Artificial Intelligence-Based Prediction of Pancreatic Stone Clearance in Pancreatolithiasis Using Pretreatment CT Images and Clinical Features

Background/Objectives: Nonsurgical treatment for pancreatolithiasis is widely performed. However, treatment success remains difficult to predict before treatment initiation, complicating the selection of an appropriate treatment strategy. This study aimed to predict pancreatic stone clearance after nonsurgical treatment for pancreatolithiasis associated with chronic pancreatitis by integrating pretreatment computed tomography (CT) images and clinical information using deep learning and machine learning models. Methods: Of 195 patients with pancreatolithiasis associated with chronic pancreatitis who underwent nonsurgical treatment, including extracorporeal shock wave lithotripsy, at our institution between 1992 and 2024, only 91 (47%) had extractable pretreatment noncontrast abdominal CT images and were included in the AI analysis. Multiple deep learning models (VGG16/19, InceptionV3, ResNet50, DenseNet121/169/201, Vision Transformer, and Swin Transformer) were trained using CT images, and their predictive performance was compared. Imaging-derived and clinical predictors selected using only the training data in each patient-level cross-validation fold were combined and used as inputs for conventional machine learning models, including random forest, support vector machine, naïve Bayes, neural network, and gradient boosting. Results: Successful pancreatic stone clearance was achieved in 54 of 91 patients (59%). Compared with the 104 patients without extractable CT data, the analyzed cohort had a higher proportion of asymptomatic pancreatolithiasis (43% vs. 15%) and a markedly lower pancreatic stone clearance rate (59% vs. 88%), indicating potential selection bias. Asymptomatic pancreatolithiasis and a pancreatic stone size of ≥15 mm, defined using a data-derived exploratory cutoff, were significantly associated with unsuccessful stone clearance. Among the deep learning models, ResNet50 achieved the highest performance (area under the receiver operating characteristic curve [AUC], 0.718), followed by Vision Transformer (Large model, 16 × 16 patches) (AUC, 0.700). When image-derived features were combined with clinical features, the neural network achieved the best performance, with a mean AUC of 0.757, a median sensitivity of 0.568, a median specificity of 0.704, and a median accuracy of 0.659. Conclusions: A neural network integrating CT-derived image features with clinical information showed moderate internal predictive performance for pancreatic stone clearance. Because this was a single-center retrospective study without external validation, the present model should be regarded as a preliminary predictive model requiring validation in independent cohorts before clinical application.