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

Diagnostic decision support by inference networks

P H Bartels1, D Thompson, J E Weber

  • 1Optical Sciences Center, University of Arizona, Tucson.

In Vivo (Athens, Greece)
|July 1, 1993
PubMed
Summary

Inference networks improve diagnostic accuracy by considering evidence dependencies and providing uncertainty measures. This approach allows for independent control of false positive and false negative rates in rare event detection, such as cervical cancer prescreening.

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

Hypertension as a marker for later development of end-stage renal failure after lung and heart-lung transplantation: a cohort study.

The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation·2004
Same author

Cloning and characterization of an inversion breakpoint at 6q23.3 suggests a role for Map7 in sacral dysgenesis.

Cytogenetic and genome research·2004
Same author

Systematic review of interventions to reduce delay in patients with suspected heart attack.

Emergency medicine journal : EMJ·2004
Same author

Evidence for interaction between the TCO and NMTC1 loci in familial non-medullary thyroid cancer.

Journal of medical genetics·2004
Same author

Prolonged vitamin C supplementation and recovery from eccentric exercise.

European journal of applied physiology·2004
Same author

Pediatric nutrition surveillance.

Nutrition in clinical care : an official publication of Tufts University·2004

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Diagnostic Decision Support

Background:

  • Diagnostic procedures often struggle to balance false positive and false negative rates, especially for rare conditions.
  • Accurate combination of diverse diagnostic evidence is crucial for reliable decision-making.
  • Uncertainty quantification is essential for understanding the confidence in diagnostic outcomes.

Purpose of the Study:

  • To explore the utility of inference networks for combining diagnostic evidence.
  • To assess the ability of inference networks to provide probabilistic uncertainty measures.
  • To investigate the potential for decoupling false negative and false positive rates in rare event detection.

Main Methods:

  • Utilized inference networks for evidence aggregation in a diagnostic context.

Related Experiment Videos

  • Implemented automatic reasoning within the inference network framework.
  • Evaluated performance in a simulated diagnostic scenario for rare event detection.

    • Main Results:

    • Inference networks successfully integrated multiple pieces of diagnostic evidence.
    • The approach provided a probabilistic measure of diagnostic decision uncertainty.
    • Demonstrated the capability to independently manage false negative and false positive rates.

    Conclusions:

    • Inference networks offer a robust method for evidence combination in diagnostics.
    • Probabilistic outputs enhance the interpretability and reliability of diagnostic decisions.
    • This technology shows promise for improving rare event detection, exemplified by cervical cancer prescreening.