AI-driven tool to guide blood preparation before surgery
Intelligent Clinical Decision Support for Preoperative Blood Management: A Cluster-Randomized Clinical Trial
NA · Washington University School of Medicine · NCT07223853
This tests an AI decision-support tool that helps clinicians decide which surgery patients should have blood prepared ahead of time to ensure timely transfusion for those who need it and avoid unnecessary preparation for those who don't.
Quick facts
| Phase | NA |
|---|---|
| Study type | Interventional |
| Enrollment | 50 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Washington University School of Medicine (other) |
| Locations | 1 site (St Louis, Missouri) |
| Trial ID | NCT07223853 on ClinicalTrials.gov |
What this trial studies
The trial compares an AI-based clinical decision support system (S-PATH) to usual care for perioperative blood ordering at a single academic center. Clinicians in affiliated preoperative assessment clinics will use model predictions to guide whether blood is prepared for patients scheduled in main operating rooms. The study will track outcomes such as how often blood is prepared, actual transfusion needs and timing, blood waste, costs, and patient safety. Implementation occurs at Barnes Jewish Hospital with patients who have a valid S-PATH prediction and meet inclusion criteria.
Who should consider this trial
Good fit: Ideal candidates are patients scheduled for surgery in a main operating room at Barnes Jewish Hospital who are seen in an affiliated preoperative assessment clinic and have a valid S-PATH model prediction prior to that visit, and who are not pregnant and have no history of red cell alloantibodies.
Not a fit: Patients who are pregnant, have a history of red cell alloantibodies, are having procedures in remote operating rooms, or are not evaluated in the affiliated preoperative clinics (or lack a valid S-PATH prediction) are unlikely to benefit from this intervention.
Why it matters
Potential benefit: If successful, the tool could reduce unnecessary blood preparation and waste while ensuring patients who need transfusions receive blood promptly.
How similar studies have performed: Retrospective and predictive-model studies have shown machine-learning methods can identify patients at risk of transfusion, but prospective implementations of AI decision support for perioperative blood ordering remain limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Clinician Level Exclusion Criteria: * Clinician (resident physician or advanced practice provider) who works at a preoperative assessment clinic Clinician Level Exclusion Criteria: * None Patient Inclusion Criteria: * Scheduled for surgery in one of the main operating room areas (non-remote) at Barnes Jewish Hospital * Evaluated in-person at one of the preoperative assessment clinics affiliated with BJC Healthcare * Have a valid S-PATH model prediction prior to their preoperative assessment clinic visit Patient Exclusion Criteria: * Pregnant * Presence or history of red cell alloantibodies
Where this trial is running
St Louis, Missouri
- Washington University / Barnes Jewish Hospital — St Louis, Missouri, United States (RECRUITING)
Study contacts
- Study coordinator: Sunny S Lou, MD, PhD
- Email: slou@wustl.edu
- Phone: 314-362-5000
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Surgery, artificial intelligence, clinical decision support, machine learning, surgery, perioperative blood management, anesthesia, pretransfusion testing