文献速递儿童呼吸儿童感染

青海地区儿童重症社区获得性肺炎风险预测模型的构建

Construction of a risk prediction model for severe community-acquired pneumonia in children in Qinghai region
RSS 订阅 · BMJ Paediatrics Open

本研究回顾性纳入2023年6月至2024年9月在青海大学附属医院儿科住院的29天至14岁CAP患儿,按7:3随机分为训练集345例和验证集149例,采用LASSO回归筛选预测因子并构建多因素logistic回归模型。模型基于咳嗽天数、CT实变模式、淋巴细胞百分比、降钙素原、CRP、ALT、AST、LDH、IL-6和IL-8共10项指标,训练集AUROC为0.863,验证集AUROC为0.829,校准曲线和决策曲线分析显示模型具有良好预测效能和临床实用性。

要点

  • 模型纳入咳嗽天数、CT实变模式、淋巴细胞百分比、降钙素原、CRP、ALT、AST、LDH、IL-6和IL-8共10项预测因子。
  • 训练集AUROC=0.863(95%CI 0.811-0.916),验证集AUROC=0.829(95%CI 0.732-0.927)。
  • DCA显示模型在临床阈值范围内净获益优于「全部治疗」或「全不治疗」策略。

核心结论

  • 基于10项临床指标构建的模型对青海地区儿童重症CAP具有良好预测效能,有助于早期识别和临床决策。

研究设计与样本

  • 回顾性纳入2023年6月至2024年9月青海大学附属医院儿科住院的29天至14岁CAP患儿,按7:3随机分为训练集345例和验证集149例。
  • 采用LASSO回归筛选预测因子,构建多因素logistic回归模型,以AUROC和校准曲线评估区分度与校准度,以DCA和CIC评估临床效用。

主要发现

  • LASSO和LR分析识别出咳嗽天数、CT实变模式、淋巴细胞百分比、降钙素原、CRP、ALT、AST、LDH、IL-6和IL-8为重症CAP的显著预测因子。
  • 训练集AUROC=0.863(95%CI 0.811-0.916;特异度=0.827,敏感度=0.809),验证集AUROC=0.829(95%CI 0.732-0.927;特异度=0.893,敏感度=0.714)。
  • Bootstrap验证(1000次迭代)和校准曲线确认模型稳健性,Hosmer-Lemeshow检验训练集p=0.416、验证集p=0.775。
  • DCA显示模型在临床阈值范围内净获益优于「全部治疗」或「全不治疗」策略。
  • CIC显示在阈值>0.5(训练集)和>0.4(验证集)时预测高风险病例与实际观察高度一致。

关键数值与推荐

  • 模型基于咳嗽天数、肺部实变部位、淋巴细胞百分比、降钙素原、CRP、ALT、AST、IL-6、IL-8和LDH共10项临床指标构建。
  • 训练集AUROC=0.863(95%CI 0.811-0.916),验证集AUROC=0.829(95%CI 0.732-0.927)。
  • 训练集特异度=0.827、敏感度=0.809;验证集特异度=0.893、敏感度=0.714。
  • Hosmer-Lemeshow检验训练集p=0.416,验证集p=0.775。

临床怎么用

  • 可利用列线图基于10项临床指标评估CAP患儿进展为重症的风险,辅助早期识别高危患儿并指导临床决策。
  • 模型在训练集和验证集中均显示良好区分度与校准度,DCA提示其净获益优于「全部治疗」或「全不治疗」策略。

局限性

  • 本研究为单中心回顾性研究,样本来自青海大学附属医院儿科,外部推广性需进一步验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Objective This study aims to identify risk factors associated with the progression of community-acquired pneumonia (CAP) to severe CAP in children from Qinghai Province and to develop a risk prediction model, thereby providing a basis for early identification of severe CAP in children and guiding clinical decision-making. Methods This study retrospectively enrolled paediatric patients (aged ≥29 days to ≤14 years) diagnosed with CAP and hospitalised in the Department of Pediatrics at Qinghai University Affiliated Hospital between June 2023 and September 2024. The patients were randomly allocated into a training cohort (n=345) and a validation cohort (n=149) at a 7:3 ratio. Predictors were selected via least absolute shrinkage and selection operator (LASSO) regression, and a multivariate logistic regression model (LR) was developed. Discrimination and calibration were assessed using the area under the receiver operating characteristic curve (AUROC) and calibration curves, while clinical utility was evaluated through decision curve analysis (DCA) and clinical impact curves (CIC). Results LASSO and LR analyses identified several significant predictors of severe paediatric CAP: duration of cough, CT consolidation patterns, lymphocyte percentage, procalcitonin, C-reactive protein (CRP), alanine aminotransferase (ALT), aspartate transaminase (AST), lactate dehydrogenase (LDH), interleukin (IL)-6 and IL-8. The R software-generated nomogram demonstrated strong predictive performance, with training set AUROC=0.863 (95% CI 0.811 to 0.916; specificity=0.827, sensitivity=0.809) and validation set AUROC=0.829 (95% CI 0.732 to 0.927; specificity=0.893, sensitivity=0.714). Bootstrap validation (1000 iterations) and calibration curves confirmed model robustness. Hosmer-Lemeshow tests showed excellent fit for both training (p=0.416) and validation sets (p=0.775). DCA revealed superior net benefit across clinical thresholds versus ‘treat-all’ or ‘treat-none’ strategies. CIC demonstrated close agreement between predicted and observed high-risk cases at thresholds >0.5 (training) and >0.4 (validation), confirming clinical utility. Conclusion In this study, we successfully constructed a model for predicting the occurrence of severe CAP in children in Qinghai based on 10 clinical indicators: number of days of coughing, site of lung solid involvement, percentage of lymphocytes, procalcitonin, CRP, ALT, AST, IL-6, IL-8 and LDH, which had a good predictive efficacy and was useful f

来源:BMJ Paediatrics Open,查看原文。版权归原作者所有。

引用

  1. BMJ Paediatrics Open:Construction of a risk prediction model for severe community-acquired pneumonia in children in Qinghai region

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。