A novel machine learning-based diagnostic tool for obstructive jaundice has shown promising results. Researchers analyzed data from over 6,000 patients and identified key causes including pancreatic adenocarcinoma and biliary cholangiocarcinoma. Traditional markers performed poorly on their own. Two machine learning models were developed, achieving an area under the receiver operating characteristic of 0.862 for identifying malignant causes and 0.777 accuracy for classifying conditions, enhancing diagnostic confidence and clinical decision-making.
Journal Article by Wen N, Wang Y (…) Cheng N et 9 al. in Clin Transl Gastroenterol
Copyright © 2025 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of The American College of Gastroenterology.