Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

ACUTE MYELOID LEUKEMIA

Machine learning identifies the independent role of dysplasia in the prediction of response to chemotherapy in AML

Leukemia volume 36, pages 656–663 (2022)Cite this article

Subjects

Abstract

The independent prognostic impact of specific dysplastic features in acute myeloid leukemia (AML) remains controversial and may vary between genomic subtypes. We apply a machine learning framework to dissect the relative contribution of centrally reviewed dysplastic features and oncogenetics in 190 patients with de novo AML treated in ALFA clinical trials. One hundred and thirty-five (71%) patients achieved complete response after the first induction course (CR). Dysgranulopoiesis, dyserythropoiesis and dysmegakaryopoiesis were assessable in 84%, 83% and 63% patients, respectively. Multi-lineage dysplasia was present in 27% of assessable patients. Micromegakaryocytes (q = 0.01), hypolobulated megakaryocytes (q = 0.08) and hyposegmented granulocytes (q = 0.08) were associated with higher ELN-2017 risk. Using a supervised learning algorithm, the relative importance of morphological variables (34%) for the prediction of CR was higher than demographic (5%), clinical (2%), cytogenetic (25%), molecular (29%), and treatment (5%) variables. Though dysplasias had limited predictive impact on survival, a multivariate logistic regression identified the presence of hypolobulated megakaryocytes (p = 0.014) and micromegakaryocytes (p = 0.035) as predicting lower CR rates, independently of monosomy 7 (p = 0.013), TP53 (p = 0.004), and NPM1 mutations (p = 0.025). Assessment of these specific dysmegakarypoiesis traits, for which we identify a transcriptomic signature, may thus guide treatment allocation in AML.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Distribution of dysplasia and association with genomic covariates.
Fig. 2: Association between frequent dysplastic features in the 111 patients with tri-lineage assessability.
Fig. 3: Contribution of morphology to outcome.

Similar content being viewed by others

References

  1. Gerstung M, Papaemmanuil E, Martincorena I, Bullinger L, Gaidzik VI, Paschka P, et al. Precision oncology for acute myeloid leukemia using a knowledge bank approach. Nat Genet. 2017;49:332–40.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Nagy M, Radakovich N, Nazha A. Machine learning in oncology: What should clinicians know? JCO Clin Cancer Inf. 2020;4:799–810.

    Google Scholar 

  3. Nagata Y, Zhao R, Awada H, Kerr CM, Mirzaev I, Kongkiatkamon S, et al. Machine learning demonstrates that somatic mutations imprint invariant morphologic features in myelodysplastic syndromes. Blood. 2020;136:2249–62.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Vardiman JW, Harris NL, Brunning RD. The World Health Organization (WHO) classification of the myeloid neoplasms. Blood. 2002;100:2292–302.

    Article  CAS  PubMed  Google Scholar 

  5. Vardiman JW, Thiele J, Arber DA, Brunning RD, Borowitz MJ, Porwit A, et al. The 2008 revision of the World Health Organization (WHO) classification of myeloid neoplasms and acute leukemia: rationale and important changes. Blood. 2009;114:937–51.

    Article  CAS  PubMed  Google Scholar 

  6. Arber DA, Orazi A, Hasserjian R, Thiele J, Borowitz MJ, Le Beau MM, et al. The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia. Blood. 2016;127:2391–405.

    Article  CAS  PubMed  Google Scholar 

  7. Haferlach T, Schoch C, Loffler H, Gassmann W, Kern W, Schnittger S, et al. Morphologic dysplasia in de novo acute myeloid leukemia (AML) is related to unfavorable cytogenetics but has no independent prognostic relevance under the conditions of intensive induction therapy: results of a multiparameter analysis from the German AML Cooperative Group studies. J Clin Oncol. 2003;21:256–65.

    Article  PubMed  Google Scholar 

  8. Wandt H, Schakel U, Kroschinsky F, Prange-Krex G, Mohr B, Thiede C, et al. MLD according to the WHO classification in AML has no correlation with age and no independent prognostic relevance as analyzed in 1766 patients. Blood. 2008;111:1855–61.

    Article  CAS  PubMed  Google Scholar 

  9. Miesner M, Haferlach C, Bacher U, Weiss T, Macijewski K, Kohlmann A, et al. Multilineage dysplasia (MLD) in acute myeloid leukemia (AML) correlates with MDS-related cytogenetic abnormalities and a prior history of MDS or MDS/MPN but has no independent prognostic relevance: a comparison of 408 cases classified as “AML not otherwise specified” (AML-NOS) or “AML with myelodysplasia-related changes” (AML-MRC). Blood. 2010;116:2742–51.

