Search

Objective: This study aims to construct an artificial intelligence (AI) model capable of effectively discriminating between abdominal Henoch-Schönlein purpura (AHSP) and acute appendicitis (AA) in pediatric patients., Methods: A total of 6965 participants, comprising 2201 individuals with AHSP and 4764 patients with AA, were enrolled in the study. Additionally, 53 laboratory indicators were taken into consideration. Five distinct artificial intelligence (AI) models were developed employing machine learning algorithms, namely XGBoost, AdaBoost, Gaussian Naïve Bayes (GNB), MLPClassifier (MLP), and support vector machine (SVM). The performance of these prediction models was assessed through receiver operating characteristic (ROC) curve analysis, calibration curve assessment, and decision curve analysis (DCA)., Results: We identified 32 discriminative indicators (p < .05) between AHSP and AA. Five indicators, namely the lymphocyte ratio (LYMPH ratio), eosinophil ratio (EO ratio), eosinophil count (EO count), neutrophil ratio (NEUT ratio), and C-reactive protein (CRP), exhibited strong performance in distinguishing AHSP from AA (AUC ≥ 0.80). Among the various prediction models, the XGBoost model displayed superior performance evidenced by the highest AUC (XGBoost = 0.895, other models < 0.89), accuracy (XGBoost = 0.824, other models < 0.81), and Kappa value (XGBoost = 0.621, other models < 0.60) in the validation set. After optimization, the XGBoost model demonstrated remarkable diagnostic performance for AHSP and AA (AUC > 0.95). Both the calibration curve and decision curve analysis suggested the promising clinical utility and net benefits of the XGBoost model., Conclusion: The AI-based machine learning model exhibits high prediction accuracy and can differentiate AHSP and AA from a data-driven perspective., (© 2023 Asia Pacific League of Associations for Rheumatology and John Wiley & Sons Australia, Ltd.)

Objective: To study and develop a predictive model for the differential diagnosis of acute appendicitis (AA) and Henoch-Schonlein purpura (HSP) in children and to validate the model internally and externally. Methods: The complete data of AA and HSP cases were retrospectively analyzed and divided into internal and external verification groups. SPSS software was used for single-factor analysis and screening of independent variables, and R software was used for the development and verification of the diagnostic model. Lasso regression analysis was used to screen predictors and Lasso-logistic regression model was constructed, and K-fold cross-validation was used for the internal verification. In addition, nonfever patients were selected for model development and validation in the same way. Receiver operating characteristic (ROC) curves and calibration curves were drawn, respectively, to evaluate the 2 models. Results: Internal development and validation of the model showed that fever, neutrophil ratio (NEUT%), albumin (ALB), direct bilirubin (DBIL), C-reactive protein (CRP), and K were predictive factors for the diagnosis of HSP. The model was presented in the form of a nomogram, and the area under ROC curve of the development group and verification group was 0.9462 (95% confidence interval [CI] = 0.9402-0.9522) and 0.8931 (95% CI = 0.8724-0.9139), respectively. In the model of patients without fever, NEUT%, platelets (PLT), ALB, DBIL, alkaline phosphatase (ALP), CRP, and K were predictive factors for the diagnosis of HSP, and the area under ROC curve of the development group and verification group was 0.9186 (95% CI = 0.908-0.9293) and 0.8591 (95% CI = 0.8284-0.8897), respectively. Conclusion: In this study, 2 diagnostic models were constructed for fever or not, both of which had good discrimination and calibration, and were helpful to distinguish AA and HSP in children.