Blood and immune cell markers to predict chronic graft‑versus‑host disease

Machine Learning to identify Biomarkers for Risk of Chronic Graft-Versus-Host Disease

['FUNDING_R01'] · MEDICAL UNIVERSITY OF SOUTH CAROLINA · NIH-11304070

Using machine learning on blood and immune cell tests, this project looks for early signs that children and adults who had bone marrow (allogeneic) transplants may develop chronic graft‑versus‑host disease.

Quick facts

Phase['FUNDING_R01']
Study typeNih_funding
SexAll
SponsorMEDICAL UNIVERSITY OF SOUTH CAROLINA (nih funded)
Locations1 site (CHARLESTON, UNITED STATES)
Trial IDNIH-11304070 on ClinicalTrials.gov

What this research studies

Researchers will analyze already collected plasma and peripheral blood mononuclear cell (PBMC) samples from several multicenter transplant trials and a tissue bank to look for protein and immune‑cell patterns linked to future cGVHD. They will measure about 14 plasma proteins and dozens of cell markers (up to ~300 parameters in some patients) around day +90 after transplant and compare people who later developed cGVHD to those who did not. Machine learning methods will be used alongside traditional statistics to find combinations of markers that predict who is at higher risk. The work includes both adult and pediatric transplant patients drawn from a pooled cohort of roughly 1,300 participants with a focused PBMC/plasma subset of about 200 patients.

Who could benefit from this research

Good fit: People who have received an allogeneic hematopoietic cell transplant (children and adults) and are in the early post‑transplant period, especially around day +90 with available blood/PBMC samples, are the population this work focuses on.

Not a fit: Patients who have not had allogeneic transplant, those well beyond the early post‑transplant window, or people with unrelated immune conditions would not be expected to benefit directly from this project.

Why it matters

Potential benefit: If successful, this could let doctors identify transplant patients at high risk for cGVHD earlier so they can increase monitoring or try preventive therapies.

How similar studies have performed: Previous studies have identified individual markers (for example ST2 and CXCL9) linked to cGVHD risk, but combining many proteins and cell markers with machine learning is a newer approach intended to improve prediction accuracy.

Where this research is happening

CHARLESTON, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.

View on NIH RePORTER →

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.