A Predictive Model of Pressure Injury in Children Undergoing Living Donor Liver Transplantation Based on Machine
Xiaomei Chen1, Shi Tang1, Yanwen Qin1
1Department of Nursing, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai, China.
Insights
Machine learning effectively predicts pressure injuries (PIs) in pediatric liver transplant patients. A Decision Tree model identified key risk factors, enabling targeted prevention strategies for nurses.
Area of Science:
- Pediatric transplantation
- Medical informatics
- Machine learning in healthcare
Background:
- Pressure injuries (PIs) pose a significant risk to pediatric patients undergoing living donor liver transplantation (LDLT).
- Accurate risk prediction is crucial for implementing timely preventive measures in this vulnerable population.
Purpose of the Study:
- To develop and validate a machine learning-based prediction model for forecasting the risk of PIs in children undergoing LDLT.
- To identify key risk factors associated with PI development in this cohort.
Main Methods:
- Retrospective cohort study involving 438 pediatric patients who underwent LDLT.
- Data was randomly split into training (70%) and testing (30%) sets.
- Four machine learning algorithms (Decision Tree, Random Forest, Gradient Boosting Decision Tree, eXtreme Gradient Boosting) were employed to build predictive models.
Main Results:
- The overall incidence of PIs was 9.6% (42 out of 438 patients).
- The Decision Tree model demonstrated the highest predictive efficacy.
- Key predictors identified by the Decision Tree model included operation time, intraoperative corticosteroid use, and preoperative skin condition/protection.
Conclusions:
- Machine learning, particularly the Decision Tree algorithm, effectively identifies critical factors for predicting PIs in pediatric LDLT patients.
- The developed predictive model provides an intuitive tool for nurses to assess PI risk and implement targeted preventive strategies.
Aims:
The aim of our study was to formulate and validate a prediction model using machine learning algorithms to forecast the risk of pressure injuries (PIs) in children undergoing living donor liver transplantation (LDLT).
Design:
A retrospective cohort study.
Methods:
The research was carried out at China's largest paediatric liver transplantation centre. A total of 438 children who underwent LDLT between June 2021 and December 2022 constituted the study cohort. The dataset was partitioned randomly into 70% for training datasets (306 cases) and 30% for testing datasets (132 cases). Utilising four machine learning algorithms-Decision Tree, Random Forest, Gradient Boosting Decision Tree and eXtreme Gradient Boosting-we identified risk factors and constructed predictive models.
Results:
Out of 438 children, 42 developed PIs, yielding an incidence rate of 9.6%. Notably, 94% of these cases were categorised as Stage 1, and 54% were localised on the occiput. Upon evaluating the four prediction models, the Decision Tree model emerged as the most effective. The primary contributors to pressure injury in the Decision Tree model were identified as operation time, intraoperative corticosteroid administration, preoperative skin protection measures and preoperative skin conditions. A visualisation elucidating the logical inference process for the 10 variables within the Decision Tree model was presented. Ultimately, based on the Decision Tree model, a predictive system was developed.
Conclusion:
Machine learning algorithms facilitate the identification of crucial factors, enabling the creation of an effective Decision Tree model to forecast pressure injury development in children undergoing LDLT.
Impact:
With this predictive model at their disposal, nurses can assess the pressure injury risk level in children more intuitively. Subsequently, they can implement tailored preventive strategies to mitigate the occurrence of PIs.
Patient Or Public Contribution:
Paediatric patients contributed electronic health records datasets.
