-Author name in bold denotes the presenting author
-Asterisk * with author name denotes a Non-ASH member
Clinically Relevant Abstract denotes an abstract that is clinically relevant.

PhD Trainee denotes that this is a recommended PHD Trainee Session.

Ticketed Session denotes that this is a ticketed session.

62 Machine Learning Provides Individualized Prediction of Outcomes after First Complete Remission in Adult AML Patients – Results from the Harmony Platform

Program: Oral and Poster Abstracts
Type: Oral
Session: 617. Acute Myeloid Leukemias: Biomarkers, Molecular Markers and Minimal Residual Disease in Diagnosis and Prognosis: Risk Refinement and Therapy Response
Hematology Disease Topics & Pathways:
artificial intelligence (AI), adult, Research, AML, Acute Myeloid Malignancies, health outcomes research, Clinical Research, genomics, Diseases, Biological Processes, Myeloid Malignancies, molecular biology, Technology and Procedures, Human, Study Population, machine learning, omics technologies
Saturday, December 9, 2023: 9:45 AM

Alberto Hernández Sánchez, MD1,2*, Javier Martínez Elicegui2*, Marta Sobas, MD, PhD3*, Eric Sträng4*, Axel Benner5*, María Abáigar, PhD2,6*, Gastone Castellani, PhD7*, Laura Tur8*, Peter J. M. Valk, PhD9, Angela Villaverde Ramiro10*, Klaus H Metzeler, MD11, Raúl Azibeiro Melchor1,2*, Jurjen Versluis, MD, PhD12*, Daniele Dall'Olio, PhD7*, Teresa González, PhD6*, Jesse M. Tettero, MD13,14,15*, Joaquin Martinez-Lopez, MD, PhD16*, Helena Fidalgo2*, Jorge Sierra, MD17*, Frederik Damm4*, Ken I Mills, BSc, PhD, FRCPath18, Soren Lehmann, MD, PhD19*, Ian Thomas20*, Jiří Mayer, MD21,22, Christian Thiede, MD23, Maria Teresa Voso, MD24, Guillermo Sanz, MD, PhD25,26*, Konstanze Döhner27, Michael Heuser, MD28, Torsten Haferlach, MD, PhD29, Amin T. Turki, MD30,31*, Dirk Reinhardt, MD, PhD30*, Michel van Speybroeck32*, Renate Schulze-Rath, MD, MSc33*, Martje Barbus, PhD34*, John E Butler, PhD35*, Jesús María Hernández-Rivas, PhD2,6,36, Brian Huntly, PhD37*, Gert Ossenkoppele, MD, PhD13,15,38, Hartmut Döhner, MD27 and Lars Bullinger4

1University Hospital of Salamanca, Salamanca, Spain
2Institute of Biomedical Research of Salamanca (IBSAL), Salamanca, Spain
3Wroclaw Medical University, Wroclaw, Poland
4Charité Universitätsmedizin Berlin, Berlin, Germany
5Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
6Cancer Research Center of Salamanca (USAL-CSIC), Salamanca, Spain
7University of Bologna, Bologna, Italy
8GMV Innovating Solutions, Valencia, Spain
9Department of Hematology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, Netherlands
10University of Salamanca, IBSAL, IBMCC, CSIC, Cancer Research Center, Department of Hematology - Hospital Universitario de Salamanca, Salamanca, Spain
11University of Leipzig, Leipzig, Germany
12Erasmus MC Cancer Institute, University Medical Center Rotterdam, Department of Hematology, Rotterdam, Netherlands
13Amsterdam University Medical Center, Amsterdam, Netherlands
14Imaging and Biomarkers, Cancer Center Amsterdam, Amsterdam, Netherlands
15VU University Medical Center, Amsterdam, Netherlands
16Hospital 12 de Octubre, Madrid, Spain
17Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
18Patrick G Johnston Centre for Cancer Research, Queen's University Belfast, Belfast, NI, United Kingdom
19Department of Medical Sciences, Hematology, Uppsala University, University Hospital Uppsala, Uppsala, Sweden
20Cardiff University, Cardiff, United Kingdom
21Masaryk University, Brno, Czech Republic
22University Hospital Brnoand, University Hospital Brnoand, Czech Republic
23Department of Medicine I, University Hospital Carl Gustav Carus, Dresden, Germany
24University of Rome “Cattolica S. Cuore”, Rome, Italy
25Hospital Universitario y Politécnico e Instituto de Investigación Sanitaria La Fe, Valencia, Spain
26CIBERONC, Instituto de Salud Carlos III, Valencia, Spain
27Department of Internal Medicine III, University Hospital of Ulm, Ulm, Germany
28Department of Hematology, Hemostasis, Oncology and Stem Cell Transplantation, Hannover Medical School, Hannover, Germany
29MLL Munich Leukemia Laboratory, Munich, Germany
30Essen University Hospital, Essen, Germany
31West-German Cancer Center, Essen, Germany
32Janssen Pharmaceutica NV, Beerse, Belgium
33Bayer AG, Berlin, Germany
34AbbVie Germany GmbH & Co. KG, Wiesbaden, Germany
35Bayer Innovation GmbH, Duesseldorf, Germany
36Servicio de Hematología, Hospital Universita­rio de Salamanca, Universidad de Salamanca, Salamanca, Spain
37Wellcome - MRC Cambridge Stem Cell Institute, Cambridge, United Kingdom
38Cancer Center Amsterdam, Amsterdam, Netherlands


