Personalized Surgical Transfusion Risk Prediction Using Machine Learning to Guide Preoperative Type and Screen Orders.
Sunny S Lou, Hanyang Liu, Chenyang Lu...
https://pubmed.ncbi.nlm.nih.gov/35147666/Actively Recruiting
Led by Washington University School of Medicine · Updated on 2026-08-27
50
Participants Needed
1
Research Sites
4 weeks
Total Duration
Every year, about 20 million patients undergo surgery in the United States, with around 1 million needing life-saving blood transfusions. Presurgical preparation for transfusion is crucial for safe and timely care, but excessive preparation is common and leads to unnecessary costs and blood waste. This trial evaluates an intelligent clinical decision support system designed to help clinicians prepare blood only for patients likely to need it, aiming to improve patient safety while reducing waste and healthcare expenses. The study compares two approaches usual care using the institutional Maximum Surgical Blood Ordering Schedule MSBOS and access to the S-PATH electronic health record-integrated clinical decision support system. This cluster-randomized crossover trial involves patients scheduled for surgery who are evaluated at preoperative assessment clinics. Participants will experience both usual care and the S-PATH system during different periods, allowing comparison of how blood orders are managed. Participants will be assessed at their preoperative clinic visit where decisions about blood type and screen orders are made. Researchers will monitor the frequency of these orders, blood transfusions during surgery, emergency blood use, and transfusion reactions up to 30 days after surgery. The study aims to track patient safety outcomes and blood management efficiency over the course of the trial, which runs until early 2027.
CONDITIONS
AI-driven Clinical Decision Support for Perioperative Blood Orders
S
Sunny S Lou, MD, PhD
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here
Washington University School of Medicine
Lead Sponsor
National Heart, Lung, and Blood Institute (NHLBI)
Collaborating Sponsor
This table compares participation in this trial with other options available for this condition. The information is drawn from published research and the trial’s study details and is provided for educational purposes only.
| Factors | S‑PATH decision support | Usual care (MSBOS) |
|---|---|---|
| What it is | An AI‑based clinical decision support tool integrated in the EHR that predicts need for preoperative type and screen orders | Conventional care using the Maximum Surgical Blood Ordering Schedule to guide preoperative type and screen orders |
| Role in trial | Crossover‑assigned investigational decision‑support condition | Crossover‑assigned standard care condition |
| Primary use | Guide clinicians to decide on preoperative type and screen testing tailored to individual risk | Standard preoperative ordering based on procedure type via MSBOS |
| How it is given or performed | Clinician accesses AI prediction in the EHR before assessment to inform ordering decisions | Clinician refers to institutional MSBOS chart during preoperative assessment |
| Evidence status | Prospectively evaluated in this randomized crossover trial | Widely endorsed method using MSBOS to guide preoperative blood ordering |
| Important risks | None explicitly identified in trial registry | None stated in registry |
| Important limitations | Effectiveness depends on accuracy of AI predictions and integration into clinician workflow | MSBOS does not consider patient‑specific risk factors beyond surgery type, which may result in over‑ordering |
Disclaimer: This comparison is created with the help of artificial intelligence(AI) and may contain errors or missing information. It is not medical advice and does not mean one option is better or safer than another. Clinical trials are still being studied, and joining a trial is your choice. Please consult your healthcare professional before making any decisions.
You may qualify if you...
You will not qualify if you...
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Until study completion
Participants receive usual blood ordering care or access to the S-PATH clinical decision support system in a randomized crossover design.
Visits occur during preoperative assessment clinic appointments
Duration - 30 days after surgery
Researchers monitor blood transfusions during surgery, emergency blood use, transfusion reactions, and related outcomes up to 30 days after surgery.
Monitoring during hospital stay and follow-up contacts
Study Type
INTERVENTIONAL
Masking
NONE
Allocation
RANDOMIZED
Model
CROSSOVER
Primary Purpose
SCREENING
Number of Arms
2
Have more questions? Get in touch with our team for quick support
Sunny S Lou, Hanyang Liu, Chenyang Lu...
https://pubmed.ncbi.nlm.nih.gov/35147666/Phillip Yang, Emma P Zijlstra, Bruce L Hall...
https://pubmed.ncbi.nlm.nih.gov/39279676/Sunny S Lou, Yaoming Liu, Mark E Cohen...
https://pubmed.ncbi.nlm.nih.gov/37737660/Sunny S Lou, Sayantan Kumar, Charles W Goss...
https://pubmed.ncbi.nlm.nih.gov/40577014/Washington University School of Medicine
Lead Sponsor
National Heart, Lung, and Blood Institute (NHLBI)
Collaborating Sponsor