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

Evaluating four diagnostic methods with acute abdominal pain cases

B Puppe1, C Ohmann, K Goos

  • 1Department of Medicine, University Hospital, Würzburg.

Methods of Information in Medicine
|September 1, 1995
PubMed
Summary

This study compared medical decision support systems for diagnosing acute abdominal pain. System performance varied little, with data quality being more critical than the specific diagnostic method used.

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

Social media attention and citations of published outputs from re-use of clinical trial data: a matched comparison with articles published in the same journals.

BMC medical research methodology·2021
Same author

Health care utilization and excess costs after pelvic fractures among older people in Germany.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2021
Same author

Towards a European health research and innovation cloud (HRIC).

Genome medicine·2020
Same author

Incisional hernia repair in a high-fidelity silicone model for open retro-muscular mesh implantation with preparation of the fatty triangle: validation and educational impact study.

Hernia : the journal of hernias and abdominal wall surgery·2019
Same author

European survey on national training activities in clinical research.

Trials·2019
Same author

Automatic recording of individual oestrus vocalisation in group-housed dairy cattle: development of a cattle call monitor.

Animal : an international journal of animal bioscience·2019

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Clinical Decision Support Systems

Background:

  • Medical decision support systems (MDSS) employ diverse methodologies.
  • Evaluating the comparative performance of different MDSS is crucial for optimizing diagnostic accuracy.

Purpose of the Study:

  • To compare the strengths and weaknesses of various diagnostic expert system methods.
  • To assess the impact of inference methods versus knowledge/data quality on diagnostic performance.

Main Methods:

  • Developed four diagnostic expert systems using Bayes, case-based classification, and heuristic classification methods.
  • Analyzed 1254 cases of acute abdominal pain from a prospective multicenter study.
  • Conducted a comparative evaluation of the expert systems' performance.

Related Experiment Videos

Main Results:

  • Overall performance differences between the expert systems were statistically insignificant.
  • System performance was more influenced by the quality of the knowledge base and case data than by inference methods.
  • Empirical knowledge-based systems (Bayes, case-based) showed a bias towards common diseases, while expert knowledge-based systems (heuristic) were more sensitive to uncommon diseases.

Conclusions:

  • The choice of inference method in diagnostic expert systems has a limited impact on overall performance.
  • Knowledge base and case data quality are paramount for effective medical decision support.
  • Different methods offer trade-offs in sensitivity towards common versus uncommon diagnoses.