Multiple myeloma (MM) remains mostly an incurable disease with a heterogeneous clinical evolution. Despite the availability of several prognostic scores, substantial room for improvement still exists. Promising results have been obtained by integrating clinical and biochemical data with gene expression profiling (GEP). In this report, we applied machine learning algorithms to MM clinical and RNAseq data collected by the CoMMpass consortium. We created a 50-variable random forests model (IAC-50) that could predict overall survival with high concordance between both training and validation sets (c-indexes, 0.818 and 0.780). This model included the following covariates: patient age, ISS stage, serum B2-microglobulin, first-line treatment, and the expression of 46 genes. Survival predictions for each patient considering the first line of treatment evidenced that those individuals treated with the best-predicted drug combination were significantly less likely to die than patients treated with other schemes. This was particularly important among patients treated with a triplet combination including bortezomib, an immunomodulatory drug (ImiD), and dexamethasone. Finally, the model showed a trend to retain its predictive value in patients with high-risk cytogenetics. In conclusion, we report a predictive model for MM survival based on the integration of clinical, biochemical, and gene expression data with machine learning tools.
Subscribe to Journal
Get full journal access for 1 year
only $33.25 per issue
All prices are NET prices.
VAT will be added later in the checkout.
Tax calculation will be finalised during checkout.
Rent or Buy article
Get time limited or full article access on ReadCube.
All prices are NET prices.
The code to train and validate IAC-50 of survival can be requested by e-mail to the corresponding author.
Hanbali A, Hassanein M, Rasheed W, Aljurf M, Alsharif F. The evolution of prognostic factors in multiple myeloma. Adv Hematol. 2017;2017:4812637.
Greipp PR, San Miguel J, Durie BG, Crowley JJ, Barlogie B, Bladé J, et al. International staging system for multiple myeloma. J Clin Oncol. 2005;23:3412–20.
Palumbo A, Avet-Loiseau H, Oliva S, Lokhorst HM, Goldschmidt H, Rosinol L, et al. Revised international staging system for multiple myeloma: a report from International Myeloma Working Group. J Clin Oncol. 2015;33:2863–9.
Chng WJ, Dispenzieri A, Chim CS, Fonseca R, Goldschmidt H, Lentzsch S, et al. IMWG consensus on risk stratification in multiple myeloma. Leukemia. 2014;28:269–77.
Kastritis E, Terpos E, Roussou M, Gavriatopoulou M, Migkou M, Eleutherakis-Papaiakovou E, et al. Evaluation of the revised international staging system in an independent cohort of unselected patients with multiple myeloma. Haematologica. 2017;102:593–9.
Walker I, Coady A, Neat M, Ladon D, Benjamin R, El-Najjar I, et al. Is the revised International staging system for myeloma valid in a real world population? Br J Haematol. 2018;180:451–4.
Harrell FE Jr, Califf RM, Pryor DB, Lee KL, Rosati RA. Evaluating the yield of medical tests. JAMA 1982;247:2543–6.
Zhang Y, Chen XL, Chen WM, Zhou HB. Prognostic nomogram for the overall survival of patients with newly diagnosed multiple myeloma. Biomed Res Int 2019;2019:5652935. Published 2019 Apr 8
Pawlyn C, Davies FE. Toward personalized treatment in multiple myeloma based on molecular characteristics. Blood. 2019;133:660–75.
Keats JJ, Reiman T, Maxwell CA, Taylor BJ, Larratt LM, Mant MJ, et al. In multiple myeloma, t(4;14)(p16;q32) is an adverse prognostic factor irrespective of FGFR3 expression. Blood. 2003;101:1520–9.
Boyd KD, Ross FM, Chiecchio L, Dagrada GP, Konn ZJ, Tapper WJ, et al. NCRI Haematology Oncology Studies Group. A novel prognostic model in myeloma based on co-segregating adverse FISH lesions and the ISS: analysis of patients treated in the MRC Myeloma IX trial. Leukemia. 2012;26:349–55.
Narita T, Inagaki A, Kobayashi T, Kuroda Y, Fukushima T, Nezu M, et al. t(14;16)-positive multiple myeloma shows negativity for CD56 expression and unfavorable outcome even in the era of novel drugs. Blood Cancer J. 2015;5:e285.
Teoh PJ, Chung TH, Sebastian S, Choo SN, Yan J, Ng SB, et al. p53 haploinsufficiency and functional abnormalities in multiple myeloma. Leukemia 2014;28:2066–74.
Fonseca R, Van Wier SA, Chng WJ, Ketterling R, Lacy MQ, Dispenzieri A, et al. Prognostic value of chromosome 1q21 gain by fluorescent in situ hybridization and increase CKS1B expression in myeloma. Leukemia. 2006;20:2034–40.
