基于列线图建立先天性心脏病患儿并发肺部感染的风险预测模型

The risk prediction model of pulmonary infection in children with congenital heart disease was established based on the line graph

目的 分析先天性心脏病(CHD)患儿并发肺部感染的危险因素,并构建风险列线图预测模型。方法 选取靖江市人民医院2021年1月至2021年12月收治的246例CHD患儿作为研究对象,根据是否发生肺部感染,分为对照组(n=201)和感染组(n=45)。分析CHD患儿的临床资料,采用单因素和Logistic回归分析筛选CHD并发肺部感染的危险因素,再构建列线图模型并进行拟合优度检验。结果 246例CHD患儿并发肺部感染有45例,其发生率为18.29%;NYHA心功能分级>Ⅱ级、左室射血分数≤40%、免疫缺陷/功能低下、侵袭性操作、肺部瘀血、ALB≤35g/L和PCT>0.5μg/L是CHD患儿并发肺部感染的独立危险因素(P<0.05);模型验证结果:C-index为0.840,预测值与实测值走势基本一致,AUC为0.826,阈值概率范围在8%~95%时净获益值较高。结论 构建的列线图模型可准确评估和量化CHD并发肺部感染的风险,有助于医务人员快速、有效识别高风险CHD患儿,并及时予以干预措施,降低肺部感染的发生概率。

Objective To analyze the risk factors of pulmonary infection in children with congenital heart disease(CHD),and to construct a risk nomogram prediction model.Methods A total of 246 children with CHD admitted to Jingjiang People’s Hospital from January 2021 to December 2021 were selected as the research objects.According to whether pulmonary infection occurred,they were divided into control group(n=201)and infection group(n=45).The clinical data of children with CHD were analyzed,and the risk factors of CHD complicated with pulmonary infection were screened by univariate and Logistic regression analysis.The nomogram model was constructed and the goodness-of-fit test was performed.Results Among 246 children with CHD,45 were complicated with pulmonary infection(18.29%).NYHA cardiac function class>class II,left ventricular ejection fraction≤40%,immunodeficiency/hypofunction,invasive operation,pulmonary blood congestion,ALB≤35 g/L and PCT>0.5μg/L were independent risk factors for pulmonary infection in children with CHD(P<0.05).Model validation results:The C-index was 0.840,the predicted value was basically consistent with the measured value,the AUC was 0.826,and the net benefit value was higher when the threshold probability range was 8%‒95%.Conclusion The constructed nomogram model can accurately assess and quantify the risk of CHD complicated with pulmonary infection,which is helpful for medical staff to quickly and effectively identify children with high-risk CHD,and take timely intervention measures to reduce the probability of pulmonary infection.