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 Video

Updated: Nov 19, 2025

Mouse Model of Pressure Ulcers After Spinal Cord Injury
06:51

Mouse Model of Pressure Ulcers After Spinal Cord Injury

Published on: March 9, 2019

9.8K

Predicting pressure injury using nursing assessment phenotypes and machine learning methods.

Wenyu Song1,2, Min-Jeoung Kang1,2, Linying Zhang3

  • 1Department of Medicine, Brigham & Women's Hospital, Boston, Massachusetts, USA.

Journal of the American Medical Informatics Association : JAMIA
|January 31, 2021
PubMed
Summary

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

Impact of Hyponatremia Correction on the Risk for 30-Day Readmission and Death in Patients with Congestive Heart Failure.

The American journal of medicine·2016
Same author

Corrigendum to "Medication safety practices in hospitals: A national survey in Saudi Arabia" [Saudi Pharm. J. 21(2) (2013) 159-164].

Saudi pharmaceutical journal : SPJ : the official publication of the Saudi Pharmaceutical Society·2016
Same author

The frequency of inappropriate nonformulary medication alert overrides in the inpatient setting.

Journal of the American Medical Informatics Association : JAMIA·2016
Same author

A cross-sectional observational study of high override rates of drug allergy alerts in inpatient and outpatient settings, and opportunities for improvement.

BMJ quality & safety·2016
Same author

Appropriateness: A Key to Enabling the Use of Genomics in Clinical Practice?

The American journal of medicine·2016
Same author

Strategies for Managing Mobile Devices for Use by Hospitalized Inpatients.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2016
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
This summary is machine-generated.

Machine learning models accurately predict pressure injuries using electronic health record data. The random forest model, utilizing nurse-entered assessments like the Glasgow Coma Scale, shows high predictive performance for patient safety.

Area of Science:

  • Clinical Informatics
  • Machine Learning in Healthcare
  • Patient Safety Research

Background:

  • Pressure injuries are significant complications in hospitalized patients, impacting care quality.
  • Existing risk assessment tools lack accuracy due to outdated methods and limited data.
  • Accurate prediction is crucial for timely prevention and treatment of pressure injuries.

Purpose of the Study:

  • To develop advanced machine learning models for predicting pressure injury risk.
  • To leverage comprehensive electronic health record data for enhanced predictive accuracy.
  • To improve patient safety by enabling early detection and intervention for pressure injuries.

Main Methods:

  • Utilized electronic health records from five hospitals, including nurse-entered assessment data.
Keywords:
artificial intelligenceclinical phenotypeelectronic health recordpatient safetyquality of care

More Related Videos

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury
07:21

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

3.4K
Fabrication of Compressed Hosiery and Measurement of its Pressure Characteristic Exerted on the Lower Limbs
08:39

Fabrication of Compressed Hosiery and Measurement of its Pressure Characteristic Exerted on the Lower Limbs

Published on: May 27, 2020

2.6K

Related Experiment Videos

Last Updated: Nov 19, 2025

Mouse Model of Pressure Ulcers After Spinal Cord Injury
06:51

Mouse Model of Pressure Ulcers After Spinal Cord Injury

Published on: March 9, 2019

9.8K
Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury
07:21

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

3.4K
Fabrication of Compressed Hosiery and Measurement of its Pressure Characteristic Exerted on the Lower Limbs
08:39

Fabrication of Compressed Hosiery and Measurement of its Pressure Characteristic Exerted on the Lower Limbs

Published on: May 27, 2020

2.6K
  • Developed and evaluated machine learning models using two pressure injury phenotypes (hospital-acquired and non-hospital-acquired).
  • Employed five-fold cross-validation and extracted 28 clinical features for model training.

    • Main Results:

    • The random forest model demonstrated superior performance with AUCs of 0.92 and 0.94 on test sets.
    • The Glasgow Coma Scale was identified as the most significant predictor for both pressure injury types.
    • Models were developed for non-hospital-acquired (N=4398) and hospital-acquired (N=1767) pressure injuries.

    Conclusions:

    • The developed machine learning model accurately predicts pressure injury development.
    • External validation of this model could support widespread pressure injury prevention strategies.
    • This approach offers a more accurate and data-driven method for pressure injury risk assessment.