The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms

Jie Song,1 Yuan Gao,2 Pengbin Yin,3 Yi Li,1 Yang Li,2 Jie Zhang,4 Qingqing Su,1 Xiaojie Fu,2 Hongying Pi5 1Medical School of Chinese PLA, Beijing, People’s Republic of China; 2First Medical Center, Chinese PLA General Hospital, Beijing, People’s Republic of China; 3Fouth Medical Center, Chinese PLA General Hospital, Beijing, People’s Republic of China; 4Sixth Medical Center, Chinese PLA General Hospital, Beijing, People’s Republic of China; 5Medical Service Training Center, Chinese PLA General Hospital, Beijing, People’s Republic of ChinaCorrespondence: Hongying PiMedical Service Training Center, Chinese PLA General Hospital, No. 28 Fuxing Road, Haidian District, Beijing, 100853, People’s Republic of ChinaTel/Fax +86 010-66939159Email pihongying@301hospital.com.cnPurpose: Build machine learning models for predicting pressure ulcer nursing adverse event, and find an optimal model that predicts the occurrence of pressure ulcer accurately.Patients and Methods: Retrospectively enrolled 5814 patients, of which 1673 suffer from pressure ulcer events. Support vector machine (SVM), decision tree (DT), random forest (RF) and artificial neural network (ANN) models were used to construct the pressure ulcer prediction models, respectively. A total of 19 variables are included, and the importance of screening variables is evaluated. Meanwhile, the performance of the prediction models is evaluated and compared.Results: The experimental results show that the four pressure ulcer prediction models all achieve good performance. Also, the AUC values of the four models are all greater than 0.95. Besides, the comparison of the four models indicates that RF model achieves a higher accuracy for the prediction of pressure ulcer.Conclusion: This research verifies the feasibility of developing a management system for predicting nursing adverse event based on big data technology and machine learning technology. The random forest and decision tree model are more suitable for constructing a pressure ulcer prediction model. This study provides a reference for future pressure ulcer risk warning based on big data.Keywords: pressure ulcer, adverse event, machine learning, risk management