A proposed SNOMED CT ontology-based encoding methodology for diabetes diagnosis case-base

Abstract

Domain knowledge ontology supports the implementation of intelligent Case Based Reasoning (CBR) systems. Standardized terminologies support efficient indexing and processing of patient data. It is an essential element for the implementation of knowledge-based clinical decision support by exploiting pre-defined semantic relationships, both hierarchical and non-hierarchical in nature. Systemized Nomenclature of Medicine-Clinical Terms (SNOMED CT) is the most comprehensive and complete terminology. This paper proposes an encoding methodology for clinical data using SNOMED CT. A case study for a diabetes diagnosis data set will be tested where SNOMED CT provides a concept coverage of ~75% for its clinical terms. Custom codes will be provided for uncovered terms. The encoded data set is derived from electronic health record database, and it represents a case base knowledge. The collected concept IDs will be used to build a domain ontology for diabetes diagnosis CBR. This ontology contains 550 concept IDs. The encoded case base and the domain ontology can be used to build a knowledge intensive CBR.