |  | from | 141 |  |  |
| | | from | 141 | | |
Abstract
Treatment of chronic hepatitis C is a complex problem. A clinical decision support system (CDSS) based on massive and distributed electronic health record can facilitate the automation of inference process and enhance its accuracy. The most important component of any CDSS is its knowledge base. This knowledge base can be formulated using ontologies. The formal description logic of ontology supports the inference of hidden knowledge. Building a complete, coherent, consistent, interoperable, and sharable ontology is a challenge. Syntax and semantic interoperability must exist among different distributed electronic health records (EHRs), and CDSSs to improve the system usability, and save real time. EHR has different data models with different coding terminologies. In order for CDSS to process different representations of EHR, it requires supporting semantic interoperability to enable the EHR exchange between different systems. In this research, we propose a new fibrosis severity prediction ( ) intelligent system. The intelligent clinical decision support system is based on hybrid knowledge-based approaches and data driven approaches. Since the resulting system achieves remarkable impacts on a correct prediction of the disease, it became the most efficient in predicting the liver fibrosis severity stage for patients having chronic infected HCV. The proposed CDSS inference process depends on rule-based ontology system reasoning. It is based on combining rule-based reasoning with formal standard constructed fuzzy ontology in a semantic interoperability framework. In order to enhance the functionality of the rule based reasoning, a set of 74 fuzzy rules have been induced using fuzzy decision tree. Moreover, many fault decisions occur due to insufficiency of correct and complete of data. The system is based on a set of knowledge acquisition for data collecting and machine learning techniques for handling dataset. In addition, it depends on domain expert knowledge for designing the membership functions and validating the fuzzy knowledge base. The proposed system is based on a suitable list of 18 symptoms, lab test features, and disease history that can accurately and significantly describe fibrosis patients. Thus, utilize machine learning techniques in the semantic framework improves the used knowledge base. To measure the efficiency of the proposed system, the experimental results of the expert system were obtained using a real dataset from the Liver Institute, Mansoura University, Egypt, of 119 patients infected by chronic viral hepatitis C. The measuring terms have been used to evaluate the semantic intelligent system comparing with the Mamdani inference system. The resulting system achieves an average accuracy 97.8%, and an increasing in the average precision rate from (91%) to (96%), which record improvement 5% from the existing systems. Thus, the semantic intelligent CDSS has proven that it can be included as a component in a healthcare system to assist physicians in their daily practices.