ABSTRACT
Objective To analyze the use of the semantic type of the top-level ontology of military medicine in order to find problems with the semantic type framework and make it more scientific and comprehensive.Methods Using data driven method, the frequency with which the semantic type of the top-level ontology of military medicine was used in military medical core concepts was statistically analyzed.Results By ranking the use frequency of the semantic types, the semantic types which had higher or lower frequency, and those that had never been used were analyzed.Conclusion The established semantic type framework of the top-level ontology of military medicine is basically consistent with the expression of military medical knowledge and can be constantly updated and improved with the development of military medicine.
ABSTRACT
Objective To explore the construction method of semantic types of military medical ontology and to establish a framework for the semantic types of the top-level ontology of military medicine in order to lay the foundation for the construction of military medical ontology and provide support for knowledge organization, knowledge disclosure and knowledge service of military medical information resources.Methods Using the method of document measurement, the core concept set of military medicine was constructed.On the basis of the framework of the top-level semantic types of Unified Medical Language System(UMLS), the semantic type framework was completed by the combination of bottom-up and top-down modes, using semantic analysis and expert consultation.Results By classifying the same kind of knowledge points of military medicine into one semantic type, the hierarchical structure of the semantic type framework of the top-level ontology of military medicine was obtained.Conclusion The proposed method is effective and practical for the construction of the semantic types of military medical ontology.The established semantic type framework of the top-level ontology of military medicine could reconstruct military medical knowledge and provide the basic framework for the establishment of the semantic relationships of the top-level ontology of military medicine.
ABSTRACT
OBJECTIVE: For the effective retrieval of clinical information, the elaborate indexing is essential. Two major types of indexing are the human indexing and the automatic or machine indexing. Human indexing shows higher quality but is time consuming, labor-intensive and inconsistent in term assignment activity. METHODS: Using the Unified Medical Language System (UMLS) MetaMap program, we mapped the free text from the diagnosis section of radiology reports into UMLS concepts. To improve the precision of UMLS concept indexing by MetaMap, we evaluated the UMLS subset mapping and semantic type filtering methods, determining the best combination for improved precision. RESULTS: After calculating the candidates from subset combinations, we obtained more enhanced results by semantic-type filtering. CONCLUSION: The results may be improved for the complete automation of indexing process.