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

Evaluation of a knowledge-based decision-support system for ventilator therapy management

N Shahsavar1, U Ludwigs, H Blomqvist

  • 1Department of Medical Informatics, Linköping University, Sweden.

Artificial Intelligence in Medicine
|February 1, 1995
PubMed
Summary

This study validated VentEx, a medical knowledge-based system for ventilator therapy decisions. VentEx provided advice comparable to physicians, with minor disagreements in setting recommendations.

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

Supporting GPs and people with hypertension to maximise medication use to control blood pressure: a pilot cluster RCT of the MIAMI intervention.

BMC primary care·2024
Same author

Prioritising the psychosocial needs of young oncology patients: a call for comprehensive care.

Hong Kong medical journal = Xianggang yi xue za zhi·2024
Same author

Correlation between improved leptin signaling and cognitive function post bariatric surgery.

Journal of affective disorders·2023
Same author

Evaluation of a semi-automated software program for the identification of vertebral fractures in children.

Clinical radiology·2017
Same author

The PARP inhibitor ABT-888 potentiates dacarbazine-induced cell death in carcinoids.

Cancer gene therapy·2016
Same author

Next-generation sequencing with a myeloid gene panel in core-binding factor AML showed KIT activation loop and TET2 mutations predictive of outcome.

Blood cancer journal·2016

Area of Science:

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

Background:

  • Evaluating medical knowledge-based systems presents unique verification and validation challenges.
  • The field of medical decision-support systems evaluation is relatively unexplored.
  • Ventilator therapy management requires sophisticated decision support.

Purpose of the Study:

  • To evaluate the performance of VentEx, a medical knowledge-based system for ventilator therapy.
  • To validate the knowledge base of VentEx using real patient data.
  • To compare the quality of VentEx recommendations with a gold standard and human physicians.

Main Methods:

  • VentEx was evaluated using 1300 hours of patient care data from 12 patients with 6 diagnoses.

Related Experiment Videos

  • The knowledge base was validated against a gold standard for ventilator setting recommendations.
  • VentEx's advice quality was compared to that of two physicians.

    • Main Results:

    • Disagreement between VentEx and the gold standard ranged from 4.5% to 15.6% for setting recommendations.
    • A 22.2% disagreement was observed for weaning recommendations.
    • VentEx produced advice of similar quality compared to two physicians.

    Conclusions:

    • VentEx demonstrates a high level of accuracy in supporting ventilator therapy decisions.
    • The system's performance is comparable to that of experienced physicians.
    • This evaluation contributes to the understanding of medical knowledge-based system validation.