基于人工神经网络建立社区获得性肺炎并发急性呼吸窘迫综合征的预测模型  

Establishing prediction model of community-acquired pneumonia complicated with acute respiratory distress syndrome based on artificial neural network

作　　者：莫继朋 贾中芝 汤艳杨 明夏 秦辉 Mo Jipeng;Jia Zhongzhi;Tang Yan;Yang Mingxia;Qin Hui(Graduate School,Bengbu Medical College,Bengbu 233000,Anhui,China;Department of Critical Care Medicine,Changzhou Second People's Hospital Affiliated to Nanjing Medical University,Changzhou 213003,Jiangsu,China;Department of Interventional and Vascular Surgery,Changzhou Second People's Hospital Affiliated to Nanjing Medical University,Changzhou 213003,Jiangsu,China;Department of Respiratory and Critical Care Medicine,Changzhou Second People's Hospital Affiliated to Nanjing Medical University,Changzhou 213003,Jiangsu,China)

机构地区：[1]蚌埠医学院研究生学院,安徽蚌埠233000 [2]南京医科大学附属常州第二人民医院重症医学科,江苏常州213003 [3]南京医科大学附属常州第二人民医院介入血管科,江苏常州213003 [4]南京医科大学附属常州第二人民医院呼吸与危重症医学科,江苏常州213003

出　　处：《中华危重病急救医学》2022年第4期367-372,共6页Chinese Critical Care Medicine

基　　金：国家自然科学基金(81472199)。

摘　　要：目的探讨社区获得性肺炎(CAP)患者并发急性呼吸窘迫综合征(ARDS)的独立危险因素,以及基于人工神经网络模型预测CAP患者发生ARDS的准确性和预防价值。方法采用病例对照研究方法,收集2020年2月至2021年2月南京医科大学附属常州第二人民医院综合重症监护病房和呼吸内科收治的符合入选标准的414例CAP患者的临床资料,根据是否并发ARDS分为两组。统计两组患者入院24 h内的临床数据,通过单因素分析筛选出发生ARDS的影响因素,并构建人工神经网络模型;通过人工神经网络模型输入层自变量(即单因素分析得出的影响因素)对输出层因变量(即是否发生ARDS)影响的重要程度,绘制出自变量重要性的条形图;将人工神经网络建模数据对按照7∶3的比例随机分为训练组(n=290)和验证组(n=124),分别计算两组模型的总体预测准确性,并绘制受试者工作特征曲线(ROC曲线),计算ROC曲线下面积(AUC)。结果414例患者均纳入分析,其中发生ARDS患者82例,未发生ARDS患者332例。单因素分析显示,两组患者性别、年龄、心率(HR)、最高收缩压(MSBP)、最大呼吸频率(MRR)、入院来源、C-反应蛋白(CRP)、降钙素原(PCT)、红细胞沉降率(ESR)、中性粒细胞计数(NEUT)、嗜酸粒细胞计数(EOS)、纤维蛋白原等量单位(FEU)、活化部分凝血活酶时间(APTT)、总胆红素(TBil)、白蛋白(ALB)、乳酸脱氢酶(LDH)、血肌酐(SCr)、血红蛋白(Hb)、血糖(GLU)水平差异均有统计学意义,可能是CAP患者并发ARDS的危险因素;将以上19个危险因素作为输入层、是否发生ARDS作为输出层,构建人工神经网络模型;其中输入层自变量中对神经网络模型预测结果影响权重最大的5个指标依次为LDH(100.0%)、PCT(74.4%)、FEU(61.5%)、MRR(56.9%)、APTT(51.6%),提示这5个指标对CAP患者发生ARDS的影响程度较大。训练组人工神经网络模型总体预测准确性为94.1%(273/290),验证组模型总�Objective To investigate the independent risk factors of community-acquired pneumonia(CAP)complicated with acute respiratory distress syndrome(ARDS),and the accuracy and prevention value of ARDS prediction based on artificial neural network model in CAP patients.Methods A case-control study was conducted.Clinical data of 414 patients with CAP who met the inclusion criteria and were admitted to the comprehensive intensive care unit and respiratory department of Changzhou Second People's Hospital Affiliated to Nanjing Medical University from February 2020 to February 2021 were analyzed.They were divided into two groups according to whether they had complicated with ARDS.The clinical data of the two groups were collected within 24 hours after admission,the influencing factors of ARDS were screened out by univariate analysis,and the artificial neural network model was constructed.Through the artificial neural network model,the importance of input layer independent variables(that was,the influence factors obtained from univariate analysis)on the output layer dependent variables(whether ARDS occurred)was drawn.The artificial neural network modeling data pairs were randomly divided into training group(n=290)and verification group(n=124)in a ratio of 7∶3.The overall prediction accuracy of the training group and the verification group was calculated respectively.At the same time,the receiver operator characteristic curve(ROC curve)was drawn,and the area under the ROC curve(AUC)was calculated.Results All 414 patients were enrolled in the analysis,including 82 patients with ARDS and 332 patients without ARDS.Univariate analysis showed that gender,age,heart rate(HR),maximum systolic blood pressure(MSBP),maximum respiratory rate(MRR),source of admission,C-reactive protein(CRP),procalcitonin(PCT),erythrocyte sedimentation rate(ESR),neutrophil count(NEUT),eosinophil count(EOS),fibrinogen equivalent unit(FEU),activated partial thromboplastin time(APTT),total bilirubin(TBil),albumin(ALB),lactate dehydrogenase(LDH),serum creatin

关 键 词：社区获得性肺炎 急性呼吸窘迫综合征 预测模型 人工神经网络 

分 类 号：R563.1[医药卫生—呼吸系统] R563.8[医药卫生—内科学]