The correct registration and encoding of medical data in Electronic Health Records is still a major challenge for health care professionals. Efficient terminological systems are lacking to enable multilingual semantic interoperability between general practitioners, patients, medical specialists, and allied health personnel. The aim of this paper is to propose an architectural structure for a Multilingual Medical Interface Terminology. We propose a dual structure with a multilingual reference terminology and a collection of unilingual lexical end-user resources. Our methods rely on ISO terminological standards, such as Terminology Markup Framework (ISO 16642) and Lexical Markup Framework (ISO 24613), and on Semantic Web technologies. We present procedures to select works, phrases, and concepts to populate these resources (manual concept extraction, automated term extraction), and to link them to NLP applications, and to many international nomenclatures and classifications. We present the publication of these resources in Linked Open Data and show the feasibility of the approach in a use case with terms related to heart failure in several languages. We illustrate in particular the difficulties in linking 168 real life concepts to multiple international classifications with different functionalities, level of granularity, and scopes.
Using ISO and Semantic Web standards for creating a Multilingual Medical Interface Terminology: A use case for Heart Failure
Cardillo, Elena;
2013-01-01
Abstract
The correct registration and encoding of medical data in Electronic Health Records is still a major challenge for health care professionals. Efficient terminological systems are lacking to enable multilingual semantic interoperability between general practitioners, patients, medical specialists, and allied health personnel. The aim of this paper is to propose an architectural structure for a Multilingual Medical Interface Terminology. We propose a dual structure with a multilingual reference terminology and a collection of unilingual lexical end-user resources. Our methods rely on ISO terminological standards, such as Terminology Markup Framework (ISO 16642) and Lexical Markup Framework (ISO 24613), and on Semantic Web technologies. We present procedures to select works, phrases, and concepts to populate these resources (manual concept extraction, automated term extraction), and to link them to NLP applications, and to many international nomenclatures and classifications. We present the publication of these resources in Linked Open Data and show the feasibility of the approach in a use case with terms related to heart failure in several languages. We illustrate in particular the difficulties in linking 168 real life concepts to multiple international classifications with different functionalities, level of granularity, and scopes.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
