基于深度学习的创伤出血量分级预测模型研究  

Research on grading prediction model of traumatic hemorrhage volume based on deep learning

作　　者：郭程娱 韩有方 龚明慧 张红亮[2] 王俊康 张睿智 卢兵 李春平[3] 黎檀实[2] Guo Chengyu;Han Youfang;Gong Minghui;Zhang Hongliang;Wang Junkang;Zhang Ruizhi;Lu Bing;Li Chunping;Li Tanshi(School of Medicine,Nankai University,Tianjin 300071,China;Department of Emergency,First Medical Center,General Hospital of the PLA,Beijing 100853,China;School of Software,Tsinghua University,Beijing 100083,China)

机构地区：[1]南开大学医学院,天津300071 [2]解放军总医院第一医学中心急诊科,北京100853 [3]清华大学软件学院,北京100083

出　　处：《中华危重病急救医学》2022年第7期746-751,共6页Chinese Critical Care Medicine

基　　金：国家重点研发计划项目(2020YFC1512702)。

摘　　要：目的基于深度学习方法开发创伤出血量分级预测模型, 以辅助预测创伤动物出血量。方法基于中国人民解放军总医院构建的战创伤动物实验时效评估数据库中猪枪弹伤实验数据进行回顾性观察性研究。提取研究总体的出血量数据, 并按照出血量将其分为0~300 mL组、301~600 mL组、>600 mL组。采用生命体征指标作为预测变量、出血量分级作为结局变量, 基于4种传统机器学习和10种深度学习方法开发创伤出血量分级预测模型;采用实验室检验指标作为预测变量、出血量分级作为结局变量, 基于上述14种算法开发创伤出血量分级预测模型。通过准确率和受试者工作特征曲线下面积(AUC)对上述两组模型进行效果评价, 并将两组中的最优模型混合得到混合模型1;通过遗传算法进行特征选择, 并根据最佳特征组合构建混合模型2;最后, 将混合模型2部署于动物实验数据库系统中。结果纳入数据库中创伤动物96只, 其中0~300 mL组27只, 301~600 mL组40只, >600 mL组29只。在基于生命体征指标构建的14种模型中, 全卷积网络(FCN)模型为最优模型〔准确率为60.0%, AUC及95%可信区间(95%CI)为0.699(0.671~0.727)〕;在基于实验室检验指标构建的14种模型中, 循环神经网络(RNN)模型为最优模型〔准确率为68.9%, AUC(95%CI)为0.845(0.829~0.860)〕。FCN与RNN模型混合后得到混合模型1, 即RNN-FCN模型, 模型效果得到提升〔准确率为74.2%, AUC(95%CI)为0.847(0.833~0.862)〕;通过遗传算法进行特征选择, 根据筛选后的特征组合构建混合模型2, 即RNN-FCN^(*)模型, 进一步提升了模型效果〔准确率为80.5%, AUC(95%CI)为0.880(0.868~0.893)〕, 该模型包含10项指标, 分别为平均动脉压(MAP)、血细胞比容(HCT)、血小板计数(PLT)、血乳酸(Lac)、动脉血二氧化碳分压(PaCO_(2))、二氧化碳总量、血Na^(+)、阴离子隙(AG)、纤维蛋白原(FIB)、国际标准化比值(INR)。最�Objective To develop a grading prediction model of traumatic hemorrhage volume based on deep learning and assist in predicting traumatic hemorrhage volume.Methods A retrospective observational study was conducted based on the experimental data of pig gunshot wounds in the time-effect assessment database for experiments on war-traumatized animals constructed by the General Hospital of the Chinese People's Liberation Army.The hemorrhage volume data of the study population were extracted,and the animals were divided into 0-300 mL,301-600 mL,and>600 mL groups according to the hemorrhage volume.Using vital signs indexes as the predictive variables and hemorrhage volume grading as the outcome variable,trauma hemorrhage volume grading prediction models were developed based on four traditional machine learning and ten deep learning methods.Using laboratory test indexes as predictive variables and hemorrhage volume grading as outcome variables,trauma hemorrhage volume grading prediction models were developed based on the above fourteen methods.The effect of the two groups of models was evaluated by accuracy and area under the receiver operator characteristic curve(AUC),and the optimal models in the two groups were mixed to obtain hybrid model 1.Feature selection was conducted according to the genetic algorithm,and hybrid model 2 was constructed according to the best feature combination.Finally,hybrid model 2 was deployed in the animal experiment database system.Results Ninety-six traumatic animals in the database were enrolled,including 27 pigs in the 0-300 mL group,40 in the 301-600 mL group,and 29 in the>600 mL group.Among the fourteen models based on vital signs indexes,fully convolutional network(FCN)model was the best[accuracy:60.0%,AUC and 95%confidence interval(95%CI)was 0.699(0.671-0.727)].Among the fourteen models based on laboratory test indexes,recurrent neural network(RNN)model was the best[accuracy:68.9%,AUC(95%CI)was 0.845(0.829-0.860)].After mixing the FCN and RNN models,the hybrid model 1,namely RNN-FCN mo

关 键 词：战创伤 出血量 深度学习 预测模型 

分 类 号：R826.5[医药卫生—临床医学]