Artificial Intelligence–Enabled Stool Analysis for Lactulose Titration Assistance in Hepatic Encephalopathy Through a Smartphone Application
乳果糖
肝性脑病
医学
脑病
内科学
胃肠病学
排便
物理疗法
肝硬化
作者
Beatriz Sordi Chara,Kamalpreet Hara,Daniel Penrice,Kathryn A. Schmidt,Blake A. Kassmeyer,James Anstey,David Tiede,Patrick S. Kamath,Vijay H. Shah,Jasmohan S. Bajaj,Asaf Kraus,Douglas A. Simonetto
Management of hepatic encephalopathy relies on self-titration of lactulose. In this feasibility trial, we assess an artificial intelligence-enabled tool to guide lactulose use through a smartphone application.Subjects with hepatic encephalopathy on lactulose captured bowel movement pictures during lead-in and intervention phases. During the intervention phase, daily feedback on lactulose titration was delivered through the application. Goals were determined according to number of bowel movement and Bristol Stool Scale reports.Subjects completed the study with more than 80% satisfaction. In the lead-in phase, less compliant subjects achieved Bristol Stool Scale goal on 62/111 (56%) of days compared with 107/136 (79%) in the intervention phase ( P = 0.041), while the most compliant subjects showed no difference. Severe/recurrent hepatic encephalopathy group achieved Bristol Stool Scale goal on 80/104 (77%) days in the lead-in phase and 90/110 (82%) days in the intervention phase ( P = NS), compared with 89/143 (62%) days and 86/127 (68%) days in the stable group.Dieta application is a promising tool for objective Bowel Movement/Bristol Stool Scale tracking for hepatic encephalopathy and may potentially be used to assist with lactulose titration.