Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Evaluating natural language processors in the clinical domain

C Friedman1, G Hripcsak

  • 1Department of Computer Science, Queens College CUNY, New York, USA. friedman.carol@columbia.edu

Methods of Information in Medicine
|December 29, 1998
PubMed
Summary

Evaluating clinical natural language processing (NLP) systems is crucial but challenging. This study proposes criteria to improve NLP evaluation methods in healthcare, addressing limitations in current approaches for better clinical data extraction.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Urban air pollution and in vitro fertilization outcomes: A Canadian retrospective study.

Reproductive toxicology (Elmsford, N.Y.)·2026
Same author

MAO inhibitory activity of bromo-2-phenylbenzofurans: synthesis, <i>in vitro</i> study, and docking calculations.

MedChemComm·2018
Same author

Estimating summary statistics for electronic health record laboratory data for use in high-throughput phenotyping algorithms.

Journal of biomedical informatics·2018
Same author

Development of a battery of tests to measure attitudes and intended behaviours of dental students towards people with disability or those in marginalised groups.

European journal of dental education : official journal of the Association for Dental Education in Europe·2017
Same author

Patient-Centered Network of Learning Health Systems: Developing a resource for clinical translational research.

Journal of clinical and translational science·2017
Same author

Decision Support, Knowledge Representation and Management.

Yearbook of medical informatics·2016

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Artificial Intelligence in Medicine

Background:

  • Clinical natural language processing (NLP) systems are increasingly developed for information extraction from free-text clinical reports.
  • Despite system development, rigorous evaluation of these NLP tools in the clinical domain remains a significant challenge.
  • Existing evaluations often suffer from methodological weaknesses, limiting the reliability of reported performance measures.

Purpose of the Study:

  • To address the difficulties in evaluating clinical NLP systems.
  • To propose a set of criteria designed to enhance the quality and rigor of NLP evaluation studies within the medical field.
  • To provide an overview of current NLP evaluation practices in clinical settings and discuss relevant insights from non-clinical NLP evaluations.

Related Experiment Videos

Main Methods:

  • Review and analysis of existing NLP evaluation methodologies, including those from the Message Understanding Conferences (MUC).
  • Identification and discussion of factors contributing to the complexity of evaluating NLP systems in the clinical domain.
  • Development of a proposed set of criteria for improved clinical NLP evaluation.

Main Results:

  • A comprehensive overview of the state of NLP evaluation in the clinical domain is presented.
  • Key challenges and complexities inherent in evaluating clinical NLP systems are detailed.
  • A framework of criteria is proposed to guide more effective and reliable NLP system evaluations.

Conclusions:

  • Improving evaluation methodologies is essential for the advancement of clinical NLP.
  • The proposed criteria aim to standardize and strengthen the assessment of NLP systems used in healthcare.
  • More robust evaluations will lead to greater confidence in NLP tools for clinical information extraction.