Toward early diagnosis decision support for breast cancer: Ontology-based semantic interoperability.

Abstract

e18072 Background: Breast cancer is ranked as the most common cancer among women in China, cases in China account for about 300,000 of all newly diagnosed breast cancers each year. Developing Clinical Decision Supporting System (CDSS) to assist early diagnosis breast cancer is valuable, however, lack of semantic interoperability in CDSS has been identified as the main obstacle for broad adoption of CDSS. Ontology is considered to be one of the effective approaches to bridge the terminology gap between various clinical systems and data sources. In this study, we describe our efforts in transforming breast cancer clinical knowledge into computable ontology to support breast cancer early diagnosis. Methods: We have built a breast cancer ontology (BCO) to support our CDSS pipeline. A number of NCCN clinical practice guidelines in Oncology for Breast Cancer and the breast cancer diagnosis and treatment guidelines of China are the main knowledge sources of the BCO. BCO is a manually curated resource that contains concepts and relations of breast cancer clinical findings, demographics, laboratory tests, imaging results, treatments, pathologies, cancer stages, body structure and follow-up information. These curated knowledges are annotated through interoperable standard vocabulary SNOMED CT. Two physicians reviewed and evaluated the BCO. Results: Concepts in BCO currently contains 79 clinical findings, 8 demographics, 42 laboratory tests, 105 imaging results, 332 treatments, 141 pathology and cancer stages, 30 body structures and 3 follow-ups. Relations are defined such as finding site, associated with, etc. The concepts hierarchies and relationships were built by using Protégé to support OWL representation. As an initial evaluation results, most of concepts could be mapped to SNOMED CT, but there are some concepts could not be exactly mapped to SNOMED CT. We created local Chinese Vocabularies for these local terms. Conclusions: Based on interoperable BCO, a group of computable rules are developed by adding statements according to early diagnosis criteria of breast cancer. Diagnosis assistance around complex patients is supported though connecting the Electronic Health Record (EHR). This is an ongoing development that the BCO is continuingly enriched with standard concepts, relations and integrate with individual instances to support broader adoptability.