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

Avoiding premature closure in sequential diagnosis

D McSherry1

  • 1School of Information and Software Engineering, University of Ulster, Coleraine, UK.

Artificial Intelligence in Medicine
|July 1, 1997
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

Direct observation of strong coupling in a dense plasma.

Physical review. E, Statistical, nonlinear, and soft matter physics·2002
Same author

Dynamic and static approaches to clinical data mining.

Artificial intelligence in medicine·1999
Same author

Obtaining medical information from the Internet.

Journal of the Royal College of Physicians of London·1997
Same author

Clinical problem solving by computer.

Journal of the Royal College of Physicians of London·1997
Same author

Albert's test: a neglected test of perceptual neglect.

Lancet (London, England)·1986
Same author

Knowledge acquisition in the development of an introductory guide to diagnosis in rheumatology.

Medical informatics = Medecine et informatique·1985
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Avoid diagnostic errors by using probability bounds to determine when to stop medical testing. This approach prevents premature closure and unnecessary tests, improving diagnostic reasoning.

Area of Science:

  • Medical diagnostics
  • Artificial intelligence in medicine
  • Cognitive science

Background:

  • Diagnostic reasoning requires balancing evidence sufficiency with avoiding premature closure.
  • Current sequential diagnosis often uses arbitrary probability thresholds, risking unreliability.
  • Human diagnosticians intuitively use evidence bounds to guide decision-making.

Purpose of the Study:

  • To develop a more reliable termination strategy for sequential diagnostic testing.
  • To mitigate the risks of premature closure and unnecessary testing in medical diagnosis.
  • To enhance computational methods for determining probability bounds in diagnostic reasoning.

Main Methods:

  • Proposed a termination strategy based on upper and lower bounds of the leading diagnostic hypothesis probability.

Related Experiment Videos

  • Introduced new computational techniques to efficiently calculate these bounds.
  • Extended a probabilistic model of hypothetico-deductive reasoning within a Bayesian framework.

    • Main Results:

    • Demonstrated the unreliability of arbitrary thresholds for discontinuing diagnostic tests.
    • Showcased how probability bounds effectively prevent premature closure and undue test prolongation.
    • Presented novel methods significantly reducing computational effort for bound calculation.

    Conclusions:

    • A termination strategy using probability bounds is superior to arbitrary thresholds for sequential diagnosis.
    • The proposed methods enable diagnostic AI to better emulate human reasoning.
    • This approach enhances the efficiency and reliability of medical diagnostic processes.