Artificial neural network predicts the need for therapeutic ERCP in patients with suspected choledocholithiasis

Background: Selection of patients with the highest probability for therapeutic ERCP remains an important task in a clinical workup of patients with suspected choledocholithiasis (CDL). Objective: To determine whether an artificial neural network (ANN) model can improve the accuracy of selecting patients with a high probability of undergoing therapeutic ERCP among those with strong clinical suspicion of CDL and to compare it with our previously reported prediction model. Design: Prospective, observational study. Setting: Single, tertiary-care endoscopy center. Patients: Between January 2010 and September 2012, we prospectively recruited 291 consecutive patients who underwent ERCP after being referred to our center with firm suspicion for CDL. Interventions: Predictive scores for CDL based on a multivariate logistic regression model and ANN model. Main Outcome Measurements: The presence of common bile duct stones confirmed by ERCP. Results: There were 80.4% of patients with positive findings on ERCP. The area under the receiver-operating characteristic curve for our previously established multivariate logistic regression model was 0.787 (95% CI, 0.720-0.854; P < .001), whereas area under the curve for the ANN model was 0.884 (95% CI, 0.831-0.938; P < .001). The ANN model correctly classified 92.3% of patients with positive findings on ERCP and 69.6% patients with negative findings on ERCP. Limitations: Only those variables believed to be related to the outcome of interest were included. The majority of patients in our sample had positive findings on ERCP. Conclusions: An ANN model has better discriminant ability and accuracy than a multivariate logistic regression model in selecting patients for therapeutic ERCP.