Advancements in AI Research for Digestive System Diseases

Abstract

With the "boom" of AI, researchers have made significant progress in assisting clinical disease diagnosis, prediction, and treatment. This article provides an overview of models built using both traditional machine learning methods and deep learning methods, as well as research progress on robotics in digestive system diseases, aiming to provide references for further studies. An application has been developed by domestic and foreign scholars that allows users to upload images of stool samples, which are then analyzed using big data to provide a score for bowel preparation, thereby improving the quality of bowel preparation. In some gastrointestinal diseases, such as Hp infection, Barrett's esophagus and esophageal cancer, chronic atrophic gastritis and gastric cancer, IBD, etc., artificial intelligence possesses diagnostic capabilities comparable to those of professional endoscopists, and some applications can achieve real-time diagnosis. In the field of liver, gallbladder, and pancreatic diseases, artificial intelligence can assist in preoperative diagnosis using imaging or pathology, and robotic remote operations can be performed during surgery, predicting postoperative risk levels, and more. Different scholars have compared and analyzed various algorithm networks for different diseases to find the best-performing models. On this basis, methods such as the MCA attention mechanism, feature selection, gradient descent, and ensemble models can be introduced to further improve the diagnostic performance of the models. In the future, AI can not only help patients self-manage single or multiple diseases, monitor and manage their own diseases in a standardized and reasonable manner, but also predict and treat digestive system diseases at the genetic level.