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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Frailty and geriatric complications in older patients with IBD: a nationwide hospital claims database study across Japan.

Aging clinical and experimental research·2026
Same author

Enhancing Team-Based Learning in Virtual Environments: The Role of Avatar Agency and Immersive Social Presence.

JMIR medical education·2026
Same author

Acute peritonitis-induced adipose CD127<sup>+</sup> ILC1s express PD-L1 and ameliorate inflammation in mice.

Nature communications·2026
Same author

Gut-primed neutrophils activate Kupffer cells to promote hepatic injury in mouse sepsis.

Nature communications·2025
Same author

Poor Appetite Negatively Affects Recovery of Swallowing Function During Post-Acute Rehabilitation.

Geriatrics & gerontology international·2025
Same author

Impact of frailty risk on postoperative activities of daily living and in-hospital events in older patients with hydrocephalus using a nationwide Japanese database.

Geriatrics & gerontology international·2025

Related Experiment Video

Updated: Jun 13, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.0K

Machine Learning-Based Prediction of Delirium and Risk Factor Identification in Intensive Care Unit Patients With

Ryo Esumi1, Hiroki Funao2, Eiji Kawamoto1

  • 1Department of Molecular Pathobiology and Cell Adhesion Biology, Mie University Graduate School of Medicine, Mie University, Tsu, Japan.

JMIR Formative Research
|February 3, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models accurately predict delirium in intensive care unit (ICU) burn patients using initial data. Key predictors include urine output, oxygen saturation, and burn area, aiding early risk identification.

Keywords:
AIartificial intelligenceburnsdeliriumintensive care unitmachine learningprediction model

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
11:02

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

494

Related Experiment Videos

Last Updated: Jun 13, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.0K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
11:02

Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics

Published on: November 29, 2024

494

Area of Science:

  • Medical informatics
  • Critical care medicine
  • Burn surgery

Background:

  • Delirium incidence in intensive care unit (ICU) burn patients is high (up to 77%) and linked to increased mortality.
  • Early identification of high-risk patients is crucial for effective treatment strategies.

Purpose of the Study:

  • Develop a machine learning model to predict delirium in burn patients during ICU stay.
  • Utilize data from the first day of ICU admission for prediction.
  • Identify key predictive factors for ICU delirium in burn patients.

Main Methods:

  • Analyzed data from 82 adult burn patients admitted to ICU for ≥24 hours.
  • Measured 70 variables upon ICU admission for prediction model input.
  • Employed 10 machine learning methods and Shapley additive explanations for risk factor identification.

Main Results:

  • Several machine learning models, including logistic regression (AUC 0.906), achieved high accuracy in delirium prediction.
  • Major risk factors identified: 24-hour urine output, oxygen saturation, burn area, total bilirubin, and intubation.
  • Other significant factors include white blood cell fractions (monocytes), methemoglobin, and respiratory rate.

Conclusions:

  • Machine learning models effectively predict delirium in ICU burn patients.
  • Models trained on initial vital signs and blood data show predictive capability.
  • Identified risk factors can guide early intervention strategies for burn patients.