| Summary |
Knowledge discovery from the patient's health records is a challenging task for the medical specialists. The knowledge generated from the patient's records can assist specialists to make an effective decision and recommend more precise diagnosis. This provides the basis for decision-making process with the recommendation for patient diagnosis and expertise advice by retrieving the information from the knowledgebase. This research aims at utilizing data mining techniques to discover patterns and relationships in between diagnosis and corresponding symptoms. The extracted patterns are used to assist the physician to determine the precise diagnosis with patient's context. We consider graph database-Neo4j to develop a knowledgebase that stores knowledge in the ontological form of patterns and relationships and use the knowledgebase in clinical decision support system to provide recommendations of next possible symptoms and diagnosis for the effective recommendation. In addition, we integrate the expert knowledge with our knowledgebase and explore the feature of graph visualization, with more detail information of patterns and connection of associated patterns in the knowledgebase. |
| General note | Presented to the faculty of the Department of Computer Science |
| General note | Advisor: Kamran Sartipi |
| General note | Title from PDF t.p. (viewed February 18, 2019). |
| Dissertation note | M.S. East Carolina University 2018 |
| Bibliography note | Includes bibliographical references. |
| Technical details | System requirements: Adobe Reader. |
| Technical details | Mode of access: World Wide Web. |
| Genre/form | Academic theses. |
| Genre/form | Academic theses. |
