Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Prediction and forecasting

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

Yamamoto S; Teramoto A; Ono T; Hashimoto S; Katano Y; Kobayashi T; Muto H; Tachi Y; Miyoshi H; Inui K

Originally published in Diagnostics (Basel) · 2026-08-24

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

AbstractBackground/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…

3.1. Treatment Results and Comparison of Pancreatic Stone Clearance Rates Based

Among the 91 patients whose noncontrast abdominal CT images were available, 54 (59%) achieved successful stone clearance. The median number of ESWL sessions was 6 (range, 1–61); the number of sessions was unavailable for one patient. The patient who underwent 61 ESWL sessions was treated over a prolonged period before the stopping criterion proposed in our previous study was established; therefore, this exceptionally high number does not represent our current treatment strategy [14]. Receiver operating characteristic curve analysis identified a data-derived exploratory cutoff of 15 mm for pancreatic stone size. In comparisons of stone clearance rates based on clinical features among the 91 patients, no significant differences were associated with age, sex, etiology, number of stones, stone distribution, or presence of a main…

4. Discussion

The principal finding of this study is that a preliminary AI-based model integrating pretreatment CT images and clinical information showed moderate internal performance in predicting pancreatic stone clearance after nonsurgical treatment for pancreatolithiasis. This study should be regarded as an initial application of CT-based AI prediction to pancreatolithiasis rather than as a novel AI methodology. In chronic pancreatitis, the formation of pancreatic stones can obstruct pancreatic juice outflow, leading to increased intraductal pressure and consequent pain. These changes may accelerate fibrosis of the pancreatic parenchyma, progressively impairing both exocrine and endocrine pancreatic function. Because removal of pancreatic stones improves pancreatic juice outflow, it may reduce pain and slow the progression of chronic…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?