An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Abstract

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1–3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.

Applications of artificial intelligence in gastroscopy: a narrative review

“…Two multicenter studies in China investigated the value of AI in efforts to detect gastroesophageal varices. 48,49 Their results showed that, in the detection of gastroesophageal varices, AI and physicians demonstrated comparable accuracy. Furthermore, in the diagnosis of bleeding risk factors such as the red color sign, AI demonstrated diagnostic ability superior to physicians.…”

“…Finally, the AI model provided appropriate treatment recommendations based on the current test results. 48,49…”

The Prediction and Treatment of Bleeding Esophageal Varices in the Artificial Intelligence Era: A Review

“…Machine learning algorithms, neural networks, and radiomics are fast-paced developing fields in medicine that, year after year, are showing promising results, especially in imaging interpretation. The creation of new software in detecting esophageal varices has shown comparable results with endoscopic findings; even though large-scale studies are still needed, an artificial intelligence called ENDOANGEL-GEV outperformed many endoscopist findings [ 47 , 48 ]. Several other software programs are still in development, but some neural network systems demonstrated comparable results with endoscopy predicting bleeding episodes [ 49 ].…”

“…The creation of new software in detecting esophageal varices has shown comparable results with endoscopic findings; even though large-scale studies are still needed, an artificial intelligence called ENDOANGEL-GEV outperformed many endoscopist findings [ 47 , 48 ]. Several other software programs are still in development, but some neural network systems demonstrated comparable results with endoscopy predicting bleeding episodes [ 49 ]. Machine learning algorithms have taken the spotlight on predicting high-risk esophageal varices.…”

“…With the remarkable progress of AI in healthcare, particularly in the endoscopy field, AI has been used with colonoscopy to detect colorectal adenomas and esophagogastroduodenoscopy to minimize blind spots [ 47 ]. It is essential for medical education to continually incorporate advancements, ensuring healthcare professionals stay ahead of the latest, more accurate technologies.…”