A great addition to EMERSE is our large collection of manually curated terms and phrases that we call Synonyms. This dataset was created for term expansion, to help users find related concepts that they might otherwise miss. The Synonyms collection is a work in progress — new terms are added all the time. It currently contains over 1.1 million unique entries. The synonyms collection contains a wide variety of terms related to diseases, medications (prescription, over-the-counter, herbal, etc), symptoms, infectious agents, test names, anatomical names, misspellings (120,000 of them), and other variants. A subset of the categories, with examples, are shown below.
Category | Examples |
Acronyms | • ALL, acute lymphoblastic leukemia • ESRD, end stage renal disease • CXR, chest x-ray |
Abbreviations | • chemotherapy, chemo • ventilator, vent • shoulder pain, shld pain |
Professional and consumer terms | • myocardial infarction, heart attack • alopecia, hair loss • emesis, puking |
Misspellings | • ventilator, ventilater ventalator • pneumoina, pneuomnia, pneuomonia • diarriea, diahhrea, diarhea |
American English & British English spelling | • anesthesia, anaesthesia • anemic, anaemic • virilization, virilisation |
Trade and generic drug names | • Tylenol, acetaminophen • Prilosec, omeprazole • Zoloft, sertraline |
Chemotherapy regimens | • CHOP, cyclophosphamide, hydroxydaunorubicin, oncovin, prednisone • CFAR, cytoxan, fludarabine, alemtuzumab, rituximab • FOLFOX, folinic acid, fluorouracil, oxaliplatin |
Word stems | • pain, painful, painfully • sleep, sleeping, sleepy • test, tested, testing |
True synonyms | • frigid, cold, freezing • break, shatter, fracture • sandal, shoe, footwear |
Phrasing variations | • lidocaine with epinephrine • lido w/ epi • epi-lidocaine |
Malapropisms/usage errors | • beast mass • prostrate cancer • horse voice |
Root word variations | • adenotonsillectomy, tonsilloadenoidectomy • hepatopancreatobiliary, pancreatohepatobiliary • trichophytobezoar, phytotrichobezoar |
Hyphenations | • pseudosarcomatous, pseudo-sarcomatous • polyradiculoneuropathy, poly-radiculoneuropathy, poly-radiculo-neuropathy |
Idioms | • under the knife • under the weather • frog in her throat |
Neologisms | • trabecularity (instead of trabeculation) • misinnervation, dysinnervation, malinnervation |
Some terms are included that clinicians may not even consider to be real terms. For example, menorrhagia is considered a synonym of hypermenorrhea. These two terms are are also grouped with hypermenorrhagia, the latter of which is not a true medical term but nevertheless appears in the clinical notes of more than 500 of our patients.
Within EMERSE, Synonyms are used as system-provided suggestions, but users can always include their own terms in their searches. Additionally, it is possible for EMERSE system administrators to include additional terms that would then be available to all users of the system, perhaps needed for unique local terminologies. The Synonyms were created specifically to help with string matching in EMERSE, but the dataset could have utility for other natural language processing (NLP) tasks.
The Synonyms collection is available through licensing from our tech transfer office.
View License
95% of the terms above appear in the medical record at least once
97% of the terms above appear in the medical record at least once
100% of the terms above appear in the medical record at least once
98% of the terms above appear in the medical record at least once
90% of the terms above appear in the medical record at least once
Additional Data Sets
In addition to the EMERSE Synonyms Collection, other datasets have been formatted to work within EMERSE. These are described below and are available for download at no cost.
A list of journal titles and their MedLine abbreviations. This can be useful for searching documents for mentions of literature citations.
Source: National Center for Biotechnology Information (NCBI) (link)
MeSH (Medical Subject Headings) terms are a controlled vocabulary used for organizing biomedical literature such as PubMed and other database.
Source: National Library of Medicine (NLM), MeSH 2018 dataset (link)
A list of occupations, which may be useful if trying to find occupation data for patients. Searching for synonyms of 'occupation' will bring up the list within EMERSE.
Source: Careerplanner.com (link)
A list of occupations, which may be useful if trying to find occupation data for patients. Searching for synonyms of 'occupation' will bring up the list within EMERSE.
Source: Bureau of Labor Statistics, May 2017 dataset (link)