A model for predicting 7‐day pressure injury outcomes in paediatric patients: A machine learning approach
Chun Xiao, Liyan Pan, Yan Lin, Liyan Ye, Huiying Liang, Jianping Tao, Yi Luo
Abstract
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.