Shuai Xianghua, Li Xiaoxia, Wu Yiling
Department of Neonatology, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Front Pediatr. 2022 Sep 14;10:924014. doi: 10.3389/fped.2022.924014. eCollection 2022.
To construct a prediction model based on the data of premature infants and to apply the data in our study as external validation to the prediction model proposed by Yuejun Huang et al. to evaluate the predictive ability of both models.
In total, 397 premature infants were randomly divided into the training set ( = 278) and the testing set ( = 119). Univariate and multivariate logistic analyses were applied to identify potential predictors, and the prediction model was constructed based on the predictors. The area under the curve (AUC) value, the receiver operator characteristic (ROC) curves, and the calibration curves were used to evaluate the predictive performances of prediction models. The data in our study were used in the prediction model proposed by Yuejun Huang et al. as external validation.
In the current study, endotracheal intubation [odds ratio () = 10.553, 95% confidence interval (): 4.959-22.458], mechanical ventilation ( = 10.243, 95% : 4.811-21.806), asphyxia ( = 2.614, 95% : 1.536-4.447), and antibiotics use ( = 3.362, 95% : 1.454-7.775) were risk factors for late-onset sepsis in preterm infants. The higher birth weight of infants ( = 0.312, 95% : 0.165-0.588) and gestational age were protective factors for late-onset sepsis in preterm infants. The training set was applied for the construction of the models, and the testing set was used to test the diagnostic efficiency of the model. The AUC values of the prediction model were 0.760 in the training set and 0.796 in the testing set.
The prediction model showed a good predictive ability for late-onset sepsis in preterm infants.
基于早产儿数据构建预测模型，并将本研究中的数据作为外部验证应用于黄跃军等人提出的预测模型，以评估两个模型的预测能力。
总共397例早产儿被随机分为训练集（n = 278）和测试集（n = 119）。应用单因素和多因素逻辑回归分析来识别潜在预测因素，并基于这些预测因素构建预测模型。采用曲线下面积（AUC）值、受试者工作特征（ROC）曲线和校准曲线来评估预测模型的预测性能。本研究中的数据被用于黄跃军等人提出的预测模型作为外部验证。
在本研究中，气管插管[比值比（OR）= 10.553，95%置信区间（CI）：4.959 - 22.458]、机械通气（OR = 10.243，95%CI：4.811 - 21.806）、窒息（OR = 2.614，95%CI：1.536 - 4.4,47）和使用抗生素（OR = 3.362，95%CI：1.454 - 7.775）是早产儿晚发性败血症的危险因素。婴儿较高的出生体重（OR = 0.312，95%CI：0.165 - 0.588）和胎龄是早产儿晚发性败血症的保护因素。训练集用于构建模型，测试集用于测试模型的诊断效率。预测模型在训练集中的AUC值为0.760，在测试集中为0.796。
该预测模型对早产儿晚发性败血症具有良好的预测能力。
