Natural language processing and inference rules as strategies for updating problem list in an electronic health record

From Clinfowiki
Revision as of 04:17, 19 November 2015 by Cypriannangcas (Talk | contribs)

Jump to: navigation, search

This is a brief review of the article "Natural language processing and inference rules as strategies for updating problem list in an electronic health record."[1]

NOTE: Except for the Comments below, all other information is taken directly from the article being reviewed.

Abstract[1]

Background

The problem-oriented electronic health record has become one of the most developed clinical documentation systems in medical informatics. While the advantages of a problem list are known and have been published in numerous studies, physicians do not always keep the problem list accurate, complete and updated.

Objective

To analyze natural language processing (NLP) techniques and inference rules as strategies to maintain completeness and accuracy of the problem list in EHRs.

Materials and Methods

Non systematic literature review in PubMed, in the last 10 years. Strategies to maintain the EHRs problem list were analyzed in two ways: inputting and removing problems from the problem list.

Results

NLP and inference rules have acceptable performance for inputting problems into the problem list. No studies using these techniques for removing problems were published Conclusion: Both tools, NLP and inference rules have had acceptable results as tools for maintain the completeness and accuracy of the problem list.

Conclusion

Natural language processing and inference rules have had acceptable results as tools for incorporating health problems into a problem list, mainly using limited sets of data. Further studies are needed to validate these rules in other areas and to extend the tools to a more comprehensively.

Comments

The only comment I can legitimately make is that I did not realize until I found and read this article that a "published" piece with no usable information, many mistakes in grammar, and no references can be passed off as a scholarly work.

Related Resources

Using natural language processing to identify problem usage of prescription opioids

Visualizing unstructured patient data for assessing diagnostic and therapeutic history

References

  1. 1.0 1.1 Plazzotta F, Otero C, Luna D, De quiros FG. Natural language processing and inference rules as strategies for updating problem list in an electronic health record. Stud Health Technol Inform. 2013;192:1163. http://ebooks.iospress.nl/publication/34379