Development and validation of a deep learning and radiomics combined model for differentiating complicated from uncomplicated acute appendicitis

Abstract

Abstract Background Nonoperative management (NOM) of uncomplicated acute appendicitis (AA) has been shown to be feasible; however, the pretreatment prediction of complicated/uncomplicated AA remains challenging. We developed a deep learning and radiomics combined model to differentiate complicated from uncomplicated AA. Methods This retrospective multicenter study included 1165 adult AA patients (training cohort, 700 patients; validation cohort, 465 patients) with available abdominal pelvic CT images. The reference standard for complicated/uncomplicated AA was surgery and pathology records. We developed our combined model with CatBoost based on the selected clinical characteristics, CT visual features, deep learning features, and radiomics features. We externally validated our combined model and compared it with the conventional combined model, the deep learning radiomics (DLR) model, and the radiologist’s visual diagnosis using receiver operating characteristic (ROC) curve analysis. Results In the training cohort, the area under the ROC curve (AUC) of our combined model in distinguishing complicated from uncomplicated AA was 0.816 (95% CI: 0.785–0.844). In the validation cohort, our combined model showed robust performance across the three centers, with AUCs of 0.836 (95% CI: 0.785–0.879), 0.793 (95% CI: 0.695–0.872), and 0.723 (95% CI: 0.632–0.802). In the total validation cohort, our combined model (AUC = 0.799) performed better than the conventional combined model, DLR model and radiologist’s visual diagnosis (AUC = 0.723, 0.755, and 0.679; all P < 0.05). Decision curve analysis showed that our combined model provided greater net benefit in predicting complicated AA than the other three models. Conclusions Our combined model allows the accurate differentiation of complicated and uncomplicated AA.