Table 1 Summary of dictionaries used by cTAKES

Snomed-CT [20]

Snomed-CT is a set of clinical terms maintained by the International Health Terminology Standards Development Organization (IHTSDO). The development of Snomed-CT dates back to 1965 and is known for its comprehensive coverage of clinical terms. SNOMED-CT consists of concepts, descriptions, and relationships and can be used for semantic processing

NCI Thesaurus [21]

The National Cancer Institute (NCI) Thesaurus was created to assist in research systems made available by NCI. It covers clinical terminology regarding cancers, findings, drugs, therapies, anatomy, genes, and many other cancer research related terms. NCI thesaurus offers a partial model as to how these subjects relate to each other and aims to provide a common system for cancer researchers to communicate

MeSH [22]

Medical Subject Headings (MeSH) is an NLM controlled vocabulary used for indexing articles on NIH’s pubmed. Additionally, relationships between terms are provided which can act as a thesaurus

ICD-9 [23, 24]

International Classification of Diseases (ICD) is a coding system designed for classification of diseases and disorders. ICD is maintained by the World Health Organization (WHO) and ICD-9 is the ninth revision of the system. In the United States, ICD-9 has seen popular usage in medical billing. The system has been adopted by many organizations, including the centers for disease control for reporting mortality and morbidity statistics [25]