    Article  CAS  PubMed  Google Scholar 

  10. Rozman M, Navarro JT, Arenillas L, Aventin A, Gimenez T, Alonso E, et al. Multilineage dysplasia is associated with a poorer prognosis in patients with de novo acute myeloid leukemia with intermediate-risk cytogenetics and wild-type NPM1. Ann Hematol. 2014;93:1695–703.

    Article  PubMed  Google Scholar 

  11. Haferlach T, Stengel A, Eckstein S, Perglerova K, Alpermann T, Kern W, et al. The new provisional WHO entity ‘RUNX1 mutated AML’ shows specific genetics but no prognostic influence of dysplasia. Leukemia. 2016;30:2109–12.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Bacher U, Schnittger S, Macijewski K, Grossmann V, Kohlmann A, Alpermann T, et al. Multilineage dysplasia does not influence prognosis in CEBPA-mutated AML, supporting the WHO proposal to classify these patients as a unique entity. Blood. 2012;119:4719–22.

    Article  CAS  PubMed  Google Scholar 

  13. Devillier R, Mansat-De Mas V, Gelsi-Boyer V, Demur C, Murati A, Corre J, et al. Role of ASXL1 and TP53 mutations in the molecular classification and prognosis of acute myeloid leukemias with myelodysplasia-related changes. Oncotarget. 2015;6:8388–96.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Falini B, Macijewski K, Weiss T, Bacher U, Schnittger S, Kern W, et al. Multilineage dysplasia has no impact on biologic, clinicopathologic, and prognostic features of AML with mutated nucleophosmin (NPM1). Blood. 2010;115:3776–86.

    Article  CAS  PubMed  Google Scholar 

  15. Diaz-Beya M, Rozman M, Pratcorona M, Torrebadell M, Camos M, Aguilar JL, et al. The prognostic value of multilineage dysplasia in de novo acute myeloid leukemia patients with intermediate-risk cytogenetics is dependent on NPM1 mutational status. Blood. 2010;116:6147–8.

    Article  CAS  PubMed  Google Scholar 

  16. Goasguen JE, Matsuo T, Cox C, Bennett JM. Evaluation of the dysmyelopoiesis in 336 patients with de novo acute myeloid leukemia: major importance of dysgranulopoiesis for remission and survival. Leukemia. 1992;6:520–5.

    CAS  PubMed  Google Scholar 

  17. Gahn B, Haase D, Unterhalt M, Drescher M, Schoch C, Fonatsch C, et al. De novo AML with dysplastic hematopoiesis: cytogenetic and prognostic significance. Leukemia. 1996;10:946–51.

    CAS  PubMed  Google Scholar 

  18. Weinberg OK, Pozdnyakova O, Campigotto F, DeAngelo DJ, Stone RM, Neuberg D, et al. Reproducibility and prognostic significance of morphologic dysplasia in de novo acute myeloid leukemia. Mod Pathol. 2015;28:965–76.

    Article  CAS  PubMed  Google Scholar 

  19. Weinberg OK, Gibson CJ, Blonquist TM, Neuberg D, Pozdnyakova O, Kuo F, et al. Association of mutations with morphological dysplasia in de novo acute myeloid leukemia without 2016 WHO Classification-defined cytogenetic abnormalities. Haematologica. 2018;103:626–33.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Castaigne S, Pautas C, Terre C, Raffoux E, Bordessoule D, Bastie JN, et al. Effect of gemtuzumab ozogamicin on survival of adult patients with de-novo acute myeloid leukaemia (ALFA-0701): a randomised, open-label, phase 3 study. Lancet. 2012;379:1508–16.

    Article  CAS  PubMed  Google Scholar 

  21. Thomas X, de Botton S, Chevret S, Caillot D, Raffoux E, Lemasle E, et al. Randomized phase II study of clofarabine-based consolidation for younger adults with acute myeloid leukemia in first remission. J Clin Oncol. 2017;35:1223–30.

    Article  CAS  PubMed  Google Scholar 

  22. Mufti GJ, Bennett JM, Goasguen J, Bain BJ, Baumann I, Brunning R, et al. Diagnosis and classification of myelodysplastic syndrome: International Working Group on Morphology of myelodysplastic syndrome (IWGM-MDS) consensus proposals for the definition and enumeration of myeloblasts and ring sideroblasts. Haematologica. 2008;93:1712–7.

    Article  PubMed  Google Scholar 

  23. Goasguen JE, Bennett JM, Bain BJ, Brunning R, Vallespi MT, Tomonaga M, et al. Proposal for refining the definition of dysgranulopoiesis in acute myeloid leukemia and myelodysplastic syndromes. Leuk Res. 2014;38:447–53.

