An encoding methodology for medical knowledge using SNOMED CT ontology
Knowledge-Intensive Case Based Reasoning (KI-CBR) systems mainly depend on ontology. Using ontology as domain knowledge supports the implementation of semantically-intelligent case retrieval algorithms. The case-based knowledge must be encoded with the same concepts of the domain ontology. Standard...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2016-07-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157815000919 |
| _version_ | 1819133902089879552 |
|---|---|
| author | Shaker El-Sappagh Mohammed Elmogy |
| author_facet | Shaker El-Sappagh Mohammed Elmogy |
| author_sort | Shaker El-Sappagh |
| collection | DOAJ |
| description | Knowledge-Intensive Case Based Reasoning (KI-CBR) systems mainly depend on ontology. Using ontology as domain knowledge supports the implementation of semantically-intelligent case retrieval algorithms. The case-based knowledge must be encoded with the same concepts of the domain ontology. Standard medical ontologies, such as SNOMED CT (SCT), can play the role of domain ontology to enhance case representation and retrieval. This study has three stages. First, we propose an encoding methodology using SCT. Second, this methodology is used to encode the case-based knowledge. Third, all the used SCT concepts are collected in a reference set, and an OWL2 ontology of 550 pre-coordinated concepts is proposed. A diabetes diagnosis is chosen as a case study of our proposed framework. SCT is used to provide a pre-coordination concept coverage of ∼75% for diabetes diagnosis terms. Whereas, the uncovered concepts in SCT are proposed. The resulting OWL2 ontology will be used as domain knowledge representation in diabetes diagnosis CBR systems. The proposed framework is tested by using 60 real cases. |
| first_indexed | 2024-12-22T09:54:40Z |
| format | Article |
| id | doaj.art-b4dc7467518e407998f5bb9c93dc6a12 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-12-22T09:54:40Z |
| publishDate | 2016-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-b4dc7467518e407998f5bb9c93dc6a122022-12-21T18:30:18ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782016-07-0128331132910.1016/j.jksuci.2015.10.002An encoding methodology for medical knowledge using SNOMED CT ontologyShaker El-Sappagh0Mohammed Elmogy1Faculty of Computers and Information, Minia University, EgyptFaculty of Computers and Information, Mansoura University, EgyptKnowledge-Intensive Case Based Reasoning (KI-CBR) systems mainly depend on ontology. Using ontology as domain knowledge supports the implementation of semantically-intelligent case retrieval algorithms. The case-based knowledge must be encoded with the same concepts of the domain ontology. Standard medical ontologies, such as SNOMED CT (SCT), can play the role of domain ontology to enhance case representation and retrieval. This study has three stages. First, we propose an encoding methodology using SCT. Second, this methodology is used to encode the case-based knowledge. Third, all the used SCT concepts are collected in a reference set, and an OWL2 ontology of 550 pre-coordinated concepts is proposed. A diabetes diagnosis is chosen as a case study of our proposed framework. SCT is used to provide a pre-coordination concept coverage of ∼75% for diabetes diagnosis terms. Whereas, the uncovered concepts in SCT are proposed. The resulting OWL2 ontology will be used as domain knowledge representation in diabetes diagnosis CBR systems. The proposed framework is tested by using 60 real cases.http://www.sciencedirect.com/science/article/pii/S1319157815000919Clinical decision support system (CDSS)SNOMED CT (SCT) codingSemantic data retrievalOntologyCase-based reasoning (CBR)Diabetes diagnosis |
| spellingShingle | Shaker El-Sappagh Mohammed Elmogy An encoding methodology for medical knowledge using SNOMED CT ontology Journal of King Saud University: Computer and Information Sciences Clinical decision support system (CDSS) SNOMED CT (SCT) coding Semantic data retrieval Ontology Case-based reasoning (CBR) Diabetes diagnosis |
| title | An encoding methodology for medical knowledge using SNOMED CT ontology |
| title_full | An encoding methodology for medical knowledge using SNOMED CT ontology |
| title_fullStr | An encoding methodology for medical knowledge using SNOMED CT ontology |
| title_full_unstemmed | An encoding methodology for medical knowledge using SNOMED CT ontology |
| title_short | An encoding methodology for medical knowledge using SNOMED CT ontology |
| title_sort | encoding methodology for medical knowledge using snomed ct ontology |
| topic | Clinical decision support system (CDSS) SNOMED CT (SCT) coding Semantic data retrieval Ontology Case-based reasoning (CBR) Diabetes diagnosis |
| url | http://www.sciencedirect.com/science/article/pii/S1319157815000919 |
| work_keys_str_mv | AT shakerelsappagh anencodingmethodologyformedicalknowledgeusingsnomedctontology AT mohammedelmogy anencodingmethodologyformedicalknowledgeusingsnomedctontology AT shakerelsappagh encodingmethodologyformedicalknowledgeusingsnomedctontology AT mohammedelmogy encodingmethodologyformedicalknowledgeusingsnomedctontology |