Genetic mutations (somatic or germline), cytogenetic abnormalities and their combinations contribute to the heterogeneity of acute myeloid leukemia (AML) phenotypes. To date, prototypic founder lesions [e.g., t(8;21), inv(16), t(15;17)] define only a fraction of AML subgroups with specific prognoses. Indeed, in a larger proportion of AML patients, somatic mutations or cytogenetic abnormalities potentially serve as driver lesions in combination with numerous acquired secondary hits. However, their combinatorial complexity can preclude the resolution of distinct genomic classifications and overlap across classical pathomorphologic AML subtypes, including de novo/primary (pAML) and secondary AML (sAML) evolving from an antecedent myeloid neoplasm (MN). These prognostically discrete AML subtypes are themselves nonspecific due to variable understanding of their pathogenetic links, especially in cases without overt dysplasia. Without dysplasia, reliance is mainly on anamnestic clinical information that might be unavailable or cannot be correctly assigned due to a short prodromal history of antecedent MN. We explored the potential of genomic markers to sub-classify AML objectively and provide unbiased personalized prognostication, irrespective of the clinicopathological information, and thus become a standard in AML assessment.

We collected and analyzed genomic data from a multicenter cohort of 6788 AML patients using standard and machine learning (ML) methods. A total of 13,879 somatic mutations were identified and used to predict traditional pathomorphologic AML classifications. Logistic regression modeling (LRM) detected mutations in CEBPA (both monoallelic "CEBPAMo" and biallelic "CEBPABi"), DNMT3A, FLT3ITD, FLT3TKD, GATA2, IDH1, IDH2R140, NRAS, NPM1 and WT1 being enriched in pAML while mutations in ASXL1, RUNX1, SF3B1, SRSF2, U2AF1, -5/del(5q), -7/del(7q), -17/del(17P), del(20q), +8 and complex karyotype being prevalent in sAML. Despite these significant findings, the genomic profiles of pAML vs. sAML identified by LRM resulted in only 74% cross-validation accuracy of the predictive performance when used to re-assign them. Therefore, we applied Bayesian Latent Class Analysis that identified 4 unique genomic clusters of distinct prognoses [low risk (LR), intermediate-low risk (Int-Lo), intermediate-high risk (Int-Hi) and high risk (HR) of poor survival) that were validated by survival analysis. To link each prognostic group to pathogenetic features, we generated a random forest (RF) model that extracted invariant genomic features driving each group and resulted in 97% cross-validation accuracy when used for prognostication. The model's globally most important genomic features, quantified by mean decrease in accuracy, included NPM1MT, RUNX1MT, ASXL1MT, SRSF2MT, TP53MT, -5/del(5q), DNMT3AMT, -17/del(17p), BCOR/L1MT and others. The LR group was characterized by the highest prevalence of normal cytogenetics (88%) and NPM1MT (100%; 86% with VAF>20%) with co-occurring DNMT3AMT (52%), FLT3ITD-MT (27%; 91% with VAF <50%), IDH2R140-MT (16%, while absent IDH2R172-MT), and depletion or absence of ASXL1MT, EZH2MT, RUNX1MT, TP53MT and complex cytogenetics. Int-Lo had a higher percentage of abnormal cytogenetics cases than LR, the highest frequency of CEBPABi-MT (9%), IDH2R172K-MT (4%), FLT3ITD-MT (14%) and FLT3TKD-MT (6%) occurring without NPM1MT, while absence of NPM1MT, ASXL1MT, RUNX1MT and TP53MT. Int-Hi had the highest frequency of ASXL1MT (39%), BCOR/L1MT (16%), DNMT3AMT without NPM1MT (19%), EZH2MT (9%), RUNX1MT (52%), SF3B1MT (7%), SRSF2MT (38%) and U2AF1MT (12%). Finally, HR had the highest prevalence of abnormal cytogenetics (96%), -5/del(5q) (68%), -7del(7q) (35%), -17del(17p) (31%) and the highest odds of complex karyotype (76%) as well as TP53MT (70%). The model was then internally and externally validated using a cohort of 203 AML cases from the MD Anderson Cancer Center. The RF prognostication model and group-specific survival estimates will be available via a web-based open-access resource.

