Machine Learning Models to Differentiate the Etiology of Cutaneous Reactions in Post-Stem Cell Transplant Patients
- Program: Biomedical Engineering
- Course: EN.580.480 Precision Care Medicine
Project Description:
Allogeneic hematopoietic stem cell transplantation (HSCT) is a life-saving treatment for patients with hematologic diseases and is often complicated by post-transplant cutaneous eruptions. The etiologies of these rashes include drug reactions, viral exanthema, and graft-versus-host disease (GVHD), which require timely and unique treatment regimens to lessen associated morbidity and mortality. Differentiation of post-HSCT rashes is challenging within current diagnostic paradigms. Therefore, there is a need for robust computational models that can integrate clinical and lab data to appropriately identify post-HSCT rash etiology. In this investigation, we employ supervised and unsupervised machine learning models ad a single-institution dataset to help distinguish GVHD and non-GVHD rashes.
Project Photo:
Student members of Precision Care Medicine Team Rhino
Project Poster
Open full size poster in new tab (PDF)
Project Post Summary:
Over 25,000 hematopoetic stem cell transplants (HSCT) are performed annually
in the United States to treat hematologic conditions and malignancies. Three rashes commonly occur as a post-transplant complication: cutaneous Graft-
Versus-Host-Disease (GVHD), viral reactivation syndromes, and drug eruptions. GVHD occurs in 40% of post-HSCT patients and has a 35% mortality rate. Differentiating between cutaneous eruption etiologies is difficult given overlapping clinical presentations and the complex medical course of HSCT patients (i.e. immunosuppression and complex drug regimens). Accurate identification of rash cause is essential to initiate appropriate and
timely treatment. The aim of this work is to assist dermatologists by employing machine learning models to synthesize diverse, high-dimensional data to aid in differentiating the
cause of cutaneous eruptions in post-HSCT patients.
Course Faculty
- Joseph L Greenstein
- Casey Overby Taylor
Project Mentors, Sponsors, and Partners
- Sima Rozati
- David Weiner
- Austin Burns
- Olivia Pierog