Development of a nomogram to predict acute liver injury in children with Mycoplasma pneumoniae pneumonia.

OBJECTIVE: To construct and validate a nomogram for predicting acute liver injury in children with Mycoplasma pneumoniae pneumonia (MPP). METHODS: This retrospective study included 964 hospitalized children with confirmed MPP from January 2021 to December 2024. Acute liver injury was defined as the study endpoint. Missing data were handled by multiple imputation (m = 5). The cohort was divided into a training set and a validation set at a ratio of 7:3 using stratified random sampling. Least absolute shrinkage and selection operator (LASSO)-logistic regression was used for feature selection, and the selected variables were entered into multivariable logistic regression to construct a nomogram. Model performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). RESULTS: Among the 964 children, 131 developed acute liver injury, corresponding to an incidence of 13.6%. The cohort was divided into a training set of 676 children, including 92 with acute liver injury, and a validation set of 288 children, including 39 with acute liver injury. Baseline characteristics were comparable between the training and validation sets (P > 0.05). LASSO regression identified 11 candidate predictors: gender, age, body temperature ≥37.5 °C, history of allergy, neutrophil percentage, lymphocyte percentage, D-dimer, total protein, γ-glutamyl transpeptidase (GGT), lactate dehydrogenase (LDH), and creatine kinase isoenzyme MB (CK-MB). In multivariable analysis, female gender, GGT, LDH, and CK-MB were independently associated with an increased risk of liver injury, whereas age was negatively associated with liver injury. D-dimer showed marginal statistical significance. The nomogram showed good discrimination, with an area under the curve (AUC) of 0.837 in the training set and 0.874 in the validation set. Calibration curves showed acceptable agreement between predicted and observed risks, and DCA suggested potential clinical net benefit within a certain threshold range. CONCLUSION: This nomogram, based on routinely available clinical and laboratory indicators, may help identify children with MPP at increased risk of acute liver injury and support early liver function monitoring. Further prospective multicenter validation is needed.