Predicting the Availability of Hematopoietic Stem Cell Donors Using Machine Learning.

Hematopoietic stem cell transplantation (HSCT) is firmly established as an important curative therapy for patients with hematologic malignancies and other blood disorders. Apart from finding HLA-matched donors during the HSCT process, donor availability remains a key consideration as the time taken from diagnosis to transplant is recognized to adversely affect patient outcome. In this study, we aimed to develop and validate a machine learning approach to predict the availability of stem cell donors. We retrospectively collected a data set containing 10,258 verification typing requests made during the HSCT process in the British Bone Marrow Registry (BBMR) between January 1, 2013, and December 31, 2018. Three machine learning algorithms were implemented and compared, including boosted decision trees (BDTs), logistic regression, and support vector machines. Area under the receiver operating characteristic curve (AUC) was primarily used to assess the algorithms. The experimental results showed that BDTs performed better in predicting the availability of BBMR donors. The overall predictive power of the model, using AUC on the test cohort of 2052 records, was found to be 0.826. Our findings show that machine learning can predict the availability of donors with a high degree of accuracy. We propose the use of the BDT machine learning approach to predict the availability of BBMR donors and use the predictive scores during the HSCT process to ensure patients with blood cancers or disorders receive a transplant at the optimum time.

Recommendations for a standard UK approach to incorporating umbilical cord blood into clinical transplantation practice: an update on cord blood unit selection, donor selection algorithms and conditioning protocols.

Allogeneic haemopoietic stem cell transplantation offers a potentially curative treatment option for a wide range of life-threatening malignant and non-malignant disorders of the bone marrow and immune system in patients of all ages. With rapidly emerging advances in the use of alternative donors, such as mismatched unrelated, cord blood and haploidentical donors, it is now possible to find a potential donor for almost all patients in whom an allograft is indicated. Therefore, for any specific patient, the transplant physician may be faced with a myriad of potential choices, including decisions concerning which donor to prioritize where there is more than one, the optimal selection of specific umbilical cord blood units and which conditioning and graft-versus-host disease prophylactic schedule to use. Donor choice may be further complicated by other important factors, such as urgency of transplant, the presence of alloantibodies, the disease status (homozygosity or heterozygosity) of sibling donors affected by inherited disorders and the cytomegalovirus serostatus of patient and donor. We report UK consensus guidelines on the selection of umbilical cord blood units, the hierarchy of donor selection and the preferred conditioning regimens for umbilical cord blood transplantation, with a summary of rationale supporting these recommendations.