Figure 5

(A) Nomogram for the prediction of neonatal sepsis. The nomogram consists of graph lines that include risk factors (maternal age, GDM,forceps assisted delivery,umbilical cord winding,newborn gender), individual scores (Points), total scores (Total Points), and event risk (neonatal clinical sepsis). The line segment corresponding to each risk factor is marked with a scale, which represents the range of possible values of the factor, and the length of the line segment reflects the contribution of the factor to the outcome event. “Points” at the top of the graph indicate the corresponding scores of risk factors under different values. The total score of all the individual scores of the risk factors is “Total Points”, which corresponds to “neonatal clinical sepsis” at the bottom of the graph, which represents the predicted probability of progression to neonatal clinical sepsis during hospitalisation. GDM gestational diabetes mellitus. (B) ROC curve for modelling set (Bootstrap resampling times = 500). The area under the ROC curve (AUC) was 0.713 (95% CI 0.635–0.773). Blue shading shows the bootstrap estimated 95% CI with the AUC. ROC receiver operating characteristic, AUC area under the ROC. (C) Calibration curve of the nomogram. The x-axis represents the risk predicted by the nomogram. The y-axis represents the patients diagnosed with neonatal sepsis. The diagonal dotted line represents a perfect prediction by an ideal model. The apparent line represents the performance of the nomogram. (D) Decision curve analysis in prediction of neonatal sepsis. The black line represents no neonatal sepsis in all infants and a net profit of 0;The gray line represents the occurrence of neonatal sepsis in all infants, and the net gain rate is the slope of the inverse sloping line.The red line represents the DCA curve of this model. When the threshold probability of high risk is between the gray line and the red line (0.25–1.0), it is feasible for this model to predict the occurrence of neonatal sepsis, and the net gain rate of children is high.