To Scan or Not to Scan: Development of a Clinical Decision Support Tool to Determine if Imaging Would Aid in the Diagnosis of Appendicitis

Background Appendicitis is one of the most common surgically treated diseases in the world. CT scans are often over-utilized and ordered before a surgeon has evaluated the patient. Our aim was to develop a tool using machine learning (ML) algorithms that would help determine if there would be benefit in obtaining a CT scan prior to surgeon consultation. Methods Retrospective chart review of 100 randomly selected cases who underwent appendectomy and 100 randomly selected controls was completed. Variables included components of the patient’s history, laboratory values, CT readings, and pathology. Pathology was used as the gold standard for appendicitis diagnosis. All variables were then used to build the ML algorithms. Random Forest (RF), Support Vector Machine (SVM), and Bayesian Network Classifiers (BNC) models with and without CT scan results were trained and compared to CT scan results alone and the Alvarado score using area under the Receiver Operator Curve (ROC), sensitivity, and specificity measures as well as calibration indices from 500 bootstrapped samples. Results Among the cases that underwent appendectomy, 88% had pathology-confirmed appendicitis. All the ML algorithms had better sensitivity, specificity, and ROC than the Alvarado score. SVM with and without CT had the best indices and could predict if imaging would aid in appendicitis diagnosis. Conclusion This study demonstrated that SVM with and without CT results can be used for selective imaging in the diagnosis of appendicitis. This study serves as the initial step and proof-of-concept to externally validate these results with larger and more diverse patient population.