Journal Article Ppublish
PubMed: 39439193 DOI: 10.1111/bjh.19842
A machine learning-based workflow for predicting transplant outcomes in patients with sickle cell disease.
Br J Haematol 206(3):919-923
Authors: Haiou Li, Vandana Sachdev, Xin Tian, My-Le Nguyen, Matthew Hsieh, Courtney Fitzhugh, Emily Limerick, Wynona Coles, Nancy Asomaning, Anna Conrey, Colin O Wu, Swee Lay Thein
Affiliations
- Sickle Cell Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, Maryland, USA.
- Echocardiography Laboratory, National Heart, Lung, and Blood Institute, NIH, Bethesda, Maryland, USA.
- Office of Biostatistics Research, National Heart, Lung, and Blood Institute, NIH, Bethesda, Maryland, USA.
- Cellular and Molecular Therapeutics Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, Maryland, USA.
Abstract
Allogeneic haematopoietic cell transplantation (HCT) with HLA-matched sibling donor remains the most established curative therapeutic option for patients with sickle cell disease (SCD). However, it is not without risks, highlighting the need for a risk stratification system. Utilizing a machine learning (ML) approach that combines clinical and imaging variables, we identified red cell distribution width and renal organ damage as important risk factors for patients undergoing HCT. This ML-based algorithm, similar to an approach previously reported for predicting mortality in patients with SCD, should be applicable to risk factor discovery in similar studies.
MeSH
Cells, Mortality, Hematology, Anemia, Sickle Cell, Risk Assessment, Workflow, Machine Learning, Risk Factors, Transplants, Learning