基于机器学习预测微创心脏外科手术患者术中红细胞输注概率的研究  

Machine learning to predict the probability of intraoperative red blood cell transfusion in minimally invasive cardiac surgery

作　　者：黄培菊 王晟 梁杰贤[1] Huang Peiju;Wang Sheng;Liang Jiexian(Department of Anesthesiology,Guangdong Cardiovascular Institute,Guangdong Provincial People's Hospital,Guangdong Academy of Medical Sciences,Guangzhou 510080,China)

机构地区：[1]广东省心血管病研究所,广东省人民医院,广东省医学科学院麻醉科,广州510080 [2]首都医科大学附属北京安贞医院麻醉中心

出　　处：《北京医学》2024年第4期313-324,329,共13页Beijing Medical Journal

基　　金：北京市自然科学基金(7242046);北京市卫健委第三批高层次公共卫生技术人才建设项目(领军人才-03-10);北京市临床重点专科建设项目;广州市科技计划(202201011136);国家重点研发计划(2022YFC2407406)。

摘　　要：目的探讨机器学习预测微创心脏外科手术(minimally invasive cardiac surgery,MICS)患者术中红细胞输注概率的可行性。方法选取2019年6月至2022年12月广东省人民医院行MICS的患者1837例,按照8.5∶1.5的比例随机分层划分为训练集(1562例)和测试集(275例)。使用训练集在H2O.ai平台自动进行模型训练,然后利用测试集对模型进行内部验证以选择最佳模型,并对该模型进行可视化解释。结果1837例MICS患者中,男820例,女1017例,年龄18~83岁,平均(48.3±15.0)岁。MICS术中输注红细胞的发生率为11.3%(207/1837)。自动化建立的59个机器学习模型中,基于梯度提升机(gradient boosting machine,GBM)算法的模型预测性能最佳(AUC=0.880,95%CI:0.832~0.927,P=0.029)。GBM模型中最关键的变量是体外循环(cardiopulmonary bypass,CPB)最低红细胞压积(hematocrit,HCT),其权重百分比为23.54%,其次是术前HCT(16.01%)、CPB时间(9.09%)、外科医生团队(8.36%)、BMI(4.94%)、身高(4.47%)、心脏停搏液类型(4.45%)等。结论在建立的机器学习模型中,基于GBM算法的模型表现出最佳性能,可以有效、准确地预测红细胞输注风险,提供了一个可解释的预测模型,有助于临床医生推进MICS患者的科学用血。Objective To explore the feasibility of machine learning in predicting the probability of intraoperative red blood cell transfusion in patients undergoing minimally invasive cardiac surgery(MICS).Methods A total of 1837 patients who underwent MICS in Guangdong Provincial People's Hospital from June 2019 to December 2022 were selected,and were randomly divided into training sets(1562 cases)and testing sets(275 cases)in an 8.5:1.5 ratio.The training set was used for automated model training on the H2O.ai platform.And the testing set was used for internal validation to select the best model,which was further visually interpreted.Results Among 1837 MICS patients,there were 820 males and 1017 females,aged from 18 to 83 years,with an average age of(48.3±15.0)years.The incidence of intraoperative red blood cell transfusion in MICS was 11.3%(207/1837).Among the 59 machine learning models developed through automation,the model based on the gradient boosting machine(GBM)algorithm exhibited the best predictive performance(AUC=0.880,95%CI:0.832-0.927,P=0.029).The most critical variables in the GBM model were the nadir hematocrit(HCT)during cardiopulmonary bypass(CPB),with a weight percentage of 23.54%,followed by preoperative HCT(16.01%),CPB duration(9.09%),surgeon team(8.36%),BMI(4.94%),height(4.47%),and type of cardioplegia solution(4.45%).Conclusions In the established machine learning models,the GBM model outperformed other machine learning models in predicting intraoperative red blood cell transfusion in MICS.This innovative approach provides an interpretable predictive model that can assist clinical practitioners in evidence-based transfusion practices for patients undergoing MICS.

关 键 词：微创心脏外科手术 红细胞输注 机器学习 预测模型 

分 类 号：R654.2[医药卫生—外科学] TP181[医药卫生—临床医学]