Retrospective Development of an AI Model Combining Ultrasound and Clinical Data for Pediatric Appendicitis Differentiation

TL;DR

An AI model combining ultrasound images and clinical data effectively differentiates complicated from uncomplicated appendicitis in children.

Contribution

A novel AI model integrating ultrasound and clinical data for diagnosing pediatric appendicitis is developed and validated.

Findings

The combined AI model achieved high accuracy (AUC: 0.940) in differentiating complicated from uncomplicated appendicitis.

The model's performance was comparable to senior surgeons and better than junior surgeons in internal validation.

Decision curve analysis confirmed the model's clinical utility over traditional methods.

Abstract

To differentiate complicated appendicitis (CA) from uncomplicated appendicitis (UA) in children, we developed and validated an artificial intelligence (AI) model using a multimodal approach integrating ultrasound images and clinical data.

A retrospective analysis was performed on 372 pathologically confirmed pediatric appendicitis cases (230 male, 142 female) from three centers, all with preoperative abdominal ultrasound. Deep learning (DL) features and radiomic features were extracted from appendiceal ultrasound images using deep transfer learning (DTL) and conventional radiomic methods, respectively. We selected 12 radiomic features, 9 DL features, and 3 clinical features—namely, white blood cell count (WBC), neutrophil count (NEU), and C-reactive protein (CRP)—for building the machine learning classification model. Based on these features, four distinct models were constructed: the Rad model (radiomic features only), the DL model (DL features only), the DTL model (combined radiomic and DL features), and the Combine model (integrating all three feature types: radiomic, DL, and clinical features). Model performance was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and the DeLong test. Finally, the combined model was compared to the performance of clinicians with varying levels of experience.

The combined model demonstrated consistently favorable performance across all cohorts (AUC: 0.940, 0.895, 0.866, and 0.783 for training and validation sets, respectively). The model's accuracy (0.862) and positive predictive value (0.896) were comparable to senior surgeons (0.741, 0.970) and superior to junior surgeons (0.672, 0.865) in the internal validation cohort. DCA confirmed the clinical utility of the combined model over conventional strategies.

Our ultrasound-based AI model provides reliable differentiation between CA and UA in children, offering potential value as a diagnostic support tool for clinical decision making.

Figures