Semantic Mapping Model between ICD-10 and SNOMED-CT Health Terminologies

Abstract:

The International Statistical Classification of Diseases and Health Problems and the Systematized Nomenclature of Medicine are terminologies that aim for data transparency. Terminologies have differences in their compositions, and a mapping between these terms is necessary in order to obtain meaning, seeking to improve the daily life of health professionals with their patients through a model that structures the information in a comprehensive syntactic and semantic way. The goal of this research is to develop a model for semantic mapping between these health terminologies. This is exploratory research, a case study carried out at the Hospital das Clínicas da Faculdade de Medicina de Marília, which provided the International Statistical Classification of Diseases and Health-Related Problems codes recorded in the medical records for the mapping, aiming to migrate the stored data that were in a relational database to an international structure and data sharing network. The results showed that there are four types of situations during the mapping process: semantic accuracy between terminologies, use of expressions that make the health condition generic, terms that are not exactly equivalent but are semantically close, and a variety of terms to represent a single health condition. It is concluded that it is possible to develop a replicable model that preserves the semantic layer of terms between the International Statistical Classification of Diseases and Health Problems and the Systematized Nomenclature of Medicine.

Keywords:
electronic patient record; health classifications; health terminologies; semantic mapping