الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
Abstract
In this thesis, applying Ontological Engineering Methodology in Medical Domain to build a new Medical Ontology in pathology domain specific in Hepatobiliary System Diseases. The Hepatobiliary System is one of the important systems in the human body. It is responsible for many processes, which are necessary to keep body regulated and healthy. Conceptually, it is affected by many pathologic conditions, which affect other organs negatively. Also, it plays an important role in many body functions like protein production.
We exploited the existed Ontologies in the medical domain to build a new Hepatobiliary System Diseases (HSD) Ontology. The Ontology has been built using the BioPortal system to find the correct candidate Ontologies. This Ontology was developed in pathology domain and represented in the Web Ontology Language (OWL) that has recently become the standard language for the semantic web. The HSD Ontology development methodology includes five phases: HSD Query Extraction phase, Ontology selection phase, Ontology Mapping and Partitioning phase, Knowledge Adding phase, and Ontology Merging and Validation phase. By developing the HSD Ontology in pathology domain, both intelligent systems and physicians can share, reason, and exploit this knowledge in different ways.
Additionally, a complete system for prognosing and treating the Hepatobiliary system diseases was introduced. The system utilizes the causal relations among diseases to predict the incoming diseases. Besides, it shares the Ontology knowledge by replying the inquiries of both physicians and medical students. As the proposed system is a web service-based, it can be integrated with intelligent systems to share Ontology knowledge and to prognose the patient diseases. To show how the system is very beneficial, some of case studies are presented for the HSD Ontology sharing, patient diagnosing and treatment, and expecting the patient progress. The system has been evaluated using a real dataset of 40 anonymous patients, and the diagnosis accuracy of the system is 92.5% .