Precision oncology in AML: validation of the prognostic value of the knowledge bank approach and suggestions for improvement

Journal of Hematology & Oncology

Richard M. Stone¹  Brian Giacopelli²  Marius Bill²  Christopher C. Oakes³  Ramiro Garzon³  Clara D. Bloomfield³  Dimitrios Papaioannou³  Jessica Kohlschmidt⁴  Deedra Nicolet⁴  Ann-Kathrin Eisfeld⁵  John C. Byrd⁵  Krzysztof Mrózek⁶  Andrew J. Carroll⁷  Bayard L. Powell⁸  Jonathan E. Kolitz⁹ 

[1] Department of Medical Oncology, Dana-Farber/Partners CancerCare, Boston, MA, USA;The Ohio State University Comprehensive Cancer Center, 460 West 12th Avenue, 43210-1228, Columbus, OH, USA;The Ohio State University Comprehensive Cancer Center, 460 West 12th Avenue, 43210-1228, Columbus, OH, USA;Division of Hematology, Department of Internal Medicine, The Ohio State University Comprehensive Cancer Center, 400 West 12th Avenue, Wiseman Hall, Suite 455, 43210-1228, Columbus, OH, USA;The Ohio State University Comprehensive Cancer Center, 460 West 12th Avenue, 43210-1228, Columbus, OH, USA;The Ohio State Comprehensive Cancer Center, Clara D. Bloomfield Center for Leukemia Outcomes Research, The Ohio State University, Columbus, OH, USA;Alliance Statistics and Data Center, The Ohio State University Comprehensive, Cancer Center, Columbus, OH, USA;The Ohio State University Comprehensive Cancer Center, 460 West 12th Avenue, 43210-1228, Columbus, OH, USA;The Ohio State Comprehensive Cancer Center, Clara D. Bloomfield Center for Leukemia Outcomes Research, The Ohio State University, Columbus, OH, USA;Division of Hematology, Department of Internal Medicine, The Ohio State University Comprehensive Cancer Center, 400 West 12th Avenue, Wiseman Hall, Suite 455, 43210-1228, Columbus, OH, USA;The Ohio State University Comprehensive Cancer Center, 460 West 12th Avenue, 43210-1228, Columbus, OH, USA;The Ohio State Comprehensive Cancer Center, Clara D. Bloomfield Center for Leukemia Outcomes Research, The Ohio State University, Columbus, OH, USA;The Ohio State University Comprehensive Cancer Center, 444 Tzagournis Medical Research Facility, 420 West 12th Avenue, 43210-1228, Columbus, OH, USA;University of Alabama At Birmingham, Birmingham, AL, USA;Wake Forest Baptist Comprehensive Cancer Center, Winston-Salem, NC, USA;Zucker School of Medicine At Hofstra/Northwell, Northwell Health Cancer Institute, Lake Success, NY, USA;

关键词: Acute myeloid leukemia;    Knowledge bank;    Next-generation sequencing;    Gene mutations;    Clinical outcome;   

DOI  :  10.1186/s13045-021-01118-x

来源: Springer

【 摘 要 】

Recently, a novel knowledge bank (KB) approach to predict outcomes of individual patients with acute myeloid leukemia (AML) was developed using unbiased machine learning. To validate its prognostic value, we analyzed 1612 adults with de novo AML treated on Cancer and Leukemia Group B front-line trials who had pretreatment clinical, cytogenetics, and mutation data on 81 leukemia/cancer-associated genes available. We used receiver operating characteristic (ROC) curves and the area under the curve (AUC) to evaluate the predictive values of the KB algorithm and other risk classifications. The KB algorithm predicted 3-year overall survival (OS) probability in the entire patient cohort (AUCKB = 0.799), and both younger (< 60 years) (AUCKB = 0.747) and older patients (AUCKB = 0.770). The KB algorithm predicted non-remission death (AUCKB = 0.860) well but was less accurate in predicting relapse death (AUCKB = 0.695) and death in first complete remission (AUCKB = 0.603). The KB algorithm’s 3-year OS predictive value was higher than that of the 2017 European LeukemiaNet (ELN) classification (AUC2017ELN = 0.707, p < 0.001) and 2010 ELN classification (AUC2010ELN = 0.721, p < 0.001) but did not differ significantly from that of the 17-gene stemness score (AUC17-gene = 0.732, p = 0.10). Analysis of additional cytogenetic and molecular markers not included in the KB algorithm revealed that taking into account atypical complex karyotype, infrequent recurrent balanced chromosome rearrangements and mutational status of the SAMHD1, AXL and NOTCH1 genes may improve the KB algorithm. We conclude that the KB algorithm has a high predictive value that is higher than those of the 2017 and 2010 ELN classifications. Inclusion of additional genetic features might refine the KB algorithm.

【 授权许可】

CC BY