目的 构建预测后路腰椎椎间融合患者术中低体温发生风险的决策树模型。方法 2022年6-9月，采用便利抽样法选取于某医院行后路腰椎椎间融合术的102例患者为研究对象，根据是否发生术中低体温将其分为低体温组（n=77）和非低体温组（n=25），使用单因素和多因素Logistic回归分析发生术中低体温的危险因素，并建立相关决策树预测模型。结果 体质量指数（body mass index，BMI）较低、美国麻醉医生协会（American Society of Aneshesiologists，ASA）评分较高、入室体温较低、手术时间较长和出血量较多是后路腰椎椎间融合术患者术中低体温的独立危险因素（均P＜0.05）；基于上述因素建立了预测后路腰椎椎间融合术患者术中低体温发生风险的决策树模型，模型验证结果显示，曲线下面积（area under curve，AUC）为0.821（95%CI：0.798~0.844）。结论 基于影响因素构建的决策树模型，对后路腰椎椎间融合术患者术中低体温的发生风险具有良好的预测能力。

Objective To construct a decision tree model for predicting the risk of hypothermia during posterior lumbar interbody fusion.Methods Patients who underwent posterior lumbar interbody fusion in a hospital from June 2022 to September 2022 were selected as the study objects by convenience sampling method.They were divided into hypothermia group (n=77) and non-hypothermia group (n=25) according to whether intraoperative hypothermia occurred.Univariate and multivariate Logistic regression were used to analyze the risk factors of intraoperative hypothermia in posterior lumbar interbody fusion patients,and the correlation decision tree prediction model was established.Results Low Body Mass Index (BMI)，high American Society of Aneshesiologists (ASA) score，low body temperature，long operation time and blood loss were independent risk factors for intraoperative hypothermia in posterior lumbar interbody fusion (all P＜0.05).Based on these factors，a decision tree model was established to predict the risk of intraoperative hypothermia in patients undergoing posterior lumbar interbody fusion.The model validation results showed that the AUC was 0.821 (95%CI:0.798-0.844).Conclusions The decision tree model based on influencing factors has a good predictive ability for the risk of intraoperative hypothermia in posterior lumbar interbody fusion patients.

R473.6

广东省医学科学技术研究基金项目（C2016065）