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

How accurate is computer-aided diagnosis?

G C Sutton1

  • 1Pontefract Health Authority, Ackton Hospital.

Lancet (London, England)
|October 14, 1989
PubMed
Summary
This summary is machine-generated.

Computer programs for diagnosing acute abdominal pain showed limited accuracy. Clinical diagnosis remained superior, suggesting Bayes

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

Newly diagnosed heart failure: change in quality of life, mood, and illness beliefs in the first 6 months after diagnosis.

British journal of health psychology·2011
Same author

Improving survival in the 6 months after diagnosis of heart failure in the past decade: population-based data from the UK.

Heart (British Cardiac Society)·2009
Same author

Echocardiographic features and brain natriuretic peptides in patients presenting with heart failure and preserved systolic function.

Heart (British Cardiac Society)·2005
Same author

N-terminal brain natriuretic peptide and subsequent hospital admission for worsening heart failure.

Heart (British Cardiac Society)·2005
Same author

The core of bluetongue virus binds double-stranded RNA.

Journal of virology·2002
Same author

Measurement of left ventricular volume after anterior myocardial infarction: comparison of magnetic resonance imaging, echocardiography, and radionuclide ventriculography.

The international journal of cardiovascular imaging·2002
Same journal

Medical compartmentalisation: a patient with chromosome 22q11.2 deletion syndrome in Japan.

Lancet (London, England)·2026
Same journal

[<sup>177</sup>Lu]Lu-edotreotide versus everolimus for gastroenteropancreatic neuroendocrine tumours (COMPETE): a phase 3, multicentre, randomised, open-label, superiority trial.

Lancet (London, England)·2026
Same journal

Research priorities for characterising Bundibugyo virus.

Lancet (London, England)·2026
Same journal

Rethinking treatment sequence in advanced gastroenteropancreatic neuroendocrine tumours.

Lancet (London, England)·2026
Same journal

Dual mobility total hip replacement in fractures: stability promotes patient confidence.

Lancet (London, England)·2026
Same journal

Dual mobility versus standard cups in total hip replacement for displaced femoral neck fractures (Duality): an international, multicentre, randomised, controlled, superiority trial.

Lancet (London, England)·2026
See all related articles

Area of Science:

  • Medical Informatics
  • Clinical Decision Support Systems
  • Diagnostic Accuracy

Background:

  • Acute abdominal pain presents a diagnostic challenge in clinical practice.
  • Computer-aided diagnostic systems aim to improve diagnostic accuracy.
  • Bayes' formula is a probabilistic method often employed in diagnostic algorithms.

Purpose of the Study:

  • To evaluate the diagnostic performance of two computer programs for acute abdominal pain.
  • To compare computer-aided diagnosis with clinical judgment in a real-world setting.
  • To determine the utility of Bayes' formula-based systems for this condition.

Main Methods:

  • Two computer programs, CAD-A and an amended version DIAG, were tested.
  • The programs were evaluated against clinical performance.

Related Experiment Videos

  • Data were collected from 6962 cases across three Scottish hospitals.

    • Main Results:

    • CAD-A achieved diagnostic accuracy between 48% and 59%.
    • DIAG demonstrated accuracy in the range of 56% to 62%.
    • Clinical diagnosis consistently showed higher accuracy at 65%.

    Conclusions:

    • Computer systems utilizing Bayes' formula demonstrated suboptimal diagnostic accuracy for acute abdominal pain.
    • Clinical expertise remains the most reliable method for diagnosing acute abdominal pain.
    • Current computer-aided diagnostic systems based on Bayes' formula have no significant role in managing acute abdominal pain.