目的 基于新生儿的一般临床特征和初始血常规指标构建新生儿败血症（NS）的 Nomogram早期预测模型。 方法 回顾性分析MIMICⅢ数据库中首次入住NICU并在入院后完善血常规检查的新生儿资料。采用LASSO?Logistic回归的方式建立NS预测模型并绘制Nomogram图，采用Bootstrap重采样1 000次的方法进行内部验证，使用来自中国郑州大学第一附属医院的新生儿数据进行了外部验证。采用受试者工作特征曲线下面积（AUROC）、C-index指数、校准曲线和决策曲线分析来评价预测性能。 结果 在MIMICⅢ数据库中，共纳入3 001例新生儿患者，其中185例被诊断为NS。LASSO?Logistic回归模型显示，是否发生呼吸窘迫综合征、胎龄、出生体质量、初始血常规检查中红细胞计数、白细胞计数、淋巴细胞百分比、中性粒细胞百分比为NS的独立预测因素；将以上指标建立Nomogram预测模型，模型的AUROC = 0.860。经内外部验证，模型的预测性能良好。 结论 本研究构建了一个参数简单的NS预测模型，模型的预测性能良好，能够帮助临床医生及早识别高风险患儿。

Objective To establish a Nomogram predictive model for Neonatal Sepsis （NS） based on the general characteristics and initial complete blood count of neonates. Methods Retrospective analysis was conducted on the clinical data of newborns who were admitted for the first time to NICU and completed blood routine examination after admission in the MIMIC Ⅲ database. The LASSO?Logistic regression was used to investigate the prediction factors of NS， and then Nomogram prediction model was established. Internal validation was performed using bootstrap resampling with 1000 iterations. External validation of the model was performed using the data from newborns admitted to the First Affiliated Hospital of Zhengzhou University. We evaluated the predictive performance by Area Under the Receiver Operating Characteristic Curve （AUROC）， C?index， calibration curve， and decision curve analysis （DCA）. Results Among the 3，001 neonates， 185 were diagnosed with NS. The Nomogram model was constructed based on indicators such as respiratory distress syndrome， gestational age， birthweight， and initial hematological parameters （red blood cell count， white blood cell count， lymphocyte percentage， neutrophil percentage）， exhibiting good predictive performance with an AUROC of 0.860. Satisfactory predictive abilities were confirmed through both internal and external validation. Conclusion This study developed and validated a well?performing Nomogram prediction model. With simple parameters， it can help clinicians identify newborns at high risk early.