MUSC Hollings Researchers Create AI Tool to Identify Transplant Patients at Risk of Complications

The AI model predicts chronic graft-versus-host disease risk after stem cell and bone marrow transplants.

Published on Feb. 19, 2026

Got story updates? Submit your updates here. ›

Researchers at MUSC Hollings Cancer Center have developed an AI-based tool to help clinicians predict which patients may be at high risk of serious complications, such as chronic graft-versus-host disease, after a stem cell or bone marrow transplant. The model combines blood-based immune biomarkers and clinical data to generate individualized risk estimates.

Why it matters

Chronic graft-versus-host disease is one of the most serious complications after a stem cell or bone marrow transplant, in which donor immune cells attack a patient's healthy tissue. Earlier identification of higher-risk patients could allow for closer monitoring or preventive strategies, with the potential to improve long-term outcomes.

The details

The tool was developed and validated using data from 1,310 stem cell and bone marrow transplant recipients across multiple studies. In testing, it reliably predicted patients' risk and separated them into low- and high-risk groups with distinct outcomes. The tool is intended to support risk assessment and clinical research rather than guide treatment decisions, and it is available as a free, web-based application for clinicians and researchers.

  • The findings were published on February 16, 2026.

The players

MUSC Hollings Cancer Center

A comprehensive cancer center located in Charleston, South Carolina, that is part of the Medical University of South Carolina.

Sophie Paczesny, MD, PhD

The lead study author and co-leader of Hollings' Cancer Biology and Immunology Research Program.

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.”

— Sophie Paczesny, Lead Study Author and Co-Leader of Hollings' Cancer Biology and Immunology Research Program (MUSC News Release)

What’s next

As a next step, researchers plan to study whether earlier intervention for high-risk patients improves long-term outcomes.

The takeaway

This AI tool developed by MUSC Hollings researchers has the potential to significantly improve outcomes for stem cell and bone marrow transplant patients by allowing for earlier identification of those at high risk of serious complications like chronic graft-versus-host disease, enabling closer monitoring and preventive strategies.