Experiences with Multilingual Modeling in the Development of the International Classification of Traditional Medicine Ontology

The World Health Organization (WHO) in collaboration with several international stakeholders have started recently the work on the International Classification of Traditional Medicine (ICTM), which will provide a standardized system for encoding and collecting health statistics data related to Traditional Medicine practice throughout the world. ICTM is represented in OWL, and is developed by Traditional Medicine experts in a collaborative Semantic Web platform, called iCAT-TM. The content of ICTM is developed simultaneously in four languages (English, Chinese, Japanese and Korean). In this paper, we describe how we modeled the multilingual content, the Web platform used for editing, and some of the challenges we have encountered related to the multilingual aspects of the model and use of the platform. 1 The International Classification of Traditional Medicine (ICTM) The World Health Organization (WHO) in collaboration with a large group of international stakeholders is developing the International Classification of Traditional Medicine (ICTM).1 ICTM will provide a standardized international system for classifying Traditional Medicine (TM) related health concepts, such as disorder names, disease patterns, signs and symptoms, causal factors, and interventions [9]. One of the goals of the project is to be able to unify the data collection and monitoring for Traditional Medicine systems with those of the conventional (i.e., “Western”) medicine, which will be realized by integrating a relevant part of ICTM as Chapter 23 of the 11th revision of the International Classification of Diseases (ICD).2 ICD is an essential classification used in the United Nation countries for compiling basic health statistics, billing, and clinical documentation [8]. The content of ICTM is based on classifications of Traditional Medicine from three countries, China, Japan and Korea. Even if these classifications have a common root, they have diverged significantly over the years. The role of ICTM is to harmonize these different efforts and come to a consensus classification that can be used in health systems around the world. With the information age revolution, WHO has changed significantly the way they build classifications. To make them ready for electronic health records and enable easy 1 https://sites.google.com/site/whoictm/ 2 http://www.who.int/classifications/icd11/browse/f/en cross-linking between them, the classifications have now a formal underpinning. ICTM, similarly to ICD-11, is represented as an OWL ontology and is developed using Semantic Web technologies. Given the international nature of ICTM, tackling the multilinguality problem is one of the main challenges in the project. Domain experts from the three countries and the project coordinators in Geneva, Switzerland, are developing the content of ICTM simultaneously in four languages: English, Chinese, Japanese, and Korean. Our group has provided the ontology modeling support and the Web platform infrastructure used for editing ICTM. In this paper, we describe our experiences in supporting multiple languages in the ICTM ontology, including the model and tooling, and the challenges we encountered. The rest of the paper is organized as follows: Section 2 describes the related work, in Section 3, we describe how we modeled the multilingual content in ICTM, Section 4 presents the collaborative Semantic Web platform used by the domain experts to edit ICTM, and finally, Section 5 presents the challenges and some lessons learned in the project, and gives an overview of the future work.