Using word embeddings to expand terminology of dietary supplements on clinical notes
Authors:
Open Access
- 28 March 2019
- journal article
- research article
- Published by Oxford University Press (OUP) in JAMIA Open
- Vol. 2 (2) , 246-253
Abstract
Objective: The objective of this study is to demonstrate the feasibility of applying word embeddings to expand the terminology of dietary supplements (DS) using over 26 million clinical notes.Methods: Word embedding models (ie, word2vec and GloVe) trained on clinical notes were used to predefine a list of top 40 semantically related terms for each of 14 commonly used DS. Each list was further evaluated by experts to generate semantically similar terms. We investigated the effect of corpus size and other settings (ie, vector size and window size) as well as the 2 word embedding models on performance for DS term expansion. We compared the number of clinical notes (and patients they represent) that were retrieved using the word embedding expanded terms to both the baseline terms and external DS sources expanded terms.Results: Using the word embedding models trained on clinical notes, we could identify 1–12 semantically similar terms for each DS. Using the word embedding expanded terms, we were able to retrieve averagely 8.39% more clinical notes and 11.68% more patients for each DS compared with 2 sets of terms. The increasing corpus size results in more misspellings, but not more semantic variants and brand names. Word2vec model is also found more capable of detecting semantically similar terms than GloVe.Conclusion: Our study demonstrates the utility of word embeddings on clinical notes for terminology expansion on 14 DS. We propose that this method can be potentially applied to create a DS vocabulary for downstream applications, such as information extraction.Keywords
Funding Information
- National Center for Complementary & Integrative Health (#R01AT009457)
- National Center for Advancing Translational Science (#U01TR002062, #1UL1TR002494)
This publication has 19 references indexed in Scilit:
- A comparison of word embeddings for the biomedical natural language processingJournal of Biomedical Informatics, 2018
- Expanding a radiology lexicon using contextual patterns in radiology reportsJournal of the American Medical Informatics Association, 2018
- Estimation of the prevalence of adverse drug reactions from social mediaInternational Journal of Medical Informatics, 2017
- Evaluating Term Coverage of Herbal and Dietary Supplements in Electronic Health Records.2015
- Utilizing social media data for pharmacovigilance: A reviewJournal of Biomedical Informatics, 2015
- Mining clinical text for signals of adverse drug-drug interactionsJournal of the American Medical Informatics Association, 2014
- Evaluating Word Representation Features in Biomedical Named Entity Recognition TasksBioMed Research International, 2014
- The prevalence of herb and dietary supplement use among children and adolescents in the United States: Results from the 2007 National Health Interview SurveyComplementary Therapies in Medicine, 2013
- Dietary Supplement Use in the United States, 2003–2006The Journal of Nutrition, 2011
- Measures of semantic similarity and relatedness in the biomedical domainJournal of Biomedical Informatics, 2007