Acute myeloid leukemia (AML) is a heterogeneous disease with high disease-related mortality and allogeneic hematopoietic stem cell transplantation (allo-HSCT) remains the only curative option for a large proportion of patients. However, allo-HSCT has a significant transplant-related mortality (TRM), so a careful evaluation between risk of disease relapse and TRM is needed for the challenging decision of whom to transplant in first complete remission (CR1). The European LeukemiaNet (ELN) provides a 3-tier static risk classification which is already a useful guidance, although dynamic risk assessment using measurable residual disease (MRD) information should also be taken into account. However, the intermediate-risk group is characterized by a wide heterogeneity and there are also some favorable-risk patients who require allo-HSCT because of early relapses after CR1. Therefore, more precise prediction tools are warranted to provide additional information valuable for clinical decision-making.


To develop and validate a model that provides individualized outcome estimations in adult AML patients achieving CR1 with intensive treatment approaches.


From the HARMONY Platform including 7467 AML patients at the time of the analysis, we selected patients aged 18-70 years old who received intensive treatment, achieved CR and were not consolidated with allo-HSCT in CR1. Patients who were refractory to first line chemotherapy or who had a relapse-free survival (RFS) of less than two months after achieving CR were excluded. A Bayesian Additive Regression Trees (BART) nonparametric machine learning model was used to predict the individualized likelihood of RFS, cumulative incidence of relapse (CIR) and overall survival (OS) in 1863 AML patients who were also selected based on the availability of comprehensive mutational information by next-generation sequencing analysis. Genomic aberrations that were present in at least 10 patients were included in the model. In order to test the accuracy of the model, a 10-fold cross-validation was applied using the area under receiver operating curve (AUC) at predefined time points (1, 2, 3, 4 and 5 years). Subsequently, the model was validated using an external publicly available database (Tazi et al, Nat. Commun. 2022) which included 722 patients based on identical inclusion criteria.


The study population of 1863 adult AML patients in CR1 included 51.2% of males and median age was 50 years. Regarding ELN2022 classification, 52% of patients were classified as favorable, 30% as intermediate and 18% as adverse risk. Most frequently mutated genes were NPM1 (35.9%), DNMT3A (25.6%) and NRAS (21.6%). The HARMONY model was able to estimate individualized likelihood of RFS, CIR and OS for all patients, providing confidence intervals for all estimations. Moreover, we could predict outcomes with increased accuracy over ELN2022 at all predefined time points. At 5 years, the AUC value was significantly better for the HARMONY model than ELN2022 in predicting RFS (0.729 vs 0.679, p=0.003), CIR (0.729 vs 0.680, p=0.002) and OS (0.733 vs 0.675, p<0.001) (figure 1A). Validation in an external independent AML cohort confirmed superiority of the HARMONY model in predicting RFS (5-year AUC 0.714 vs 0.609, p <0.001), CIR (0.713 vs 0.610, p <0.001) and OS (0.737 vs 0.638, p <0.001) as compared to the ELN2022 risk stratification (figure 1B), despite the fact that there was a different distribution of risk categories (28% favorable, 45% intermediate and 27% adverse risk).


Analysis of large well-defined AML cohorts allows the development of increasingly precise predictive models for clinically relevant scenarios. The HARMONY machine learning model provides individualized outcome prediction for patients aged 18-70 years in CR1 consolidated without allo-HSCT and might be used in the future for clinical decision-making. The model can be accessed online via an interactive web calculator () and, while it has been validated using a large independent AML cohort, future studies are required focusing on prospective validation. Furthermore, the incorporation of additional variables such as MRD and the inclusion of patients treated with targeted therapies and non-intensive approaches will provide more accurate risk predictions.

