-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.

646 Individualized Treatment-Adjusted Risk Stratification in Newly Diagnosed Multiple Myeloma

Program: Oral and Poster Abstracts
Type: Oral
Session: 652. Multiple Myeloma and Plasma Cell Dyscrasias: Clinical and Epidemiological: Prognostic Markers in Multiple Myeloma
Hematology Disease Topics & Pathways:
Research, artificial intelligence (AI), Translational Research, Clinical Research, Combination therapy, genomics, Plasma Cell Disorders, bioinformatics, patient-reported outcomes, Diseases, Therapies, Lymphoid Malignancies, computational biology, Biological Processes, Technology and Procedures, machine learning, omics technologies
Sunday, December 11, 2022: 5:15 PM

Francesco Maura, MD1, Arjun Raj Rajanna, MSc1*, Andriy Derkach, PhD2*, Bachisio Ziccheddu, PhD3*, Niels Weinhold, PhD4*, Kylee H Maclachlan, MBBCh, PhD5, Benjamin Diamond1*, Faith E. Davies, MD6*, Eileen Boyle6*, Brian A. Walker, PhD7, Alexandra M Poos, PhD4*, Malin Hultcrantz, MD, PhD5, Ariosto Siqueira Silva, PhD8*, Oliver Hampton, PhD9*, Jamie Teer, PhD8*, Niccolo Bolli, MD10*, Graham Jackson, MBBS, FRCP, FRCPath, MA, DM11, Martin F. Kaiser, MD, FRCP, FRCPath12, Charlotte Pawlyn, PhD13, Gordon Cook14*, Dennis Verducci1*, Dickran Kazandjian, MD1, Frits van Rhee15, Saad Usmani, MD16, Ken H. Shain, MD, PhD8, Marc S Raab, MD4*, Gareth J. Morgan, MD6 and Ola Landgren, MD3

1Myeloma Division, University of Miami, Sylvester Comprehensive Cancer Center, Miami
2Department of Biostatistics and Epidemiology, Memorial Sloan Kettering Cancer Center, New York, NY
3Myeloma Service, Sylvester Comprehensive Cancer Center, University of Miami, Miami, FL
4Multiple Myeloma Research Group, Department of Internal Medicine V, University Hospital Heidelberg, Heidelberg, Germany
5Myeloma Service, Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY
6NYU Langone, Perlmutter Cancer Center, New York
7Melvin and Bren Simon Comprehensive Cancer Center, Division of Hematology Oncology, Indiana University, Indianapolis, IN
8Department of Malignant Hematology, Moffitt Cancer Center, Tampa
9M2GEN, Tampa, FL
10Hematology Unit, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico & University of Milan, Milan, Italy
11Department of Haematology, NCCC Freeman Road Hospital, Newcastle Upon Tyne, United Kingdom
12The Institute of Cancer Research, London, ENG, United Kingdom
13The Institute of Cancer Research, London, United Kingdom
14Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom
15Myeloma Center, University of Arkansas for Medical Sciences, Little Rock, AR
16Myeloma Service, Memorial Sloan Kettering Cancer Center, New York

Introduction. For newly diagnosed multiple myeloma (NDMM) patients, median overall survival (OS) and progression free survival (PFS) have dramatically improved during recent years due to the introduction of novel agents. Unfortunately, a subset of patients with NDMM does not benefit from newer therapies reflected in persisting poor outcomes. In contrast, another subset has favorable outcomes despite receiving limited therapy. Though having demonstrated that several genomic events contribute to clinical outcomes, yet the “one-size-fits-all” treatment paradigm remains dominant for NDMM. Here, we present the first artificial intelligence individualized prediction model for NDMM to facilitate individually tailored therapeutic decisions.

Methods. We included 1840 patients with available clinical and genomic data from the following cohorts: MMRF CoMMpass (n=1062), MGP (n=492), Moffit AVATAR (n=177), and MSKCC (n=109). The median follow up was 42 months. To build a treatment-adjusted predictive model of individualized risk for patients with NDMM, we considered 160 variables across clinical (e.g., age, ECOG, sex, ISS), therapeutics, genomics, and time-dependent treatments such as autologous stem cell transplant (ASCT) and continuous treatment (Palumbo et al. JCO 2015). A multi-state model was designed across two phases: induction (phase 1), and post-induction (phase 2). Phase 1 included patients that: 1) completed the induction without progression (PD); 2) PD of failed to respond during induction remaining alive after; 3) PD during induction and subsequently died. Phase 2 have patients that: 4) PD after induction and were alive; 5) PD after induction and died; 6) reached remission after induction and were alive; 7) responded after induction and died due to other causes. We leveraged and compared survival methods based on deep neural networks (Neural Cox Non-proportional-hazards; NCNPH), Random Survival Forest (RSF), and Cox proportional-hazard (CPH).

Results. NCNPH showed the best cross-validated prognostic performance for OS with median Uno’s concordance (C=0.67), followed by RSF (C=0.65) and CPH (C=0.64; Fig. 1a-b). Overall, the model significantly outperformed R2-ISS (C=0.6), ISS (C=0.59) and R-ISS (C=0.57; Fig. 1b). Additionally, the model found 28 genomic features to increase concordance accuracy for PFS by (3% in phase 1 and 1.5% in phase 2), and with greater effect on OS (10% in phase 1 and 5% in phase 2). The 14% of patients who did not respond in phase 1 were enriched for ISS3, age >75 y, 1q amp, NSD2 translocation, TP53 mutations, and deletions on 17p13 and 1p.

