AI-Assisted Blood Pressure Control During Anesthesia

Starting soon · Not applicable

Conditions studied: Intraoperative Hypotension, Hemodynamic Instability

In brief

This proof-of-concept randomized controlled trial evaluates a reinforcement learning (RL)-based clinical decision support system for intraoperative hemodynamic management during non-cardiac surgery. Background: Intraoperative hypotension is common during general anesthesia and is associated with adverse outcomes including acute kidney injury, myocardial injury, and increased mortality. Current hemodynamic management relies on the individual anesthesiologist's clinical judgment, which can vary in consistency and timeliness. An RL-based system that learns optimal vasoactive agent dosing strategies from clinical data may help standardize and improve real-time hemodynamic decision-making. Purpose: The primary objective is to evaluate whether the RL-based decision support system can learn intraoperative hemodynamic management decisions comparable to those of experienced anesthesiologists, as measured by the mean absolute error (MAE) between RL-recommended and clinician-executed vasoactive agent doses. The secondary objective is to assess whether RL-guided management improves clinical hemodynamic outcomes, including the time-weighted average of hypotension and the percentage of time with mean arterial pressure within the target range. Participants: Adult patients (aged 18 to 85 years, ASA I-IV) scheduled for elective non-cardiac surgery under general anesthesia with continuous invasive arterial blood pressure monitoring. Procedures: Participants will be randomly assigned (1:1) to one of two groups. In the RL-guided group, the anesthesiologist will receive real-time vasoactive agent dosing recommendations from the decision support system displayed on a bedside screen; the anesthesiologist retains full clinical autonomy over all final decisions. In the standard care group, the anesthesiologist will manage hemodynamics according to institutional standard practice without input from the system. The patient and the outcomes assessor will be masked to group assignment. Data collection covers the intraoperative period and 30-day postoperative follow-up.

Key facts

Study ID

NCT07123675

Run by

Beijing Tsinghua Chang Gung Hospital

People needed

40

Starts

2026-06-01

Expected to finish

2027-12-15

Last updated by the study team

2026-04-06

Who can join

Age: 18 and older, up to 85. Sex: any. Healthy volunteers: not accepted.

You may qualify if…

• Age 18 to 85 years
• Scheduled for elective non-cardiac surgery
• Receiving intravenous-inhalation combined general anesthesia with tracheal intubation
• ASA physical status I to IV
• Anesthesia maintenance plan includes propofol for continuous sedation, remifentanil for continuous analgesia, and sevoflurane or desflurane for inhalation anesthesia
• Continuous invasive arterial blood pressure monitoring during surgery
• Continuous monitoring of heart rate and Bispectral Index (BIS) during surgery
• Expected surgical duration of at least 2 hours

You may not qualify if…

• Emergency surgery
• Continuous infusion of remifentanil or propofol for less than 30 minutes during surgery
• Receiving continuous intravenous sedatives other than propofol during the maintenance phase
• Receiving continuous intravenous analgesics other than remifentanil during the maintenance phase
• Inhaled anesthetic maintenance concentration not equal to 0.5 MAC
• Known allergy to propofol or remifentanil
• Severe obesity (BMI >= 35 kg/m2)
• Severe cardiovascular disease (NYHA class IV heart failure, unstable angina, or recent myocardial infarction within 30 days)
• Participation in another interventional clinical trial within 30 days

Where it is running

• Peking University People's Hospital — Beijing, Beijing Municipality, China
• Beijing Tsinghua Changgung Hospital — Beijing, Beijing Municipality, China

Full record on ClinicalTrials.gov

Trial information comes from ClinicalTrials.gov and is refreshed daily. TrialsForMe does not provide medical care and does not run the studies it lists.