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

Computerized extraction of coded findings from free-text radiologic reports. Work in progress.

P J Haug1, D L Ranum, P R Frederick

  • 1Department of Medical Informatics, LDS Hospital/University of Utah, Salt Lake City 84143.

Radiology
|February 1, 1990
PubMed
Summary

A new system, the Special Purpose Radiology Understanding System (SPRUS), extracts and codes information from radiology reports. This tool shows promise for improving research and patient care by organizing radiologic data.

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

Familiality of diabetes mellitus.

Experimental and clinical endocrinology & diabetes : official journal, German Society of Endocrinology [and] German Diabetes Association·2007
Same author

Building a comprehensive clinical information system from components. The approach at Intermountain Health Care.

Methods of information in medicine·2003
Same author

Combining decision support methodologies to diagnose pneumonia.

Proceedings. AMIA Symposium·2002
Same author

Clinical performance measures: the changing status of peritoneal dialysis.

Kidney international·2001
Same author

Automatic identification of patients eligible for a pneumonia guideline: comparing the diagnostic accuracy of two decision support models.

Studies in health technology and informatics·2001
Same author

Nutritional markers during peritoneal dialysis: data from the 1998 Peritoneal Dialysis Core Indicators Study.

Peritoneal dialysis international : journal of the International Society for Peritoneal Dialysis·2001

Area of Science:

  • Medical Informatics
  • Radiology
  • Artificial Intelligence in Healthcare

Background:

  • Free-text radiology reports contain valuable clinical data that is difficult to access for research and audits.
  • Current methods for extracting information from radiology reports are often manual and time-consuming.
  • There is a need for automated tools to efficiently process and encode radiologic information.

Purpose of the Study:

  • To implement and evaluate the Special Purpose Radiology Understanding System (SPRUS) for automated data extraction from radiology reports.
  • To assess the accuracy of SPRUS in recognizing and encoding radiologic findings and diagnostic interpretations.
  • To explore the potential of SPRUS for clinical data management, medical audit, and research.

Main Methods:

Related Experiment Videos

  • The Special Purpose Radiology Understanding System (SPRUS) was developed as a module within the Health Evaluation through Logical Processing Hospital Information System.
  • SPRUS utilizes semantic information from a diagnostic expert system to parse free-text radiology reports.
  • The system extracts and encodes radiologic findings and radiologists' interpretations into a clinical database.

    • Main Results:

    • SPRUS achieved an 87% true-positive rate for recognizing radiographic findings with a 5% bad data rate.
    • The system demonstrated a 95% recognition rate for diagnostic interpretations with a 6% bad data rate.
    • Initial testing indicates that system performance can be enhanced through improvements to its thesaurus and knowledge base.

    Conclusions:

    • The Special Purpose Radiology Understanding System (SPRUS) effectively extracts and encodes key information from radiology reports.
    • SPRUS demonstrates high accuracy in identifying both radiologic findings and diagnostic interpretations.
    • This automated tool shows significant potential for improving the accessibility of coded radiologic data for research, medical audit, and patient care.