Title | ||
---|---|---|
Binary acronym disambiguation in clinical notes from electronic health records with an application in computational phenotyping |
Abstract | ||
---|---|---|
•Acronym disambiguation – identifying the meaning of an acronym – is important for information retrieval in clinical EHR systems.•Most acronym disambiguation methods rely on manual annotation.•We propose a novel unsupervised method, CASEml, that uses the surrounding words as well as visit information to disambiguate acronyms.•CASEml performs as good or better than a state-of-the-art knowledge-based methods.•We demonstrate the utility of CASEml for downstream NLP tasks using clinical EHR text. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.ijmedinf.2022.104753 | International Journal of Medical Informatics |
Keywords | DocType | Volume |
Acronym disambiguation,Electronic health records,Natural language processing,Predictive modeling,Semantic embedding,Unsupervised learning | Journal | 162 |
ISSN | Citations | PageRank |
1386-5056 | 0 | 0.34 |
References | Authors | |
0 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicholas B Link | 1 | 0 | 0.34 |
Sicong Huang | 2 | 0 | 0.34 |
Tianrun Cai | 3 | 4 | 3.45 |
Jiehuan Sun | 4 | 0 | 1.35 |
Kumar Dahal | 5 | 0 | 0.34 |
Lauren Costa | 6 | 0 | 1.01 |
Kelly Cho | 7 | 0 | 0.34 |
Katherine Liao | 8 | 0 | 0.34 |
Tianxi Cai | 9 | 43 | 12.28 |
Chuan Hong | 10 | 1 | 2.04 |