Defining the Limits of Pre-Transplant Risk Prediction in AML: Evidence From Machine Learning and Regression Models
ML approaches improved risk stratification over HCT-CI and aELN but performed comparably with Cox model. Individual outcome prediction using static pre-transplant models remained modest. Progress will require MRD standardization, richer data, and dynamic peri- and post-transplant modeling.
Authors
- Arya Rahgozar (ORCID: https://orcid.org/0000-0002-2127-2449)
- Philip Berardi (ORCID: https://orcid.org/0000-0002-2302-6145)
- Christopher Bredeson (ORCID: https://orcid.org/0000-0002-9689-5114)
- Natasha Kekre (ORCID: https://orcid.org/0000-0001-8394-0855)
- Harold Atkins
- Ashish Masurekar
- Kelly M. Burkett (ORCID: https://orcid.org/0000-0002-9488-5588)
- Yaqeen Abduallah
- Ram Vasudevan Nampoothiri (ORCID: https://orcid.org/0000-0003-2333-4081)
- Marc Carrier (ORCID: https://orcid.org/0000-0001-8296-2972)
- Santhosh Thyagu (ORCID: https://orcid.org/0000-0001-7990-4210)
- Michael Kennah
- Carolina Cieniak
- Kalina Abrol
- Pouria Mortezaagha (ORCID: https://orcid.org/0009-0006-4768-6654)
- Philippe Giguère
- Megan Othus
- Ranjeeta Mallick
- David Allan
- Roland B. Walter
- Tim Ramsay
Institutions
- University of Ottawa (CA)
- Ottawa Hospital (CA)
- Fred Hutch Cancer Center (US)
- Ottawa Hospital Research Institute (CA)
Publication Details
- Journal
- Transplantation and Cellular Therapy
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1016/j.jtct.2025.12.996
- Primary Topic
- Acute Myeloid Leukemia Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00