Search

Achievement of complete remission signifies a crucial milestone in the therapy of acute myeloid leukemia (AML) while refractory disease is associated with dismal outcomes. Hence, accurately identifying patients at risk is essential to tailor treatment concepts individually to disease biology. We used nine machine learning (ML) models to predict complete remission and 2-year overall survival in a large multicenter cohort of 1,383 AML patients who received intensive induction therapy. Clinical, laboratory, cytogenetic and molecular genetic data were incorporated and our results were validated on an external multicenter cohort. Our ML models autonomously selected predictive features including established markers of favorable or adverse risk as well as identifying markers of so-far controversial relevance. De novo AML, extramedullary AML, double-mutated CEBPA, mutations of CEBPA-bZIP, NPM1, FLT3-ITD, ASXL1, RUNX1, SF3B1, IKZF1, TP53, and U2AF1, t(8;21), inv(16)/t(16;16), del(5)/del(5q), del(17)/del(17p), normal or complex karyotypes, age and hemoglobin concentration at initial diagnosis were statistically significant markers predictive of complete remission, while t(8;21), del(5)/del(5q), inv(16)/t(16;16), del(17)/del(17p), double-mutated CEBPA, CEBPA-bZIP, NPM1, FLT3-ITD, DNMT3A, SF3B1, U2AF1, and TP53 mutations, age, white blood cell count, peripheral blast count, serum lactate dehydrogenase level and hemoglobin concentration at initial diagnosis as well as extramedullary manifestations were predictive for 2-year overall survival. For prediction of complete remission and 2-year overall survival areas under the receiver operating characteristic curves ranged between 0.77–0.86 and between 0.63–0.74, respectively in our test set, and between 0.71–0.80 and 0.65–0.75 in the external validation cohort. We demonstrated the feasibility of ML for risk stratification in AML as a model disease for hematologic neoplasms, using a scalable and reusable ML framework. Our study illustrates the clinical applicability of ML as a decision support system in hematology.

Alloreactivity or opportunistic infections following allogeneic stem cell transplantation are difficult to predict and contribute to post-transplantation mortality. How these immune reactions result in changes to the T-cell receptor repertoire remains largely unknown. Using next-generation sequencing, the T-cell receptor alpha (TRα) repertoire of naïve and memory CD8+ T cells from 25 patients who had received different forms of allogeneic transplantation was analyzed. In parallel, reconstitution of the CD8+/CD4+ T-cell subsets was mapped using flow cytometry. When comparing the influence of anti-T-cell therapy, a delay in the reconstitution of the naïve CD8+ T-cell repertoire was observed in patients who received in vivo T-cell depletion using antithymocyte globulin or post-transplantation cyclophosphamide in case of haploidentical transplantation. Sequencing of the TRα identified a repertoire consisting of more dominant clonotypes (>1% of reads) in these patients at 6 and 18 months post transplantation. When comparing donor and recipient, approximately 50% and approximately 80% of the donors’ memory repertoire were later retrieved in the naïve and memory CD8+ T-cell receptor repertoire of the recipients, respectively. Although there was a remarkable expansion of single clones observed in the recipients’ memory CD8+ TRα repertoire, no clear association between graft-versus-host disease or cytomegalovirus infection and T-cell receptor diversity was identified. A lower TRα diversity was observed in recipients of a cytomegalovirus-seropositive donor (P=0.014). These findings suggest that CD8+ T-cell reconstitution in transplanted patients is influenced by the use of T-cell depletion or immunosuppression and the donor repertoire.