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

Closing the loop in ICU decision support: physiologic event detection, alerts, and documentation.

P R Norris1, B M Dawant

  • 1Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA.

Proceedings. AMIA Symposium
|February 5, 2002
PubMed
Summary

This study improved automated ICU alerting by capturing clinician feedback on patient status and therapy. This helps refine alert systems for better clinical significance and timely interventions.

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

Deep Learning Segmentation of the Nucleus Basalis of Meynert on 3T MRI.

AJNR. American journal of neuroradiology·2023
Same author

Focused stimulation of dorsal subthalamic nucleus improves reactive inhibitory control of action impulses.

Neuropsychologia·2017
Same author

Segmentation editing improves efficiency while reducing inter-expert variation and maintaining accuracy for normal brain tissues in the presence of space-occupying lesions.

Physics in medicine and biology·2013
Same author

Isolation of bacterial strains able to metabolize lignin from screening of environmental samples.

Journal of applied microbiology·2012
Same author

Evaluation of multiple-atlas-based strategies for segmentation of the thyroid gland in head and neck CT images for IMRT.

Physics in medicine and biology·2011
Same author

Comparison of manual and automatic segmentation methods for brain structures in the presence of space-occupying lesions: a multi-expert study.

Physics in medicine and biology·2011

Area of Science:

  • Biomedical Engineering
  • Critical Care Medicine
  • Health Informatics

Background:

  • Automated detection and alerting for physiologic events in the Intensive Care Unit (ICU) face challenges in defining clinical significance and opportunity for intervention.
  • Measuring the effectiveness of current alerting algorithms is difficult due to the complexity of defining these critical parameters for automated systems.

Purpose of the Study:

  • To assess the value of event definitions and refine alerting algorithms by capturing information from ICU care providers on patient state and therapy in response to alerts.
  • To improve automated physiologic event detection and alerting systems for enhanced clinical utility and patient care.

Main Methods:

  • The Simon project implemented a system to automatically deliver alerts for intracranial pressure and cerebral perfusion pressure to clinical users via alphanumeric pagers.

Related Experiment Videos

  • A system was developed to capture electronic documentation from clinicians regarding patient state and therapy in response to the automated alerts.
  • Data was collected over a 6-month period in a trauma ICU, encompassing 2280 hours of data from 14 patients, resulting in 530 detected alerts.

    • Main Results:

    • Clinical users electronically documented 81% of the 530 detected alerts as they occurred.
    • Retrospective classification of this documentation, based on therapeutic actions or reasons for inaction, provided valuable insights.
    • The captured data demonstrated potential for improving event definitions and enhancing the overall utility of the alerting system.

    Conclusions:

    • Capturing clinician feedback on patient state and therapy in response to automated alerts is crucial for refining event definitions.
    • This approach offers a viable method for assessing and enhancing the utility of automated alerting systems in the ICU.
    • Further refinement of alerting algorithms based on user-documented responses can lead to more clinically significant and actionable alerts.