摘要
目的基于机器学习算法构建全身麻醉手术患者术中低体温预测模型, 并进行验证。方法采用便利抽样法, 回顾性收集2023年3-8月新疆医科大学第一附属医院1 075例全身麻醉手术患者数据, 按7∶3随机划分为建模集和验证集。结合LASSO回归与随机森林算法, 筛选术中低体温危险因素, 基于Logistic回归、决策树、K近邻算法(KNN)、支持向量机(SVM)、极端梯度提升(XGBoost)、多层感知器(MLP)6种机器学习算法构建模型, 并评估模型性能。开发网页版动态列线图, 并利用SHAP图对最优模型进行可解释性分析。结果根据LASSO回归和随机森林算法, 麻醉时长、术中失血量、基线体温、年龄、术中尿量、手术种类为全身麻醉患者术中低体温的危险因素(P<0.05)。Logistic回归、决策树、XGBoost、KNN、MLP、SVM模型的受试者工作特征曲线下面积分别为0.777、0.746、0.793、0.743、0.768、0.793;F1分数分别为0.667、0.719、0.861、0.756、0.820、0.842。决策性曲线显示, 当阈值概率处于0~1时, XGBoost模型预测患者术中低体温风险的净收益较高。开发的网页版动态列线图具有较好的临床适用性和可推广性。结论本研究基于机器学习算法构建并验证了全身麻醉手术患者术中低体温动态列线图, 可辅助临床医护人员识别术中低体温高风险患者并实施个性化干预。
Objective To construct and validate a prediction model for intraoperative hypothermia in general anesthesia surgery patients based on machine learning algorithm.Methods Convenience sampling was used to retrospectively collect data from 1075 general anesthesia surgery patients in the First Teaching Hospital of Xinjiang Medical University from March to August 2023,which were randomly divided into modeling set and validation set in the ratio of 7:3.Combining LASSO regression with the random forest algorithm,intraoperative hypothermia risk factors were screened.Models were constructed based on six machine learning algorithms,Logistic regression,decision tree,support vector machine(SVM),extreme gradient boosting(XGBoost),multilayer perceptron(MLP)and K-Nearest Neighbors(KNN),and evaluate the performance of all models.Web-based dynamic nomogram was developed and interpretable analysis of the optimal model was performed using SHAP graph.Results According to LASSO regression and random forest algorithm,length of anesthesia,intraoperative blood loss,baseline body temperature,age,intraoperative urine volume,and type of surgery were risk factors for intraoperative hypothermia in patients under general anesthesia,and the difference was statistically significant(P<0.05).The areas under the receiver operating characteristic curve for Logistic regression,decision tree,XGBoost,KNN,MLP,and SVM models were 0.777,0.746,0.793,0.743,0.768,0.793,and the F1 scores were 0.667,0.719,0.861,0.756,0.820,and 0.842,respectively.Decision curve showed that the net benefit of the XGBoost model for predicting intraoperative hypothermia in patients was high when the threshold probability was between O and 1.A web-based dynamic nomogram was developed with good clinical applicability and generalizability.Conclusions A dynamic nomogram of intraoperative hypothermia in general anesthesia surgery patients constructed and validated based on the machine learning algorithm can assist medical and nursing staff in identifying patients at high risk of intraoperative hypothermia and implementing personalized interventions.
作者
冯敏
加依娜尔·木哈台勒
马文涓
李丽
Feng Min;Jiayinaer Muhataile;Ma Wenjuan;Li Li(School of Nursing,Xinjiang Medical University,Urumqi 830000,China;Operating Room,the First Teaching Hospital of Xinjiang Medical University,Urumqi 830000,China;Xinjiang Research Center for Population Disease and Healthcare,Urumqi 830000,China)
出处
《中华现代护理杂志》
2025年第21期2837-2844,共8页
Chinese Journal of Modern Nursing
基金
第三批“天山英才”医药卫生高层次人才项目(TSYC202401A075)。
关键词
机器学习
术中低体温
预测模型
列线图
危险因素
Machine learning
Intraoperative hypothermia
Prediction model
Nomograms
Risk factors
