Song Jie, Gao Yuan, Yin Pengbin, Li Yi, Li Yang, Zhang Jie, Su Qingqing, Fu Xiaojie, Pi Hongying
Medical School of Chinese PLA, Beijing, People's Republic of China.
First Medical Center, Chinese PLA General Hospital, Beijing, People's Republic of China.
Risk Manag Healthc Policy. 2021 Mar 18;14:1175-1187. doi: 10.2147/RMHP.S297838. eCollection 2021.
Build machine learning models for predicting pressure ulcer nursing adverse event, and find an optimal model that predicts the occurrence of pressure ulcer accurately.
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.
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.
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.
构建预测压疮护理不良事件的机器学习模型，寻找能准确预测压疮发生的最优模型。
回顾性纳入5814例患者，其中1673例发生压疮事件。分别采用支持向量机（SVM）、决策树（DT）、随机森林（RF）和人工神经网络（ANN）模型构建压疮预测模型。共纳入19个变量，并评估筛选变量的重要性。同时，对预测模型的性能进行评估和比较。
实验结果表明，四种压疮预测模型均取得了良好的性能。此外，四种模型的AUC值均大于0.95。此外，四种模型的比较表明，RF模型在压疮预测方面具有更高的准确性。
本研究验证了基于大数据技术和机器学习技术开发护理不良事件预测管理系统的可行性。随机森林和决策树模型更适合构建压疮预测模型。本研究为未来基于大数据的压疮风险预警提供了参考。
