Related Experiment Video
Updated: Jan 14, 2026
06:04
Objective Nociceptive Assessment in Ventilated ICU Patients: A Feasibility Study Using Pupillometry and the Nociceptive Flexion Reflex
Published on: July 4, 2018
9.2K
Comparative Evaluation of Pressure Injury Risk Assessment Tools and Machine Learning Models in Postoperative Surgical
Touran Bahrami Babaheidari1, Mansooreh Tajvidi2, Mahmood Bakhtiyari1,3
1Department of Community Medicine, School of Medicine, Alborz University of Medical Sciences, Karaj, Iran.
Nursing in Critical Care
|January 13, 2026
Summary
The modified Braden scale accurately predicts pressure injuries in surgical intensive care unit (ICU) patients. Machine learning models offered minimal improvement over this established risk assessment tool.
Area of Science:
- Critical Care Medicine
- Patient Safety
- Predictive Analytics
Background:
- Pressure injuries are a significant complication in critically ill surgical patients.
- Intensive care unit (ICU) patients are particularly vulnerable, especially after major surgeries.
Purpose of the Study:
- To evaluate the predictive accuracy of common pressure injury risk assessment tools.
- To compare these tools against machine learning models in surgical ICU patients.
Main Methods:
- Prospective cohort study in a tertiary care surgical hospital.
- Assessed Braden, modified Braden, Waterlow, and Cubbin-Jackson scales.
- Explored machine learning models for enhanced prediction.
Main Results:
- Modified Braden scale showed the highest predictive accuracy (AUC: 0.90).
- Key predictors included prior pressure injuries, low hemoglobin, and diabetes.
- Machine learning models provided marginal accuracy improvement.
Conclusions:
- The modified Braden scale is the most reliable tool for predicting pressure injuries in surgical ICUs.
- Machine learning and other predictors offered limited added benefit.
- Future research should explore broader clinical measures for prevention.
