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

A general natural-language text processor for clinical radiology

C Friedman1, P O Alderson, J H Austin

  • 1Columbia University, New York, NY, USA.

Journal of the American Medical Informatics Association : JAMIA
|March 1, 1994
PubMed
Summary
This summary is machine-generated.

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

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

Coding Systems in Health Care.

Yearbook of medical informatics·2016
Same author

Medical Informatics Training at Columbia University and the Columbia-Presbyterian Medical Center.

Yearbook of medical informatics·2016
Same author

Toward an optimal "antiplatelet" dose of aspirin: Preliminary observations.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2015

A new natural-language processor accurately extracts clinical information from radiology reports. This system achieved 70% recall and 87% precision, improving to 85% recall with query training.

Area of Science:

  • Natural Language Processing
  • Medical Informatics
  • Radiology

Background:

  • Clinical information is often unstructured in narrative reports.
  • Efficiently extracting and structuring this data is crucial for clinical applications.

Purpose of the Study:

  • To develop a general natural-language processor (NLP) for identifying and structuring clinical information from narrative reports.
  • To map identified information into a structured representation using clinical terms.

Main Methods:

  • A three-phase NLP system: parsing using a semantic grammar, regularization of terms, and encoding to a controlled vocabulary.
  • The system was tested on 230 radiology reports, focusing on the impression sections.
  • Performance was evaluated by comparing automated queries for four diseases against physician analysis for recall and precision.

Related Experiment Videos

Main Results:

  • The NLP system achieved 70% recall and 87% precision for disease identification without specific training.
  • Training the query component enhanced recall to 85% while maintaining precision.

Conclusions:

  • The developed NLP processor effectively extracts and structures clinical information from radiology reports.
  • The system demonstrates strong performance in automated information retrieval and has potential for clinical decision support.