AI Tool Predicts Transplant Complications Months Early

Researchers develop an AI-based model to identify patients at higher risk for chronic graft-versus-host disease before symptoms appear.

Published on Feb. 18, 2026

Got story updates? Submit your updates here. ›

Researchers at MUSC Hollings Cancer Center have developed an AI-based tool called BIOPREVENT that can predict a patient's risk of developing life-threatening complications like chronic graft-versus-host disease (GVHD) months after a stem cell or bone marrow transplant. The tool combines immune biomarkers and clinical data to identify high-risk patients early, before symptoms appear, allowing for earlier monitoring and intervention.

Why it matters

Chronic GVHD is one of the leading causes of illness and death after transplants, but the disease process often begins months before symptoms appear. BIOPREVENT aims to give clinicians a head start in identifying high-risk patients, potentially leading to earlier treatment and better long-term outcomes for transplant recipients.

The details

The researchers analyzed data from 1,310 stem cell and bone marrow transplant recipients, testing blood samples for seven immune proteins and combining that with nine clinical factors. Using machine learning, they developed BIOPREVENT, a model that can reliably predict a patient's risk of chronic GVHD and transplant-related mortality up to 18 months in advance. The tool separates patients into low- and high-risk groups and is now available as a free, web-based application for clinicians to use.

  • The blood samples used to develop BIOPREVENT were collected 90 to 100 days after transplant.
  • The tool can predict patient outcomes up to 18 months after transplant.

The players

Sophie Paczesny

M.D., Ph.D., co-leader of the Cancer Biology and Immunology Research Program at MUSC Hollings Cancer Center and lead researcher on the study.

Michael Martens

Ph.D., researcher with the Center for International Blood and Marrow Transplant Research at the Medical College of Wisconsin and co-author of the study.

Brent Logan

Ph.D., researcher with the Center for International Blood and Marrow Transplant Research at the Medical College of Wisconsin and co-author of the study.

MUSC Hollings Cancer Center

The academic medical center where the research was conducted.

Center for International Blood and Marrow Transplant Research

The organization that maintains the transplant registry data used in the study.

Got photos? Submit your photos here. ›

What they’re saying

“By the time chronic GVHD is diagnosed, the disease process has often been unfolding for months, quietly hurting the body. We wanted to know whether we could detect warning signs earlier, before patients feel sick, and soon enough for clinicians to intervene, before the damage becomes irreversible.”

— Sophie Paczesny, M.D., Ph.D., co-leader of the Cancer Biology and Immunology Research Program at MUSC Hollings Cancer Center (Journal of Clinical Investigation)

“It was important to us that this not remain a theoretical model or a tool limited to a single institution. Making BIOPREVENT freely available helps ensure that researchers and clinicians can test it, learn from it and, ultimately, improve care for transplant patients.”

— Sophie Paczesny, M.D., Ph.D., co-leader of the Cancer Biology and Immunology Research Program at MUSC Hollings Cancer Center (Journal of Clinical Investigation)

What’s next

The researchers plan to conduct clinical trials to test whether acting on the early risk signals identified by BIOPREVENT, such as closer monitoring or preventive therapies for high-risk patients, can improve long-term outcomes for transplant recipients.

The takeaway

BIOPREVENT represents an important step toward more personalized transplant care, using data-driven risk assessment to help clinicians make more informed decisions and potentially prevent one of the most serious complications of stem cell and bone marrow transplants.