Liu Qiang, Chen An-Tian, Li Runmin, Yan Liang, Quan Xubin, Liu Xiaozhu, Zhang Yang, Xiang Tianyu, Zhang Yingang, Chen Anfa, Jiang Hao, Hou Xuewen, Xu Qizhong, He Weiheng, Chen Liang, Zhou Xin, Zhang Qiang, Huang Wei, Luan Haopeng, Song Xinghua, Yu Xiaolin, Xi Xiangdong, Wang Kai, Wu Shi-Nan, Liu Wencai, Zhang Yusi, Zheng Jialiang, Ding Haizhen, Xu Chan, Yin Chengliang, Hu Zhaohui, Qiu Baicheng, Li Wenle
Department of Orthopedics, Xianyang Central Hospital, Xianyang, Shannxi, China.
Department of Cardiology, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing, China.
iScience. 2024 Oct 5;27(11):111106. doi: 10.1016/j.isci.2024.111106. eCollection 2024 Nov 15.
Lumbar disc herniation (LDH) is a common cause of lower back pain and sciatica, and posterior lumbar interbody fusion (PLIF) is always employed. This multicenter retrospective study investigates predicting intraoperative blood transfusion for LDH patients undergoing PLIF in China. The research includes 6,241 patients from 22 medical centers and employs 8 feature selection methods and 10 machine learning models, including an integrated stacking model. The optimal predictive model was selected based on the receiver operating characteristic area under the curve, clinical applicability, and computational efficiency. Among the evaluated combinations, the simulated annealing support vector machine recursive + stacking model achieved the highest performance with an area under the curve of 0.884, supported by robust calibration and decision curve analyses. A publicly accessible web calculator was developed to assist clinicians in decision-making. This work significantly enhances intraoperative transfusion predictions, providing valuable tools for improving patient management.
腰椎间盘突出症（LDH）是下背部疼痛和坐骨神经痛的常见原因，后路腰椎椎间融合术（PLIF）是常用的治疗方法。这项多中心回顾性研究旨在预测中国接受PLIF手术的LDH患者的术中输血情况。该研究纳入了来自22个医疗中心的6241例患者，并采用了8种特征选择方法和10种机器学习模型，包括集成堆叠模型。基于曲线下面积、临床适用性和计算效率选择了最佳预测模型。在评估的组合中，模拟退火支持向量机递归+堆叠模型表现最佳，曲线下面积为0.884，经稳健校准和决策曲线分析验证。开发了一个可公开访问的网络计算器，以协助临床医生进行决策。这项工作显著提高了术中输血预测能力，为改善患者管理提供了有价值的工具。
