Automated Anesthesia System-Gastrointestinal Endoscopy: Reinforcement Learning-Based Control for Anesthesia During Gastrointestinal Endoscopy

What this Trial Is About

Researchers are evaluating the use of an artificial intelligence (AI) system to control anesthesia during painless gastrointestinal endoscopy in adults aged 18 to 65 years with ASA physical status I-II. The study aims to compare the performance of the AI model against anesthesia provided by experienced clinical professionals to see if the AI is not inferior in safely managing anesthesia during the procedure. Participants will be randomly assigned to one of two groups: the test group receiving anesthesia controlled by the AI model using ciprofol, and the control group receiving anesthesia induced and maintained by anesthesiologists with ciprofol. Anesthesia induction and maintenance will be closely monitored during the gastrointestinal endoscopy. During the study, participants will fast for 8 hours before the procedure, with no drinking water allowed for 2 hours after taking intestinal purgatives. Researchers will assess outcomes including the incidence of hypoxemia, blood oxygen levels, anesthesia doses and timing, body movements, hypotension, norepinephrine use, procedure duration, and any adverse reactions related to ciprofol. The study includes double-blind monitoring and follows participants through the procedure to evaluate safety and effectiveness measures.

Reinforcement Learned Automatic Anesthesia System During Painless Gastrointestinal Endoscopy