Disclosures: Benner: Sanofi: Other: Travel, Accomondations, Expenses. Metzeler: BMS: Consultancy, Honoraria; AbbVie: Honoraria, Research Funding; Pfizer: Honoraria; Otsuka: Honoraria; Janssen: Honoraria; Novartis: Consultancy. Versluis: AbbVie: Honoraria; ExCellThera: Consultancy. Damm: Gilead: Honoraria; Incyte: Honoraria; Roche: Honoraria; Novartis: Honoraria; AbbVie: Honoraria; Astra Zeneca: Honoraria. Mayer: MSD: Research Funding; Novartis: Research Funding. Voso: Astra Zeneca: Speakers Bureau; Abbvie: Speakers Bureau; Celgene/BMS: Other: Advisory Board; Novartis: Speakers Bureau; Jazz: Other: Advisory Board; Jazz: Speakers Bureau; Astellas: Speakers Bureau; Novartis: Research Funding; Celgene/BMS: Research Funding, Speakers Bureau; Syros: Other: Advisory Board. Döhner: Daiichi Sankyo: Consultancy; Abbvie: Consultancy; Janssen: Consultancy; Jazz: Consultancy; Roche: Consultancy, Speakers Bureau; Novartis: Consultancy, Research Funding, Speakers Bureau; CTI: Consultancy, Speakers Bureau; Celgene: Consultancy, Research Funding, Speakers Bureau; BMS: Consultancy, Research Funding, Speakers Bureau; Astellas: Research Funding; Agios: Research Funding. Heuser: Loxo Oncology: Research Funding; Astellas: Research Funding; Karyopharm: Research Funding; BergenBio: Research Funding; Bristol-Myers Squibb: Consultancy, Research Funding; Glycostem: Consultancy, Research Funding; Jazz Pharmaceuticals: Consultancy, Honoraria, Research Funding; Janssen: Honoraria; Agios: Research Funding; Novartis: Honoraria; Pfizer: Consultancy, Honoraria; Certara: Honoraria; Sobi: Honoraria; Servier: Consultancy; Abbvie: Consultancy, Research Funding; PinotBio: Consultancy, Research Funding; Amgen: Consultancy; LabDelbert: Consultancy. Haferlach: MLL Munich Leukemia Laboratory: Current Employment, Other: Equity Ownership. van Speybroeck: Johnson & Johnson: Current Employment, Current equity holder in publicly-traded company. Schulze-Rath: Bayer AG: Current Employment. Barbus: AbbVie Germany GmbH & Co. KG: Current Employment. Butler: Bayer AG: Current Employment. Hernández-Rivas: Amgen: Honoraria, Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Pfizer: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Celgene/BMS: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Novartis: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; GSK: Consultancy, Honoraria, Speakers Bureau. Ossenkoppele: Servier: Consultancy; Novartis: Consultancy, Honoraria, Research Funding; Roche: Consultancy, Membership on an entity's Board of Directors or advisory committees; JazzPharmaceuticals: Consultancy; BMS/Celgene: Consultancy, Honoraria; Janssen: Consultancy; Abbvie: Consultancy; AGIOS: Consultancy, Honoraria; Amgen: Consultancy; Pfizer: Research Funding; Gilead: Consultancy; Astellas: Consultancy, Honoraria. Döhner: Novartis: Consultancy, Honoraria, Research Funding; Syndax: Honoraria; Abbvie: Consultancy, Honoraria, Research Funding; AstraZeneca: Consultancy, Honoraria; Agios: Consultancy, Honoraria, Research Funding; Amgen: Consultancy, Honoraria, Research Funding; Stemline: Consultancy, Honoraria; Servier: Consultancy, Honoraria; Pfizer: Research Funding; Kronos-Bio: Research Funding; Berlin-Chemie: Consultancy, Honoraria; Astellas: Consultancy, Honoraria, Research Funding; Bristol Myers Squibb: Consultancy, Honoraria, Research Funding; Celgene: Consultancy, Honoraria, Research Funding; Daiichi Sankyo: Consultancy, Honoraria; Gilead: Consultancy, Honoraria; Janssen: Consultancy, Honoraria; Jazz Pharmaceuticals: Consultancy, Honoraria, Research Funding. Bullinger: Bristol-Myers Squibb: Honoraria; Daiichi Sankyo: Honoraria; Amgen: Honoraria; Abbvie: Honoraria, Membership on an entity's Board of Directors or advisory committees; Jazz Pharmaceuticals: Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Bayer Oncology: Research Funding; Pfizer: Honoraria, Membership on an entity's Board of Directors or advisory committees; Gilead: Honoraria, Membership on an entity's Board of Directors or advisory committees; Astellas: Honoraria; Celgene/BMS: Honoraria, Membership on an entity's Board of Directors or advisory committees; Janssen: Honoraria, Membership on an entity's Board of Directors or advisory committees; Novartis: Honoraria, Membership on an entity's Board of Directors or advisory committees; Sanofi: Honoraria.

*signifies non-member of ASH