Diagnostic Algorithm Based on Machine Learning to Predict Complicated Appendicitis in Children Using CT, Laboratory, and Clinical Features

Abstract

To establish a diagnostic algorithm for predicting complicated appendicitis in children based on CT and clinical features. Methods: This retrospective study included 315 children (n = 198). Complicated appendicitis was defined as gangrenous or perforated appendicitis. The diagnostic algorithm was validated using a temporal cohort (n = 117). The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) from the receiver operating characteristic curve analysis were calculated to evaluate the diagnostic performance of the algorithm. Results: All patients with periappendiceal abscesses, periappendiceal inflammatory masses, and free air on CT were diagnosed with complicated appendicitis. In addition, intraluminal air, transverse diameter of the appendix, and ascites were identified as important CT findings for predicting complicated appendicitis. C-reactive protein (CRP) level, white blood cell (WBC) count, erythrocyte sedimentation rate (ESR), and body temperature also showed important associations with complicated appendicitis. The AUC, sensitivity, and specificity of the diagnostic algorithm comprising features were 0.91 (95% CI, 0.86–0.95), 91.8% (84.5–96.4), and 90.0% (82.4–95.1) in the development cohort, and 0.7 (0.63–0.84), 85.9% (75.0–93.4), and 58.5% (44.1–71.9) in test cohort, respectively. Conclusion: We propose a diagnostic algorithm based on a decision tree model using CT and clinical findings. This algorithm can be used to differentiate between complicated and noncomplicated appendicitis and to provide an appropriate treatment plan for children with acute appendicitis.

Keywords

• computed tomography
• algorithms
• children
• appendicitis
• perforated appendicitis