Statistics and measurable residual disease (MRD) testing: uses and abuses in hematopoietic cell transplantation

The decision whether to recommend a transplant to someone with acute leukemia in first remission is complex and challenging. Diverse, often confounded co-variates interact to influence one’s recommendation. Briefly, the decision metric can be viewed in three spheres: (1) subject-; (2) transplant-; and (3) disease-related co-variates. Subject-related co-variates include items such as age and comorbidities. Transplant-related co-variates include items such as donor-types, graft source, proposed conditioning and pre- and post-transplant immune suppression. But what of disease-related variables? Previously haematologists relied on co-variates such as WBC at diagnosis, chemotherapy cycles to achieve first remission, cytogenetics and most recently, mutation topography. However, these co-variates have largely been replaced by results of measurable residual disease (MRD)-testing. Many chemotherapy-only and transplant studies report strong correlations between results of MRD-testing on therapy outcomes such as cumulative incidence of relapse (CIR), leukemia-free survival (LFS) or survival. (CIR makes biological sense in a transplant context whereas LFS and survival do not give competing causes of death such as transplant-related mortality (TRM), graft-versus-host disease and interstitial pneumonia unrelated to relapse probability). This raises the question of how useful results are of MRD-testing in predicting CIR after transplants. Elsewhere we discussed accuracy and precision of MRD-testing in predicting outcomes of therapy of acute myeloid leukemia (Estey E, Gale RP. Leukemia 31:1255−1258, 2017; Hourigan CS, Gale RP, Gormley NJ, Ossenkoppele GJ, Walter RB. Leukemia 31:1482−1490, 2017). Briefly put, not terribly good. Although results of MRD-testing are often the most powerful predictor of CIR in multivariable analyses, the C-statistic (a measure of prediction accuracy) is often only about 0.75. This is much better than flipping a fair coin but far from ideal. In the typescript which follows, Othus and colleagues discuss statistical issues underlying MRD-testing in the context of haematopoietic cell transplants. We hope readers, especially haematologists who often need to make transplant recommendations to people with acute leukemia in first remission, will read it carefully and critically. The bottom line is MRD-test data are useful but considerable uncertainty is unavoidable with substantial false-positive and -negative rates. We need to acknowledge this uncertainty to ourselves and to the people we counsel. The authors quote Voltaire who said_ Doubt is not a pleasant condition, but certainty is an absurd one. Sadly so, but we do the best we can. Robert Peter Gale, Imperial College London, and Mei-Jie Zhang, Medical College of Wisconsin and CIBMTR.