Hebraud B, Leleu X, Lauwers-Cances V, Roussel M, Caillot D, Marit G, et al. Deletion of the 1p32 region is a major independent prognostic factor in young patients with myeloma: the IFM experience on 1195 patients. Leukemia. 2014;28:675–9.
Walker BA, Mavrommatis K, Wardell CP, Ashby TC, Bauer M, Davies F, et al. A high-risk, double-hit, group of newly diagnosed myeloma identified by genomic analysis. Leukemia. 2019;33:159–70.
Walker BA, Boyle EM, Wardell CP, Murison A, Begum DB, Dahir NM, et al. Mutational spectrum, copy number changes, and outcome: results of a sequencing study of patients with newly diagnosed myeloma. J Clin Oncol. 2015;33:3911–20.
Joseph NS, Kaufman JL, Dhodapkar MV, Hofmeister CC, Almaula DK, Heffner LT, et al. Long-term follow-up results of lenalidomide, bortezomib, and dexamethasone induction therapy and risk-adapted maintenance approach in newly diagnosed multiple myeloma. J Clin Oncol. 2020;38(Jun):1928–37. Epub 2020 Apr 16. Erratum in: J Clin Oncol. 2020 Aug 10;38(23):2702. PMID: 32298201; PMCID: PMC7587409
Zimmerman T, Raje NS, Vij R, Reece D, Berdeja JG, Stephens LA, et al. Final results of a phase 2 trial of extended treatment (tx) with carfilzomib (CFZ), lenalidomide (LEN), and dexamethasone (carfilzomib-based triplets) plus autologous stem cell transplantation (ASCT) in newly diagnosed multiple myeloma (NDMM). Blood. 2016;128:675.
Stewart AK, Rajkumar SV, Dimopoulos MA, Masszi T, Špička I, Oriol A, et al. ASPIRE Investigators. Carfilzomib, lenalidomide, and dexamethasone for relapsed multiple myeloma. N Engl J Med. 2015;372:142–52.
Sidiqi MH, Aljama MA, Bin Riaz I, Dispenzieri A, Muchtar E, Buadi FK, et al. Bortezomib, lenalidomide, and dexamethasone (VRd) followed by autologous stem cell transplant for multiple myeloma. Blood Cancer J. 2018;8:106. Published 2018 Nov 8
Avet-Loiseau H, Bahlis NJ, Chng WJ, Masszi T, Viterbo L, Pour L, et al. Ixazomib significantly prolongs progression-free survival in high-risk relapsed/refractory myeloma patients. Blood. 2017;130(Dec):2610–8. Epub 2017 Oct. PMID: 29054911
Kumar S, Jacobus SJ, Cohen AD, Weiss M, Callander NS, Singh AA et al. Carfilzomib, lenalidomide, and dexamethasone (carfilzomib-based triplets) versus bortezomib, lenalidomide, and dexamethasone (VRd) for initial therapy of newly diagnosed multiple myeloma (NDMM): results of ENDURANCE (E1A11) phase III trial. J Clin Oncol. 2020 38:18_suppl, LBA3-LBA3
Gay F, Cerrato C, Petrucci MT, Zambello L, Gamberi B, Ballanti S et al. Efficacy of carfilzomib lenalidomide dexamethasone (carfilzomib-based triplets) with or without transplantation in newly diagnosed myeloma according to risk status: results from the FORTE trial. J Clin Oncol. 2019 37_suppl, 8002-8002
Rosiñol L, Oriol A, Rios R, Sureda A, Blanchard MJ, Hernández MT, et al. Bortezomib, lenalidomide, and dexamethasone as induction therapy prior to autologous transplant in multiple myeloma. Blood. 2019;134:1337–45.
van Rhee F, Giralt S, Barlogie B. The future of autologous stem cell transplantation in myeloma. Blood. 2014;124:328–33.
MMRF CoMMpass study: an update. Multiple myeloma research foundation. 2020. July 9, 2020. bit.ly/2BPiUH3.
Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. Ann Appl Stat. 2008;2:841–60. https://projecteuclid.org/euclid.aoas/1223908043
Trapnell C, Roberts A, Goff L, Pertea G, Kim D, Kelley DR, et al. Differential gene and transcript expression analysis of RNA-seq experiments with TopHat and Cufflinks [published correction appears in Nat Protoc. 2014 Oct;9(10):2513. Nat Protoc. 2012;7:562–78. Published 2012 Mar 1
Scrucca L, Fop M, Murphy TB, Raftery AE. mclust 5: clustering, classification and density estimation using gaussian finite mixture models. R J. 2016;8:289–317.
Wang J, Vasaikar S, Shi Z, Greer M, Zhang B. WebGestalt 2017: a more comprehensive, powerful, flexible and interactive gene set enrichment analysis toolkit. Nucleic Acids Res. 2017;45:W130–W137.
