Related Experiment Video
Updated: Nov 16, 2025
Mouse Model of Pressure Ulcers After Spinal Cord Injury
Published on: March 9, 2019
A model for predicting 7-day pressure injury outcomes in paediatric patients: A machine learning approach
Xiao Chun1, Liyan Pan2, Yan Lin3
1Pediatric Intensive Care Unit (PICU), Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, Guangdong, China.
Insights
Machine learning models can predict delayed healing in pediatric pressure injuries. Key indicators include serum creatinine, red blood cell count, and hematocrit, aiding early intervention.
Area of Science:
- Pediatric critical care medicine
- Wound healing research
- Biomedical informatics
Background:
- Hospital-acquired pressure injuries (PIs) pose a significant risk to pediatric patients.
- Early identification of factors contributing to delayed healing is crucial for effective management.
- Predictive modeling can enhance clinical decision-making for pediatric PIs.
Purpose of the Study:
- To identify factors associated with early pressure injury progression in pediatric patients.
- To develop and validate a machine learning model for predicting pressure injury outcomes.
- To improve the quality of care for children with pressure injuries.
Main Methods:
- Retrospective cohort study of pediatric patients with hospital-acquired stage I or suspected deep tissue injury PIs.
- Patients were followed for 7 days, categorized into healing or delayed healing groups.
- Random Forest and eXtreme Gradient Boosting models were employed, analyzing clinical, demographic, and laboratory data.
Main Results:
- The Random Forest model, using 10 variables, achieved high predictive performance (accuracy 0.82, AUC 0.89).
- Key predictive factors included serum creatinine, red blood cell count, and hematocrit.
- The model demonstrated strong sensitivity (0.80) and specificity (0.84) for predicting outcomes.
Conclusions:
- Awareness of specific clinical indicators is essential for predicting delayed healing in pediatric PIs.
- The developed evidence-based prediction model can enhance early outcome prediction.
- This tool is expected to improve the quality of care and outcomes for pediatric patients with PIs.
Aims:
We sought to explore factors associated with early pressure injury progression and build a model for predicting these outcomes using a machine learning approach.
Design:
A retrospective cohort study.
Methods:
In this study, we recruited paediatric patients, with hospital-acquired stage I pressure injury or suspected deep tissue injury, who met the inclusion criteria between 1 January 2015-31 October 2018. We divided patients into two groups, namely healing or delayed healing, then followed them up for 7 days. We analysed patient pressure injury characteristics, demographics, treatment, clinical situation, vital signs, and blood test results, then build prediction models using the Random Forest and eXtreme Gradient Boosting approaches.
Results:
The best prediction model, trained and tested using Random Forest with 10 variables, achieved an accuracy, sensitivity, specificity, and area under the curve of 0.82 (SD 0.06), 0.80 (SD 0.08), 0.84 (SD 0.08), and 0.89 (SD 0.06), respectively. The most contributing variables, in order of importance, included serum creatinine, red blood cell, and haematocrit.
Conclusion:
An awareness of specific conditions and areas that could lead to delayed healing pressure injury in paediatric patients is needed.
Impact:
This evidence-based prediction model, coupled with the aforementioned clinical indicators, is expected to enhance early prediction of outcomes in paediatric patients thereby improve the quality of care and the outcome of children with PIs.
