Nomogram for predicting fulminant necrotizing enterocolitis

Abstract

Background Fulminant necrotizing enterocolitis (FNEC) is the most serious subtype of NEC and has a high mortality rate and a high incidence of sequelae. Onset prediction can help in the establishment of a customized treatment strategy. This study aimed to develop and evaluate a predictive nomogram for FNEC. Methods We conducted a retrospective observation to study the clinical data of neonates diagnosed with NEC (Bell stage ≥ IIB). Neonates were divided into the FNEC and NEC groups. A multivariate logistic regression model was used to construct the nomogram model. The performance of the nomogram was assessed using area under the curve, calibration analysis, and decision curve analysis. Results A total of 206 neonate cases were included, among which 40 (19.4%) fulfilled the definition of FNEC. The identified predictors were assisted ventilation after NEC onset; shock at NEC onset; feeding volumes before NEC onset; neutrophil counts on the day of NEC onset; and neutrophil, lymphocyte, and monocyte counts on day 1 after NEC onset. The nomogram exhibited good discrimination, with an area under the receiver operating characteristic curve of 0.884 (95% CI 0.825–0.943). The predictive model was well calibrated. Decision curve analysis confirmed the clinical usefulness of this nomogram. Conclusion A nomogram with a potentially effective application was developed to facilitate the individualized prediction of FNEC, with the hope of providing further direction for the early diagnosis of FNEC and timing of intervention.

The risk prediction models of neonatal necrotizing enterocolitis in China: a systematic review

“…The 10 included articles are all from China [9-18],with 7 retrospective cohort studies and 3 case-control studies.One of Wang’s [18]studies is a doctoral thesis, involving three predictive models, represented by “Wang 1”, “Wang 2”, and “Wang 3” respectively in the following text.The characteristics of the study are shown in Table 1.…”

“…A total of 12 NEC risk prediction models were established in the 10 included literature, with a focus on premature infants and mostly single center studies,the total sample size is 177-1173.In terms of model building methods, ten models [9,[11][12][13][14][15][16]18] only used logistic regression algorithm, one model [10] used four algorithms: logistic regression, support vector machine, multilayer perceptron, and extreme gradient boosting, and one model [17] used three algorithms: artificial neural network, decision tree, and extreme gradient boosting.The modeling is detailed in Table 3.…”

“…Five models [9][10][11][16][17] were validated internally only, four models [12][13][14][15] used both internaland external validation, and three models [18] did not report a validation methodology or did not perform validation.Nine models [9][10]13,[15][16][17][18] reported that the area under the curve (AUC) of the working characteristics of the subjects ranged from 0.716 to 0.947, all of which were above 0.7. Three models [11][12]14] reported C indices ranging from 0.844 to 0.973, all above 0.8, indicating good predictive performance.Three models [10][11]17] did not report or evaluate model calibration, while the rest were evaluated and the model fit was good (P>0.05).The vastmajority of models report specific presentation forms, mostly presented in the form of nomogram.The performance evaluation of the model is detailed in Table 3.…”