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

Classification trees. A possible method for iso-resource grouping in intensive care

S Ridley1, S Jones, A Shahani

  • 1Department of Anaesthesia, Norfolk and Norwich Hospital, UK.

Anaesthesia
|December 16, 1998
PubMed
Summary

Classification tree analysis effectively groups intensive care unit patients by patient attributes to predict length of stay. This method minimizes variation, improving patient stratification for critical care.

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

Multicenter Study of Dose Accumulation for Reirradiation: Intercenter Variation in Radiobiological Dose Scaling Introduces Clinically Relevant Differences.

Clinical oncology (Royal College of Radiologists (Great Britain))·2026
Same author

Fetal cardiac remodeling in second trimester in pregnancies with pre-eclampsia and/or fetal growth restriction: deep-learning-based approach using population-wide data.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2025
Same author

Australian guidelines for equine internal parasite management.

Australian veterinary journal·2025
Same author

Reply.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2024
Same author

Role of artificial-intelligence-assisted automated cardiac biometrics in prenatal screening for coarctation of aorta.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2024
Same author

Considerations for study design in the DAHANCA 35 trial of protons versus photons for head and neck cancer.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2023

Area of Science:

  • Critical care medicine
  • Health informatics
  • Biostatistics

Background:

  • Classifying intensive care unit (ICU) patients is challenging due to high heterogeneity.
  • Existing methods like Diagnosis-Related Groups may not adequately capture ICU patient complexity.
  • A need exists for improved patient stratification methods in critical care.

Purpose of the Study:

  • To explore the influence of easily identifiable patient attributes on length of stay in the ICU.
  • To apply classification tree analysis for grouping critically ill patients.
  • To minimize variation in length of stay within patient groups.

Main Methods:

  • Utilized classification tree analysis on a dataset of 2,545 critically ill patients from three hospitals.
  • Identified three key independent patient attributes to predict the dependent variable: length of ICU stay.

Related Experiment Videos

  • Grouped patients to minimize the interquartile range (IQR) of length of stay within terminal groups.

    • Main Results:

    • Classification tree analysis successfully grouped patients based on selected attributes.
    • In 23 out of 39 terminal groups, the interquartile range for length of stay was reduced to 3 days or less.
    • Demonstrated significant reduction in length of stay variation within identified patient clusters.

    Conclusions:

    • Classification tree analysis is a viable method for stratifying critically ill patients in the ICU.
    • Easily identifiable patient attributes can effectively predict and group patients by length of stay.
    • This approach offers a more refined method for patient classification in critical care settings.