A machine learning-based choledocholithiasis prediction tool to improve ERCP decision making: a proof-of-concept study

Abstract

Background: Prior studies have demonstrated that existing guidelines to predict choledocholithiasis have limited accuracy, leading to overutilization of ERCP. Improved stratification may allow for appropriate patient selection for ERCP and the use of lower-risk modalities (i.e. EUS and MRCP). Methods: A machine learning model was developed using patient information from two published cohort studies originally used to evaluate performance of published guidelines in predicting choledocholithiasis. Prediction models were developed using the gradient boosting (GBM) machine learning method. GBM performance was evaluated using 10-fold cross-validation and area under the receiver operating curve (AUC). Important predictors of choledocholithiasis were identified based on relative importance in GBM. Results: 1,378 patients (mean age 43.3 years; 55.5% females) were included in the GBM model and 59.4% had choledocholithiasis. Eight variables were identified as predictors of choledocholithiasis. The GBM model was evaluated with 10-fold cross-validation and had an accuracy of 71.5±2.5% (AUC 0.79±0.06) and performed better than the 2019 ASGE guidelines (accuracy 62.4±2.6%, AUC 0.63±0.03) and the ESGE guidelines (accuracy 62.8±2.6%, AUC 0.67±0.02). The GBM model correctly categorized 22% of patients directed to unnecessary ERCP by the ASGE guidelines and appropriately recommended 48% of ERCPs incorrectly rejected by the ESGE guidelines as the next step in the management. Conclusions: A machine learning-based tool was created that provides a real-time, personalized, objective probability of choledocholithiasis and ERCP recommendations. This more accurately directs ERCP use than the existing ASGE and ESGE guidelines and has the potential to reduce morbidity and healthcare costs associated with ERCP or missed choledocholithiasis.

Development and validation of a predictive model for choledocholithiasis

“…While the cutoff points suggested by ASGE were applied based on consensus, our study, along with prior research, indicates that the risk assignment for specific clinical and laboratory parameters-such as pancreatitis, bilirubin levels, and the diameter of the CBD-may exhibit variations. Steinway et al, 21 Zhang et al, 22 and Dalai et al 11 developed machine learning prediction models; nevertheless, we contend that our model possesses the ease of use and applicability to employ common variables outlined by the ASGE, making it adaptable in any setting.…”

A ghost in the machine: is machine learning necessary for prediction of choledocholithiasis?

“…In this issue of Endoscopy, Steinway et al [1] present data using a gradient boosting machine learning model to predict the presence of CBD stones in patients with suspected choledocholithiasis. The goal of this research was to improve upon current stratification methods in patients with suspected choledocholithiasis to mitigate the risks associated with unnecessary ERCP procedures.…”

Considerations and prospects for validating a machine learning-based choledocholithiasis prediction model

“…

We are writing to express our great interest in the recent study by Steinway et al [1], which presents an impressive machine learning-based choledocholithiasis prediction model. The study demonstrated the feasibility of machine learning in gastroenterology, showing its strong clinical utility.

…”