基于机器学习的耐碳青霉烯类肠杆菌感染风险因素分析

Risk factor analysis of carbapenem-resistant enterobacteriaceae infection based on machine learning

目的探讨医院耐碳青霉烯类肠杆菌(CRE)感染的机器学习模型及风险因素分析。方法回顾性收集2018—2022年在该院治疗的451例产超广谱β内酰胺酶(ESBL)的肠杆菌感染患者病例资料,根据其对碳青霉烯是否耐药分为CRE组(115例)和敏感组(336例)。用Logistic回归分析、随机森林、支持向量机、神经网络4种机器学习方法构建预测模型并绘制受试者工作特征曲线进行评估,根据性能最好的预测模型分析CRE感染的风险因素。结果随机森林模型性能最优,其曲线下面积最大,为0.9523。随机森林模型预测CRE感染的风险因素为发热超过3 d、有脑损害、引流液标本、躯干手术、一级或特级护理、ICU治疗、降钙素原、抗厌氧菌治疗、用3代头孢、年龄、前清蛋白、肌酐、白细胞计数和清蛋白15项临床资料。结论该研究得出的CRE预测模型具有较好的预测价值,其风险因素对于临床防治CRE早期感染有指导意义。

Objective To explore the machine learning model and risk factor analysis for hospital infection caused by carbapenem-resistant enterobacteriaceae(CRE).Methods The clinical data of totally 451 patients infected with extended-spectrumβ-lactamases(ESBL)producing Enterobacteriaceae treated in the hospital from 2018 to 2022 were retrospectively collected.The patients were divided into CRE group(115 cases)and sensitive group(336 cases)according to the susceptibility of carbapenem.Four machine learning methods including Logistic regression analysis,random forest,support vector machine,and neural network were used to build prediction models and receiver operating characteristic curve was used to evaluate.Based on the prediction model with the best performance,risk factors for CRE infection were analyzed.Results Random forest model had the best performance,with the area under the curve of 0.9523.The risk factors for predicting CRE infection by the random forest model included 15 clinical data items,namely fever for more than 3 days,cerebral injury,drainage fluid sample,trunk surgery,first-level or special-level nursing,ICU treatment,procalcitonin,anti-anaerobic bacteria,the use of third-generation cephalosporins,age,pre-albumin,creatinine,white blood cell count,and albumin.Conclusion The CRE prediction model developed in this study has good predictive value and the risk factors have guiding significance for the early prevention and treatment of CRE infection in clinical practice.