The success of unrelated donor stem cell transplants depends on not only finding genetically matched donors, but also donor availability. On average 50% of potential donors in the National Marrow Donor Program database are unavailable for a variety of reasons, after initially matching a patient, with significant variations in availability among subgroups (eg, by race or age). Several studies have established univariate donor characteristics associated with availability. Individual consideration of each applicable characteristic is laborious. Extrapolating group averages to the individual-donor level tends to be highly inaccurate. In the current environment with enhanced donor data collection, we can make better estimates of individual donor availability. We propose a machine learning based approach to predict availability of every registered donor, and evaluate the predictive power on a test cohort of 44,544 requests to be .77 based on the area under the receiver-operating characteristic curve. We propose that this predictor should be used during donor selection to reduce the time to transplant.
Abstract:The success of Unrelated Donor stem-cell transplants depends not only on finding genetically matched donors but also on donor availability. On average 50% of potential donors are unavailable for a variety of reasons after initially matching a patient with significant variations in availability among subgroups (e.g., by race or age). Several studies have established univariate donor characteristics associated with availability. Individual consideration of each applicable characteristic is laborious. Extrapolating group averages to individual donor level tends to be highly inaccurate. In the current environment with enhanced donor data collection, we can make better estimates of individual donor availability. In this study, we propose a Machine Learning based approach to predict availability of every registered donor, to be used during donor selection and reduce the time taken to complete a transplant.
Unrelated Donor selection for a Hematopoietic Stem Cell Transplant is a complex multi-stage process. Choosing the most suitable donor from a list of Human Leukocyte Antigen (HLA) matched donors can be challenging to even the most experienced physicians and search coordinators. The process involves experts sifting through potentially thousands of genetically compatible donors based on multiple factors. We propose a Machine Learning approach to donor selection based on historical searches performed and selections made for these searches. We describe the process of building a computational model to mimic the donor selection decision process and show benefits of using the proposed model in this study.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.