Zhang Ke, Chen Yufang, Feng Chenglong, Xiang Xinhao, Zhang Xiaoqing, Dai Ying, Niu Wenxin
Translational Research Center, Shanghai Yangzhi Rehabilitation Hospital, School of Medicine, Tongji University, Shanghai 201619, China.
School of Physics Science and Engineering, Tongji University, Shanghai 200092, China.
Comput Methods Programs Biomed. 2025 Apr;261:108648. doi: 10.1016/j.cmpb.2025.108648. Epub 2025 Feb 7.
Patients with spinal cord injury (SCI), are prone to pressure injury (PI) in the soft tissues of buttocks. Early prediction of PI holds the potential to reduce the occurrence and progression of PI. This study proposes a machine learning model to predict soft tissue stress/strain and evaluate PI risk in SCI patients.
Based on the standard database from parametric models of buttock, the biomechanical response of soft tissues and risk factors affecting PI were analyzed. A comprehensive assessment of multiple machine-learning methods was performed to predict the risk of PI, the selected optimal model is explained locally and globally using Shapley additive explanations (SHAP).
The proposed hybrid model for predicting PI consists of a backpropagation neural network and Extreme Gradient Boosting, performed the coefficient of determination (R) of 0.977.
The model exhibits accurate performance which may be considered as the ideal method for predicting PI. Furthermore, it can be used with other health-monitoring equipment to improve the quality of patients with SCI or other dysfunctional diseases.
脊髓损伤（SCI）患者臀部软组织易发生压疮（PI）。早期预测压疮有可能减少其发生和进展。本研究提出一种机器学习模型，用于预测SCI患者的软组织应力/应变并评估压疮风险。
基于臀部参数模型的标准数据库，分析软组织的生物力学响应及影响压疮的危险因素。对多种机器学习方法进行综合评估以预测压疮风险，使用Shapley加法解释（SHAP）对所选最优模型进行局部和全局解释。
所提出的用于预测压疮的混合模型由反向传播神经网络和极端梯度提升组成，决定系数（R）为0.977。
该模型表现出准确的性能，可被视为预测压疮的理想方法。此外，它可与其他健康监测设备配合使用，以提高SCI或其他功能障碍性疾病患者的生活质量。
