Unsupervised machine learning improves risk stratification in newly diagnosed multiple myeloma: an analysis of the Spanish Myeloma Group


Por: Orgueira, AM, Perez, MSG, Arias, JD, Rosinol, L, Oriol, A, Teruel, AI, Lopez, JM, Palomera, L, Granell, M, Blanchard, MJ, de la Rubia, J, de la Guia, AL, Rios, R, Sureda, A, Hernandez, MT, Bengoechea, E, Calasanz, MJ, Gutierrez, N, Martin, ML, Blade, J, Lahuerta, JJ, San Miguel, J, Mateos, MV

Publicada: 25 abr 2022
Resumen:
The International Staging System (ISS) and the Revised International Staging System (R-ISS) are commonly used prognostic scores in multiple myeloma (MM). These methods have significant gaps, particularly among intermediate-risk groups. The aim of this study was to improve risk stratification in newly diagnosed MM patients using data from three different trials developed by the Spanish Myeloma Group. For this, we applied an unsupervised machine learning clusterization technique on a set of clinical, biochemical and cytogenetic variables, and we identified two novel clusters of patients with significantly different survival. The prognostic precision of this clusterization was superior to those of ISS and R-ISS scores, and appeared to be particularly useful to improve risk stratification among R-ISS 2 patients. Additionally, patients assigned to the low-risk cluster in the GEM05 over 65 years trial had a significant survival benefit when treated with VMP as compared with VTD. In conclusion, we describe a simple prognostic model for newly diagnosed MM whose predictions are independent of the ISS and R-ISS scores. Notably, the model is particularly useful in order to re-classify R-ISS score 2 patients in 2 different prognostic subgroups. The combination of ISS, R-ISS and unsupervised machine learning clusterization brings a promising approximation to improve MM risk stratification.

Filiaciones:
Orgueira, AM:
 Hosp Clin Univ Santiago Compostela, La Coruna, Spain

Perez, MSG:
 Hosp Clin Univ Santiago Compostela, La Coruna, Spain

Arias, JD:
 Hosp Clin Univ Santiago Compostela, La Coruna, Spain

Rosinol, L:
 Inst Invest Biomed August Pi i Sunyer, Hosp Clin, Barcelona, Spain

Oriol, A:
 Hosp Germans Trias i Pujol, Inst Josep Carreras, Inst Catala Oncol, Badalona, Spain

Teruel, AI:
 Hosp Clin Valencia, Valencia, Spain

Lopez, JM:
 Univ Complutense Madrid, CNIO, Hosp Univ 12 Octubre, Madrid, Spain

Palomera, L:
 Hosp Clin Lozano Blesa, Zaragoza, Spain

Granell, M:
 Hosp Santa Creu & Sant Pau, Barcelona, Spain

Blanchard, MJ:
 Hosp Ramon & Cajal, Madrid, Spain

de la Rubia, J:
 Hosp Doctor Peset, Valencia, Spain

de la Guia, AL:
 Hosp Univ La Paz, Madrid, Spain

Rios, R:
 Hosp Virgen Nieves, CIBERESP, Ibs, Granada, Spain

Sureda, A:
 Univ Barcelona, IDIBELL, Inst Catala Oncol Hosp, Barcelona, Spain

Hernandez, MT:
 Hosp Univ Canarias, Santa Cruz De Tenerife, Spain

Bengoechea, E:
 Hosp Donostia, San Sebastian, Spain

Calasanz, MJ:
 Clin Univ Navarra, CIMA, CIBERONC, IDISNA, Pamplona, Spain

Gutierrez, N:
 Univ Salamanca, Hosp Univ Salamanca, Inst Invest Biomed Salamanca, Inst Biol Mol & Celular Canc,CSIC,CIBERONC, Salamanca, Spain

Martin, ML:
 Univ Complutense Madrid, CNIO, Hosp Univ 12 Octubre, Madrid, Spain

Blade, J:
 Inst Invest Biomed August Pi i Sunyer, Hosp Clin, Barcelona, Spain

Lahuerta, JJ:
 Univ Complutense Madrid, CNIO, Hosp Univ 12 Octubre, Madrid, Spain

San Miguel, J:
 Clin Univ Navarra, CIMA, CIBERONC, IDISNA, Pamplona, Spain

Mateos, MV:
 Univ Salamanca, Hosp Univ Salamanca, Inst Invest Biomed Salamanca, Inst Biol Mol & Celular Canc,CSIC,CIBERONC, Salamanca, Spain
ISSN: 20445385
Editorial
NATURE PUBLISHING GROUP, MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND, Reino Unido
Tipo de documento: Article
Volumen: 12 Número: 4
Páginas:
WOS Id: 000787307100001
ID de PubMed: 35468898
imagen Green Published, gold

MÉTRICAS