Division of Biostatistics, Institute for Health and Equity, Medical College of Wisconsin (MCW), Milwaukee, WI.
Center for International Blood and Marrow Transplant Research (CIBMTR), Medical College of Wisconsin, Milwaukee, WI.
JCO Clin Cancer Inform. 2021 May;5:494-507. doi: 10.1200/CCI.20.00185.
Donor selection practices for matched unrelated donor (MUD) hematopoietic cell transplantation (HCT) vary, and the impact of optimizing donor selection in a patient-specific way using modern machine learning (ML) models has not been studied.
We trained a Bayesian ML model in 10,318 patients who underwent MUD HCT from 1999 to 2014 to provide patient- and donor-specific predictions of clinically severe (grade 3 or 4) acute graft-versus-host disease or death by day 180. The model was validated in 3,501 patients from 2015 to 2016 with archived records of potential donors at search. Donor selection optimizing predicted outcomes was implemented over either an unlimited donor pool or the donors in the search archives. Posterior mean differences in outcomes from optimal donor selection versus actual practice were summarized per patient and across the population with 95% intervals.
Event rates were 33% (training) and 37% (validation). Among donor features, only age affected outcomes, with the effect consistent regardless of patient features. The median (interquartile range) difference in age between the youngest donor at search and the selected donor was 6 (1-10) years, whereas the number of donors per patient younger than the selected donor was 6 (1-36). Fourteen percent of the validation data set had an approximate 5% absolute reduction in event rates from selecting the youngest donor at search versus the actual donor used, leading to an absolute population reduction of 1% (95% interval, 0 to 3).
We confirmed the singular importance of selecting the youngest available MUD, irrespective of patient features, identified potential for improved HCT outcomes by selecting a younger MUD, and demonstrated use of novel ML models transferable to optimize other complex treatment decisions in a patient-specific way.
用于匹配无关供者（MUD）造血细胞移植（HCT）的供者选择实践存在差异，并且尚未研究使用现代机器学习（ML）模型以患者特异性方式优化供者选择对移植结果的影响。
我们在 1999 年至 2014 年间接受 MUD HCT 的 10318 例患者中训练了一个贝叶斯 ML 模型，以提供患者和供者特异性预测，预测临床严重（3 级或 4 级）急性移植物抗宿主病或 180 天内死亡的风险。该模型在 2015 年至 2016 年间接受了 3501 例患者的验证，这些患者的潜在供者在搜索时具有存档记录。在无限制的供者库或搜索档案中的供者中实施了优化预测结果的供者选择。对每个患者和整个患者群体，使用 95%区间总结了最优供者选择与实际实践之间结果的后验均值差异。
事件发生率为 33%（训练）和 37%（验证）。在供者特征中，只有年龄影响结局，且无论患者特征如何，其影响均一致。在搜索时选择的最年轻供者和选定供者之间的年龄中位数（四分位距）差异为 6 岁（1-10 岁），而每个患者比选定供者年轻的供者数为 6 个（1-36 个）。验证数据集的 14%患者的事件率从选择搜索时最年轻的供者降低约 5%，导致绝对人群降低 1%（95%区间，0 至 3）。
我们证实选择最年轻的可用 MUD 具有独特的重要性，而与患者特征无关，确定了通过选择更年轻的 MUD 提高 HCT 结局的潜力，并证明了使用新颖的 ML 模型以患者特异性方式优化其他复杂治疗决策的可行性。
