Affordable Access

Publisher Website

A Machine Learning Model Based on Tumor and Immune Biomarkers to Predict Undetectable MRD and Survival Outcomes in Multiple Myeloma.

  • Guerrero, Camila1
  • Puig, Noemi2
  • Cedena, Maria-Teresa3
  • Goicoechea, Ibai1
  • Perez, Cristina1
  • Garcés, Juan-José1
  • Botta, Cirino4
  • Calasanz, Maria-Jose1
  • Gutierrez, Norma C2
  • Martin-Ramos, Maria-Luisa3
  • Oriol, Albert5
  • Rios, Rafael6
  • Hernandez, Miguel-Teodoro7
  • Martinez-Martinez, Rafael8
  • Bargay, Joan9
  • de Arriba, Felipe10
  • Palomera, Luis11
  • Gonzalez-Rodriguez, Ana Pilar12
  • Mosquera-Orgueira, Adrian13
  • Gonzalez-Perez, Marta-Sonia13
  • And 7 more
  • 1 Clinica Universidad de Navarra, Centro de Investigacion Medica Aplicada (CIMA), Instituto de Investigacion Sanitaria de Navarra (IDISNA), CIBER-ONC number CB16/12/00369, Pamplona, Spain. , (Spain)
  • 2 Instituto de investigacion biomedica de Salamanca (IBSAL), Hospital Universitario de Salamanca Hematologia, Salamanca, Spain. , (Spain)
  • 3 Hospital Universitario 12 de Octubre, Madrid, Spain. , (Spain)
  • 4 Hematology Unit, Department of Oncology, Annunziata Hospital, Cosenza, Italy. , (Italy)
  • 5 Institut Catala d'Oncologia L'Hospitalet, Barcelona, Spain. , (Spain)
  • 6 Hospital Universitario Virgen de las Nieves, Instituto de Investigacion Biosanitaria, Granada, Spain. , (Spain)
  • 7 Hospital Universitario de Canarias, Santa Cruz de Tenerife, Spain. , (Spain)
  • 8 Hospital Clinico Universitario San Carlos, Madrid, Spain. , (Spain)
  • 9 Hospital Universitario Son Llatzer, Institut d' investigacio Illes Balears (IdISBa), Palma de Mallorca, Spain. , (Spain)
  • 10 Hospital Morales Meseguer, IMIB-Arrixaca, Universidad de Murcia, Murcia, Spain. , (Spain)
  • 11 Hospital Clinico Universitario Lozano Blesa, Zaragoza, Spain. , (Spain)
  • 12 Hospital Central de Asturias, Oviedo, Spain. , (Spain)
  • 13 Complejo Hospitalario Universitario de Santiago de Compostela (CHUS), SERGAS, Santiago de Compostela, Spain. , (Spain)
  • 14 Hospital Clinic, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain. , (Spain)
Published Article
Clinical Cancer Research
American Association for Cancer Research
Publication Date
Jun 13, 2022
DOI: 10.1158/1078-0432.CCR-21-3430
PMID: 35063966


Undetectable measurable residual disease (MRD) is a surrogate of prolonged survival in multiple myeloma. Thus, treatment individualization based on the probability of a patient achieving undetectable MRD with a singular regimen could represent a new concept toward personalized treatment, with fast assessment of its success. This has never been investigated; therefore, we sought to define a machine learning model to predict undetectable MRD at the onset of multiple myeloma. This study included 487 newly diagnosed patients with multiple myeloma. The training (n = 152) and internal validation cohorts (n = 149) consisted of 301 transplant-eligible patients with active multiple myeloma enrolled in the GEM2012MENOS65 trial. Two external validation cohorts were defined by 76 high-risk transplant-eligible patients with smoldering multiple myeloma enrolled in the Grupo Español de Mieloma(GEM)-CESAR trial, and 110 transplant-ineligible elderly patients enrolled in the GEM-CLARIDEX trial. The most effective model to predict MRD status resulted from integrating cytogenetic [t(4;14) and/or del(17p13)], tumor burden (bone marrow plasma cell clonality and circulating tumor cells), and immune-related biomarkers. Accurate predictions of MRD outcomes were achieved in 71% of cases in the GEM2012MENOS65 trial (n = 214/301) and 72% in the external validation cohorts (n = 134/186). The model also predicted sustained MRD negativity from consolidation onto 2 years maintenance (GEM2014MAIN). High-confidence prediction of undetectable MRD at diagnosis identified a subgroup of patients with active multiple myeloma with 80% and 93% progression-free and overall survival rates at 5 years. It is possible to accurately predict MRD outcomes using an integrative, weighted model defined by machine learning algorithms. This is a new concept toward individualized treatment in multiple myeloma. See related commentary by Pawlyn and Davies, p. 2482. ©2022 American Association for Cancer Research.

Report this publication


Seen <100 times