Varying therapies emerged as a key determinant of risk, in particular, in phase 2, supporting the idea that effective combinations can have a different impact in individual patients and have the potential to significantly change the clinical outcome despite poor prognostication. The model not only predicts patient risk but also the impact of various treatment strategies (i.e., treatment variance). We identified 9 distinct clusters (C#1-9) based on predicted risk and treatment variance. C#8 and C#9 show favorable outcome, especially with ASCT and continuous treatment. C#4 and C#5 included patients with favorable outcome but low treatment variance where ASCT had marginal impact. C#6 had a substantial presence of high-risk patients associated with low variance, age >75y, 1q gain, and NSD2 translocations. Interestingly, NSD2 translocated patients not included in C#6 had an intermediate favorable outcome (p<0.0001). Early PD was observed in C#1 and C#7, both enriched for low treatment variance, and high risk genomic and clinical features. Finally, we identified a group of high-risk patients (C#2 and C#3) with high treatment variance whose poor outcome was mostly driven by a suboptimal treatment (i.e., use of doublet, no ASCT, no continuous treatment) rather than presence of distinct clinical and genomic features, highlighting the need for treatment to be considered to build more robust and accurate prognostic models.

Conclusion: This work shows the first comprehensive model integrating new and historical features to train a neural network for individualized risk prediction in NDMM. Utilizing data from 1840 patients that received a variety of therapies, the model captures the interaction of genomic, clinical and therapy factors, enabling personally-tailored therapeutic decisions in NDMM.

Disclosures: Davies: Takeda, Abbvie, Amgen, BMS/Celgene, Sanofi, GSK, Janssen: Membership on an entity's Board of Directors or advisory committees. Walker: Genentech: Research Funding; Bristol Myers Squibb: Research Funding. Hultcrantz: Bristol-Myers Squibb: Membership on an entity's Board of Directors or advisory committees; Amgen, Daichii Sankyo, Cosette, GSK: Research Funding; GSK: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Intellisphere LLC: Consultancy; Curio Science LLC: Consultancy. Hampton: M2GEN: Current Employment. Jackson: BMS: Consultancy, Honoraria, Speakers Bureau; Takeda: Consultancy, Honoraria, Research Funding, Speakers Bureau; amgen: Consultancy, Honoraria, Research Funding, Speakers Bureau; J and |J: Consultancy, Honoraria, Speakers Bureau; Pfizer: Consultancy, Honoraria; GSK: Consultancy, Honoraria, Speakers Bureau; Sanofi: Consultancy, Honoraria, Speakers Bureau; Oncopeptides: Consultancy. Kaiser: Janssen: Honoraria, Research Funding; BMS/Celgene: Honoraria, Research Funding; Karyopharm: Consultancy; Takeda: Honoraria; Pfizer: Consultancy; AbbVie: Consultancy; GSK: Consultancy; Seattle Genetics: Consultancy. Pawlyn: Janssen: Consultancy, Honoraria, Other: Travel support; Sanofi: Consultancy, Honoraria; Celgene/BMS: Consultancy, Honoraria; Abbvie: Consultancy. Cook: Takeda, BMS, Amgen, Roche, Janssen, Sanofi, Karyopharm, Pfizer: Consultancy; Takeda, BMS: Research Funding; Takeda, BMS, Amgen, Janssen, Sanofi: Speakers Bureau. Kazandjian: Plexus Communications: Honoraria; Curio Science: Honoraria; Sanofi: Membership on an entity's Board of Directors or advisory committees; Aptitude Health: Honoraria; MMRF: Honoraria; Arcellx: Membership on an entity's Board of Directors or advisory committees; SINTOMA: Honoraria; BMS: Membership on an entity's Board of Directors or advisory committees; CURE: Honoraria. van Rhee: Janssen Pharmaceuticals: Research Funding; Karyopharm: Consultancy; GlaxoSmithKline: Consultancy; Takeda: Consultancy; Bristol Myers Squibb: Research Funding; EUSA Pharma: Consultancy. Usmani: AbbVie, Amgen, BMS, Celgene, EdoPharma, Genentech, Gilead, GSK, Janssen Pharmaceuticals, Oncopeptides, Sanofi, Seagen Inc., formerly Seattle Genetics, Inc., Secura Bio, Inc., SkylineDX, Takeda, TeneoBio , Amgen, Array Biopharma, BMS, Celgene, GSK, Janssen: Research Funding; Amgen, Array Biopharma, BMS, Celgene, GSK, Janssen Pharmaceuticals, Merck, Pharmacyclics, Sanofi, Seagen Inc., formerly Seattle Genetics, Inc., SkylineDX, Takeda: Consultancy; Amgen, BMS, Janssen Pharmaceuticals, Sanofi: Speakers Bureau. Shain: Bristol Myers Squibb (BMS), Janssen, GlaxoSmithKline (GSK), Adaptive, Sanofi, and Takeda, and Amgen: Honoraria; GSK, Janssen and BMS: Membership on an entity's Board of Directors or advisory committees; GSK, BMS, Sanofi, Karyopharm, Takeda, Janssen, Adaptive and Amgen: Speakers Bureau; AbbVie and Karyopharm: Research Funding; Janssen and BMS: Other: PI of clinical trials. Raab: Takeda: Membership on an entity's Board of Directors or advisory committees; Sanofi: Membership on an entity's Board of Directors or advisory committees; Novartis: Membership on an entity's Board of Directors or advisory committees; Heidelberg Pharma: Research Funding; BMS: Membership on an entity's Board of Directors or advisory committees; Amgen: Membership on an entity's Board of Directors or advisory committees. Landgren: Pfizer: Consultancy; Amgen: Research Funding; Merck: Consultancy, Other: Independent Data Monitoring Committee (IDMC) member for clinical trials; Janssen: Consultancy, Other: Independent Data Monitoring Committee (IDMC) member for clinical trials, Research Funding.

*signifies non-member of ASH