Domain Ontology Health Informatics Service from Text Medical Data Classification

Domain Ontology can represent the particular meanings of terms as they apply to that domain from medical data. Terms of meaning and use help provide information and knowledge for a better health informatics service. In this paper, the proposed framework and method for building ontology from text medical data is called Domain Ontology Health Informatics Classification (DOHIC). This method uses data mining techniques and applies ontology categories to explore the creation of a practicable health informatics service system, including information extraction, text medical data classification and ontological terminology concepts. The text mining concept has enabled the discovery of derivational and remarkable health information, uncovered amongst assorted collections of textual medical data, for the diagnosis of diseases. Furthermore, it acts as a means of control for the vocabulary based system according to UMLS of methatherasus to support the application of a viable database, which also aided in finding key words and phrases from the health information text. A disease is identified using the IDC-10 diagnosis and disease classification system. Then, the C4.5 algorithm, a workable classification methodology, was exploited through a decision tree. The classification will then be converted and mapped into ontological techniques in XML/OWL in order to build the main structure of the health informatics domain ontology in the concept hierarchy or terminology. The retrieval mechanism is employed to show meaningful relationships among the symptoms. These relationships are useful for a health informatics service as they help discover and provide new knowledge.