Abstract
OBJECTIVE: To explore the surgical risk variables in patients with necrotizing enterocolitis (NEC) and develop a nomogram model for predicting the surgical intervention timing of NEC. METHODS: Infants diagnosed with NEC were enrolled in our study. We gathered information from clinical data, laboratory examinations, and radiological manifestations. Using LASSO (least absolute shrinkage and selection operator) regression analysis and multivariate logistic regression analysis, a clinical prediction model based on the logistic nomogram was developed. The performance of the nomogram model was evaluated using the receiver operating characteristic (ROC) curve, calibration curves, and decision curve analysis (DCA). RESULTS: A surgical intervention risk nomogram based on hypothermia, absent bowel sounds, WBC > 20 × 10(9)/L or < 5 × 10(9)/L, CRP > 50 mg/L, pneumatosis intestinalis, and ascites was practical, had a moderate predictive value (AUC > 0.8), improved calibration, and enhanced clinical benefit. CONCLUSIONS: This simple and reliable clinical prediction nomogram model can help physicians evaluate children with NEC in a fast and effective manner, enabling the early identification and diagnosis of children at risk for surgery. It offers clinical revolutionary value for the development of medical or surgical treatment plans for children with NEC.