Lub S, Maes K, Menu E, De Bruyne E, Vanderkerken K, Van Valckenborgh E. Novel strategies to target the ubiquitin proteasome system in multiple myeloma. Oncotarget. 2016;7:6521–37.
Szalat R, Avet-Loiseau H, Munshi NC. Gene expression profiles in myeloma: ready for the real world? Clin Cancer Res. 2016;22:5434–42.
Kuiper R, van Duin M, van Vliet MH, Broijl A, van der Holt B, El Jarari L, et al. Prediction of high- and low-risk multiple myeloma based on gene expression and the international staging system. Blood. 2015;126:1996–2004.
Hummel M, Hielscher T, Salwender HJ, Scheid C, Martin H, Bertsch U, et al. Quantitative integrative prediction of survival probability in multiple myeloma using molecular and clinical prognostic factors in 657 patients treated with bortezomib-based induction, high-dose therapy and autologous stem cell transplantation. Blood. 2018;132(Supplement 1):403.
Perrot A, Lauwers-Cances V, Tournay E, Hulin C, Chretien ML, Royer B, et al. Development and validation of a cytogenetic prognostic index predicting survival in multiple myeloma. J Clin Oncol. 2019;37:1657–65.
Terebelo HR, Abonour R, Gasparetto CJ, Toomey K, Durie BGM, Hardin JW, et al. Development of a prognostic model for overall survival in multiple myeloma using the Connect® MM Patient Registry. Br J Haematol. 2019;187:602–14.
Amin SB, Yip WK, Minvielle S, Broyl A, Li Y, Hanlon B, et al. Gene expression profile alone is inadequate in predicting complete response in multiple myeloma. Leukemia. 2014;28:2229–34.
Chapman MA, Sive J, Ambrose J, Roddie C, Counsell N, Lach A, et al. RNA-seq of newly diagnosed patients in the PADIMAC study leads to a bortezomib/lenalidomide decision signature. Blood. 2018;132:2154–65.
Hari P, Lentzsch S, DiCapua Siegel DS, Usmani SZ, Dhakal B, Rossi AC et al. Prospective study to measure the impact of MMprofiler on treatment intention in newly diagnosed multiple myeloma patients (PROMMIS). J Clin Oncol. 2019;37_suppl:8030–8030
Boccadoro M. Validation of a personalised medicine tool for multiple myeloma that predicts treatment effectiveness in patients (MMpredict). NCT03409692. Retrieved from https://clinicaltrials.gov/ct2/show/NCT03409692. 24 Jan 2008.
Vangsted AJ, Helm-Petersen S, Cowland JB, Jensen PB, Gimsing P, Barlogie B, et al. Drug response prediction in high-risk multiple myeloma. Gene. 2018;644:80–86.
Ubels J, Sonneveld P, van Beers EH, Broijl A, van Vliet MH, de Ridder J. Predicting treatment benefit in multiple myeloma through simulation of alternative treatment effects. Nat Commun. 2018;9:2943. Published 2018 Jul
Facon T, Kumar S, Plesner T, Orlowski RZ, Moreau P, Bahlis N, et al. Daratumumab plus lenalidomide and dexamethasone for untreated myeloma. N. Engl J Med. 2019;380:2104–15.
Moreau P, Attal M, Hulin C, Arnulf B, Belhadj K, Benboubker L, et al. Bortezomib, thalidomide, and dexamethasone with or without daratumumab before and after autologous stem-cell transplantation for newly diagnosed multiple myeloma (CASSIOPEIA): a randomised, open-label, phase 3 study [published correction appears in Lancet. 2019 Jun 14. Lancet 2019;394:29–38.
Attal M, Lauwers-Cances V, Hulin C, Leleu X, Caillot D, Escoffre M, et al. Lenalidomide, bortezomib, and dexamethasone with transplantation for myeloma. N Engl J Med. 2017;376:1311–20.
The authors wish to thank the Supercomputing Center of Galicia (CESGA) and the Multiple Myeloma Research Foundation (MMRF) for technical support and facilitating access to the data from the CoMMpass consortium, respectively.
Conflict of interest
M-VM has received honoraria for lectures and participation in advisory boards from Janssen, Celgene-BMS, Amgen, Takeda, Abbvie, GSK, Adaptive, Roche, Seatle Genetics, Pfizer, and Regeneron. AMO has received honoraria for lectures and participation in advisory boards from Janssen and AstraZeneca. AMO has received research grants from Roche and Celgene-BMS. MSGP has received honoraria for lectures and participation in advisory boards from Janssen, Amgen, Celgene-BMS, Takeda, Sanofi, and GSK.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Mosquera Orgueira, A., González Pérez, M.S., Díaz Arias, J.Á. et al. Survival prediction and treatment optimization of multiple myeloma patients using machine-learning models based on clinical and gene expression data. Leukemia (2021). https://doi.org/10.1038/s41375-021-01286-2