川崎病并发冠状动脉病变风险的列线图模型的构建与分析

Establishment and analysis of Nomogram model for risk of Kawasaki disease complicated with coronary artery lesions

目的建立预测川崎病(KD)并发冠状动脉病变(CAL)风险的列线图模型。方法回顾性分析KD患儿的临床资料及血液学指标。根据超声心动图对冠状动脉的检测结果将患儿分为冠状动脉病变组(CAL组)70例和非冠状动脉病变组(NCAL组)95例。采用最小绝对值收敛和选择算子、套索算法(LASSO)回归分析KD合并CAL风险的危险因素,纳入多因素Logistic回归建立预测模型构建列线图,再通过受试者工作特征(ROC)曲线、校正曲线、决策曲线分析3个层面对模型进行验证,评估模型的优劣性。结果采用LASSO回归筛选出5个预测因子,即发热时间≥10 d、合并支原体感染、白细胞(WBC)>20×10^(9)/L、血小板(PLT)计数、C反应蛋白(CRP)与白蛋白(ALB)比值。纳入Logistic回归并构建列线图,经验证列线图ROC曲线的曲线下面积(AUC)为0.841(95%CI为0.782~0.900),灵敏度为85.7%,特异度为71.6%。结论本研究所建立的KD并发CAL预测模型具有良好的区分度与准确性,有助于临床工作者筛选出CAL的高危患儿。

Objective To establish a Nomogram model for predicting the risk of Kawasaki disease(KD)complicated with coronary artery lesions(CAL).MethodsThe clinical data and hematological indexes of children with KD were retrospectively analyzed.According to the results of coronary artery detection by echocardiography,the children were divided into coronary artery lesions group(CAL group)with 70 cases and non-coronary artery lesions group(NCAL group)with 95 cases.The risk factors of KD complicated with CAL were analyzed regressively by minimum absolute value convergence and selection operator as well as the least absolute shrinkage and selection operator(LASSO)algorithm,and these factors were incorporated intomultivariate Logistic regression for establishing the prediction model and constructing the Nomogram.The model was verified and the advantages and disadvantages were evaluated by receiver operating characteristic(ROC)curve,correction curve and decision curve analysis.ResultsFive predictors were screened by LASSO regression,includingduration of fever≥10 d,mycoplasma infection,white blood cell(WBC)count>20×10^(9)/L,platelet(PLT)count,C-reactive protein(CRP)to serum albumin(ALB)ratio.The five predictors were included in Logistic regression to construct a Nomogram;after verification,the area under the curve(AUC)of Nomogram ROC curve was 0.841(95%CI,0.782 to 0.900),the sensitivity was 85.7%,and the specificity was 71.6%.ConclusionThe established prediction model in the study for KD complicated with CAL has good discrimination and accuracy,which is helpful for clinical workers to screen out high-risk children with CAL.