Medical Ontologies

In the domain of biomedical research, findings having vital knowledge are buried in publications in the form of unstructured text. Users cannot manage all the available amount of information by themselves. In order to deal with this problem, fields like big data and semantic web are being extensively used for sorting and classifying it. Ontologies are tools that provide a way of sorting, classifying and describing large amounts of information. This paper presents an ontology on the breast cancer domain using UMLS as data source. Our ontology contains integrated entities from well-organized sources i.e. Unified Medical Language System (UMLS) which is published by National Library of Medicine (NLM) and contains 170 bio-medical vocabularies. At present the ontology comprises facts on relations and semantic types for 106 categories of breast cancer including 14 main types and 92 subtypes. In addition to this the ontology contains 101 categories of broader relations with 27092 records and 254 categories of more specific relations covered with 10250 records.

Considering today’s surge of information, the need for well organized knowledge bases is increasing rapidly for providing simplified access to knowledge and its further processing. In biomedical domain, heaps of information is buried in scientific publications and online forums. This calls for representing this information in a more expressive semantic way by determining and storing relational information into a machine readable form. So, the primary goal of this research endeavor has been to build a knowledge base on entities and relations containing amass of formalized background knowledge suitable for supporting reasoning in biomedical domain. We introduce a way for easily accessing the knowledge about body parts and symptoms of human diseases, along with environmental, social, nutritional and diagnostic factors that cause these diseases. The information for this knowledge base is extracted from the controlled vocabulary thesaurus “Medical Subject Headings” (MeSH), which is published by National Library of Medicine.

Contemporary researches have revealed that most of the diseases are genetic. It is very important to mine the relation between gene and disease. Ontology is the best method to show the concepts and their relations. This research paper focuses on the development of ontology for the domain of Genetic Diseases. The data is extracted from UMLS. We developed this ontology on Protégé tool to facilitate the end users and clinical researchers. The resultant ontology is evaluated by domain experts.