Implication of machine learning for relapse prediction after allogeneic stem cell transplantation in adults with Ph-positive acute lymphoblastic leukemia

Abstract

The posttransplant relapse in Ph-positive ALL increases the risk of death. There is an unmet need for instruments to predict the risk of relapse and plan prophylaxis treatments. In this study we analyzed posttransplant data by machine learning algorithms. Seventy-four Ph-positive ALL patients with median age of 30 (range, 18–55) years, who previously underwent allo-HSCT were retrospectively enrolled. Ninety-three percent of patients received prophylactic/preemptive TKIs after allo-HSCT. The values ​​of the BCR::ABL1 level at serial assessments and over variables were collected in specified intervals after allo-HSCT and were used to model relapse risk with several machine learning approaches. GBM proved superior to the other algorithms utilized and provided maximal AUC score of 0.91. BCR::ABL1 level before and after allo-HSCT, prediction moment and chronic GvHD had the highest value in the model. It was shown that after Day + 100 both error rates don’t exceed 22%, while before D + 100 the model fails to make accurate prediction. After day + 100 patients with chronic GVHD, BCR::ABL1 level more than 0.11% post-transplant and current BCR::ABL1 above 0.06% can be classified as high risk group of relapse. At the same time, if the patient had no chronic GVHD after allo-HSCT till the prediction moment, he should be classified to a high risk group already with a BCR::ABL1 level more than 0,05% at any time point. GBM model with posttransplant laboratory values of BCR::ABL1 provides high prediction of relapse in the era of TKIs prophylaxis. Validation of this approach is warranted.