An Analysis of Predictive Factors for Severe Neonatal Infection and the Construction of a Prediction Model

To investigate the primary predictive factors for the occurrence of severe neonatal infection, construct a prediction model and assess its effectiveness.

A total of 160 neonates hospitalised in the Department of Neonatology at Suixi County Hospital from January 2019 to June 2022 were retrospectively analysed. Clinical data was analyzed to determine the primary predictive factors for the occurrence of severe neonatal infection. Predictive efficacy was evaluated using a receiver operating characteristic curve, and a nomogram model was constructed according to the predictors. A bootstrap technique was used to verify the accuracy of the model.

The neonates were divided, based on the degree of infection, into a mild infection group (n = 80) and a severe infection group (n = 80) according to a 1:1 ratio. Multivariate logistic regression analysis showed that compared with the recovery stage, white blood cell count (WBC) and platelet count (PLT) in the two groups were significantly decreased in the early stage of infection, and the ratio of mean platelet volume to PLT, as well as C-reactive protein (CRP) and procalcitonin levels, was elevated (P < 0.05). The area under the curves (AUCs) of decreased WBC, decreased PLT and elevated CRP levels, and the combination of these three indicators, were 0.881, 0.798, 0.523 and 0.914, respectively. According to the filtered indicators, two models (a dichotomous variable equation model and a nomogram model) of continuous numerical variables were constructed, and their AUCs were 0.958 and 0.914, respectively. The calibration curve of the nomogram model was validated with a consistency index of 0.908 (95% confidence interval [0.862, 0.954]).

Decreased WBC and PLT levels and an elevated CRP level were the primary independent predictors of severe neonatal infection.