In conclusion, the heterogeneity inherent in the genomic changes across nearly 7000 AML patients is too vast for traditional prediction methods. Using newer ML methods, however, we were able to decipher a set of prognostic subgroups predictive of survival, allowing us to move AML into the era of personalized medicine.

Disclosures

Advani:OBI: Research Funding; Abbvie: Research Funding; Macrogenics: Research Funding; Glycomimetics: Consultancy, Other: Steering committee/ honoraria, Research Funding; Immunogen: Research Funding; Seattle Genetics: Other: Advisory board/ honoraria, Research Funding; Amgen: Consultancy, Other: steering committee/ honoraria, Research Funding; Kite: Other: Advisory board/ honoraria; Pfizer: Honoraria, Research Funding; Novartis: Consultancy, Other: advisory board; Takeda: Research Funding. Ravandi:Abbvie: Consultancy, Honoraria, Research Funding; Celgene: Consultancy, Honoraria; Amgen: Consultancy, Honoraria, Research Funding; Astellas: Consultancy, Honoraria, Research Funding; Orsenix: Consultancy, Honoraria, Research Funding; AstraZeneca: Consultancy, Honoraria; Jazz Pharmaceuticals: Consultancy, Honoraria, Research Funding; Xencor: Consultancy, Honoraria, Research Funding; Macrogenics: Research Funding; BMS: Consultancy, Honoraria, Research Funding. Carraway:Novartis: Consultancy, Speakers Bureau; Takeda: Other: Independent Advisory Committe (IRC); Stemline: Consultancy, Speakers Bureau; BMS: Consultancy, Other: Research support, Speakers Bureau; Abbvie: Other: Independent Advisory Committe (IRC); ASTEX: Other: Independent Advisory Committe (IRC); Jazz: Consultancy, Speakers Bureau. Saunthararajah:EpiDestiny: Consultancy, Current equity holder in private company, Membership on an entity's Board of Directors or advisory committees, Patents & Royalties. Kantarjian:Sanofi: Research Funding; Actinium: Honoraria, Membership on an entity's Board of Directors or advisory committees; Daiichi-Sankyo: Honoraria, Research Funding; BMS: Research Funding; Abbvie: Honoraria, Research Funding; Aptitute Health: Honoraria; Pfizer: Honoraria, Research Funding; Novartis: Honoraria, Research Funding; Jazz: Research Funding; Immunogen: Research Funding; Adaptive biotechnologies: Honoraria; Ascentage: Research Funding; Amgen: Honoraria, Research Funding; BioAscend: Honoraria; Delta Fly: Honoraria; Janssen: Honoraria; Oxford Biomedical: Honoraria. Kadia:Pfizer: Honoraria, Research Funding; Novartis: Honoraria; Cyclacel: Research Funding; Ascentage: Research Funding; Astellas: Research Funding; Cellenkos: Research Funding; JAZZ: Honoraria, Research Funding; Astra Zeneca: Research Funding; Celgene: Research Funding; Incyte: Research Funding; Pulmotec: Research Funding; Abbvie: Honoraria, Research Funding; Genentech: Honoraria, Research Funding; BMS: Honoraria, Research Funding; Amgen: Research Funding. Sekeres:Pfizer: Consultancy, Membership on an entity's Board of Directors or advisory committees; BMS: Consultancy, Membership on an entity's Board of Directors or advisory committees; Takeda/Millenium: Consultancy, Membership on an entity's Board of Directors or advisory committees. Maciejewski:Alexion, BMS: Speakers Bureau; Novartis, Roche: Consultancy, Honoraria.

Author notes

*

Asterisk with author names denotes non-ASH members.