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

Monitoring expert system performance using continuous user feedback

M G Kahn1, S A Steib, W C Dunagan

  • 1Section of Medical Informatics, Division of General Medical Sciences, Washington University School of Medicine, St. Louis, MO, USA. kahn@informatics.wustl.edu

Journal of the American Medical Informatics Association : JAMIA
|May 1, 1996
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

Clinical Research Informatics for Big Data and Precision Medicine.

Yearbook of medical informatics·2016
Same author

Knowledge-Based Systems.

Yearbook of medical informatics·2016
Same author

Incidence, risk factors, and outcomes of delayed-onset cytomegalovirus disease in a large, retrospective cohort of heart transplant recipients.

Transplantation proceedings·2014
Same author

Baseline hypovitaminosis D is not associated with poor clinical outcomes in osteoarticular infections.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2014
Same author

Tuberculin skin test and isoniazid prophylaxis among health care workers in high tuberculosis prevalence areas.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2011
Same author

Persistent low-level viraemia and virological failure in HIV-1-infected patients treated with highly active antiretroviral therapy.

HIV medicine·2006
Same journal

Digital divide in clinical and operational artificial intelligence adoption and implementation stages: US hospital diffusion patterns and AI deserts.

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

Extending the fundamental theorem of biomedical informatics: a proposal and illustrative examples.

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

Human factors methods for designing safe health information technology: what do the experts think?

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

Equity-by-design for socially assistive robots as digital health tools.

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

Orchestrator multi-agent clinical decision support system for secondary headache diagnosis in primary care.

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

CUI-Curate: a GraphRAG-based framework for automated clinical concept curation for NLP applications.

Journal of the American Medical Informatics Association : JAMIA·2026
See all related articles

Routine monitoring of expert systems using user feedback, like nurse disagreement rates with the GermWatcher system, effectively tracks performance improvements without frequent formal evaluations.

Area of Science:

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

Background:

  • Expert systems are increasingly deployed in healthcare settings.
  • Continuous performance monitoring is crucial for ensuring the reliability and effectiveness of these systems.
  • Traditional formal evaluations can be resource-intensive and infrequent.

Purpose of the Study:

  • To assess the feasibility of using routine operational data to monitor the performance of a deployed expert system.
  • To validate a surrogate metric for expert system performance based on user feedback.

Main Methods:

  • Two formal evaluations of the GermWatcher expert system were conducted six months apart.
  • Infection control nurses provided feedback by disagreeing with system outputs during routine use.

Related Experiment Videos

  • The rate of nurse disagreement was used as an indirect performance metric and validated against formal evaluation results.

    • Main Results:

    • A consistent decrease in nurse disagreement rates was observed following system improvements.
    • The second formal evaluation confirmed significant performance enhancement, validating the disagreement rate as a reliable indirect metric.
    • Continuous user feedback facilitated performance tracking and guided further system enhancements.

    Conclusions:

    • Metrics derived from routine expert system use, such as user disagreement rates, are applicable for performance monitoring.
    • Continuous user feedback allows for tracking the impact of system modifications without the need for repeated extensive formal evaluations.
    • Designing expert systems with integrated performance metrics for routine data collection is recommended.