Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jan;20(1):78-86.
doi: 10.5811/westjem.2018.11.39725. Epub 2018 Dec 12.

A Review of Natural Language Processing in Medical Education

Michael Chary  1   2   3 , Saumil Parikh  1 , Alex F Manini  4 , Edward W Boyer  3 , Michael Radeos  4   5
Affiliations

A Review of Natural Language Processing in Medical Education

Michael Chary et al. West J Emerg Med. 2019 Jan.

Abstract

Natural language processing (NLP) aims to program machines to interpret human language as humans do. It could quantify aspects of medical education that were previously amenable only to qualitative methods. The application of NLP to medical education has been accelerating over the past several years. This article has three aims. First, we introduce the reader to NLP. Second, we discuss the potential of NLP to help integrate FOAM (Free Open Access Medical Education) resources with more traditional curricular elements. Finally, we present the results of a systematic review. We identified 30 articles indexed by PubMed as relating to medical education and NLP, 14 of which were of sufficient quality to include in this review. We close by discussing potential future work using NLP to advance the field of medical education in emergency medicine.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: By the WestJEM article submission agreement, all authors are required to disclose all affiliations, funding sources and financial or management relationships that could be perceived as potential sources of bias. No author has professional or financial relationships with any companies that are relevant to this study. There are no conflicts of interest or sources of funding to declare.

Figures

Figure 1
Figure 1
Hypothetical example of the use of natural language processing to quantify the evolution of resident medical decision-making as assessed by attending evaluations. [Schematic made by authors]. PGY; post graduate year; Q, quarter; MDM, medical decision making; Mg, magnesium; K, potassium; DDx, differential diagnosis; ω, topic weight; LDA, latent Dirichlet allocation.
Figure 2
Figure 2
Preferred reporting items for systematic reviews and meta-analyses (PRISM-A) style flowchart detailing extraction, screening, and inclusion of articles.
See this image and copyright information in PMC

References

    1. Ferrucci DA. Introduction to “This Is Watson.”. IBM J Res Dev. 2012;56(3.4):1–5.
    1. Assefi M, Liu G, Wittie MP, et al. An experimental evaluation of Apple Siri and Google speech recognition. Jun 14, 2018. Available at: https://www.cs.montana.edu/izurieta/pubs/sede2_2015.pdf.
    1. Agah A. Medical Applications of Artificial Intelligence. Boca Raton, FL: CRC Press; 2014.
    1. Murff HJ, FitzHenry F, Matheny ME, et al. Automated identification of postoperative complications within an electronic medical record using natural language rrocessing. JAMA. 2011;306(8):848–55. - PubMed
    1. Chapman WW, Christensen LM, Wagner MM, et al. Classifying free-text triage chief complaints into syndromic categories with natural language processing. Artif Intell Med. 2005;33(1):31–40. - PubMed

Publication types