Sunny Lou
Washington University in St Louis, MO·Medicine & Clinical Research·Early-career
About 20 million people have surgery in the United States each year, and about 1 million of them need a blood transfusion. Before surgery, hospitals test and set aside blood so that a transfusion can happen safely and quickly if it is needed.
- Fields
Medicine & Clinical Research
Computer Science
Public Health & Epidemiology
- Topics
perioperative blood management
blood transfusion
surgical transfusion risk
- Grants
- 1 known grant, through Jun 2028
What they work on
- Embed S-PATH, a personalized AI model that predicts a patient's risk of needing a surgical blood transfusion, into the electronic health record as a clinical decision support tool for presurgical blood orders.
- Test whether the EHR-embedded S-PATH tool can feasibly be deployed within the normal preoperative workflow, using a pragmatic cluster-randomized clinical trial.
- Measure the preliminary effectiveness of S-PATH decision support at guiding presurgical blood orders toward patients likely to need transfusion and away from excessive preparation.
- Design and evaluate strategies for implementing and governing AI-based decision support tools, aiming for a system that works independently of any specific EHR vendor.
More about the research
Too often, though, blood is prepared for patients who never use it. This over-preparation is costly and wastes blood, a serious problem during blood shortages. Tools that accurately estimate each patient's transfusion risk could help clinicians order blood only for patients who need it.
Why it matters
Surgical patients need blood available when there is a real risk of transfusion, but excess presurgical blood preparation wastes blood and money. An AI-based tool built into the electronic health record could help clinicians match blood orders to each patient's actual risk. This could improve patient safety, conserve scarce blood during shortages and reduce healthcare costs for hospitals.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Katherine Courtright
University of Pennsylvania, PA·Medicine & Clinical Research
Test whether an automated needs-based palliative care trigger in the electronic health record increases hospital-free days and palliative consults compared with usual care, in a cluster-randomized trial of over 64,000 patients at 9 hospitals.
Anna Krupp
University of Iowa, IA·Medicine & Clinical Research
Develop a clinical decision support system prototype in the electronic health record that identifies ICU patients suitable for physical activity, using clinician interviews and user-centered design.
Maxime Cannesson
University of California-Los Angeles, CA·Medicine & Clinical Research
Develop machine learning models that predict major complications after surgery by combining electronic health record data, high-fidelity physiological waveform features, and genomic data.
The school
Washington University in St Louis: 97 labs on PI Pages, $1.2B a year on research, 365 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.