    Article  PubMed  Google Scholar 

  24. Goasguen JE, Bennett JM, Bain BJ, Brunning RD, Vallespi MT, Tomonaga M, et al. Quality control initiative on the evaluation of the dysmegakaryopoiesis in myeloid neoplasms: difficulties in the assessment of dysplasia. Leuk Res. 2016;45:75–81.

    Article  PubMed  Google Scholar 

  25. Goasguen JE, Bennett JM, Bain BJ, Brunning R, Vallespi MT, Tomonaga M, et al. Dyserythropoiesis in the diagnosis of the myelodysplastic syndromes and other myeloid neoplasms: problem areas. Br J Haematol. 2018;182:526–33.

    Article  PubMed  Google Scholar 

  26. Fournier E, Duployez N, Ducourneau B, Raffoux E, Turlure P, Caillot D, et al. Mutational profile and benefit of gemtuzumab ozogamicin in acute myeloid leukemia patients treated in the ALFA0701 trial. Blood. 2019;135:542–6.

  27. Ruminy P, Marchand V, Buchbinder N, Larson T, Joly B, Penther D, et al. Multiplexed targeted sequencing of recurrent fusion genes in acute leukaemia. Leukemia. 2016;30:757–60.

    Article  CAS  PubMed  Google Scholar 

  28. Dohner H, Estey E, Grimwade D, Amadori S, Appelbaum FR, Buchner T, et al. Diagnosis and management of AML in adults: 2017 ELN recommendations from an international expert panel. Blood. 2017;129:424–47.

    Article  PubMed  PubMed Central  Google Scholar 

  29. McGraw KO, Wong SP. Forming inferences about some intraclass correlation coefficients. Psychol Methods. 1996;1:30–46.

    Article  Google Scholar 

  30. Conger AJ. Integration and generalization of kappas for multiple raters. Psychol Bull. 1980;88:322–8.

    Article  Google Scholar 

  31. Cicchetti DV. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychol Assess. 1994;6:284–90.

    Article  Google Scholar 

  32. Cheson BD, Bennett JM, Kopecky KJ, Buchner T, Willman CL, Estey EH, et al. Revised recommendations of the International Working Group for diagnosis, standardization of response criteria, treatment outcomes, and reporting standards for therapeutic trials in acute myeloid leukemia. J Clin Oncol. 2003;21:4642–9.

    Article  PubMed  Google Scholar 

  33. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. Ann Appl Stat. 2008;2:841–60.

    Article  Google Scholar 

  34. O’brien RM. A caution regarding rules of thumb for variance inflation factors. Qual Quant. 2007;41:673–90.

    Article  Google Scholar 

  35. Ng SW, Mitchell A, Kennedy JA, Chen WC, McLeod J, Ibrahimova N, et al. A 17-gene stemness score for rapid determination of risk in acute leukaemia. Nature. 2016;540:433–7.

    Article  CAS  PubMed  Google Scholar 

  36. Subramanian A, Tamayo P, Mootha VK, Mukherjee S, Ebert BL, Gillette MA, et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci USA. 2005;102:15545–50.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Papaemmanuil E, Gerstung M, Bullinger L, Gaidzik VI, Paschka P, Roberts ND, et al. Genomic classification and prognosis in acute myeloid leukemia. N Engl J Med. 2016;374:2209–21.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Lindsley RC, Mar BG, Mazzola E, Grauman PV, Shareef S, Allen SL, et al. Acute myeloid leukemia ontogeny is defined by distinct somatic mutations. Blood. 2015;125:1367–76.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Bennett JM, Catovsky D, Daniel MT, Flandrin G, Galton DA, Gralnick HR, et al. Proposals for the classification of the acute leukaemias. French-American-British (FAB) co-operative group. Br J Haematol. 1976;33:451–8.

    Article  CAS  PubMed  Google Scholar 

  40. Hock H, Shimamura A. ETV6 in hematopoiesis and leukemia predisposition. Semin Hematol. 2017;54:98–104.

    Article  PubMed  PubMed Central  Google Scholar 

  41. Matsuda A, Germing U, Jinnai I, Iwanaga M, Misumi M, Kuendgen A, et al. Improvement of criteria for refractory cytopenia with multilineage dysplasia according to the WHO classification based on prognostic significance of morphological features in patients with refractory anemia according to the FAB classification. Leukemia. 2007;21:678–86.

    Article  CAS  PubMed  Google Scholar 

  42. Feng G, Gale RP, Cui W, Cai W, Huang G, Xu Z, et al. A systematic classification of megakaryocytic dysplasia and its impact on prognosis for patients with myelodysplastic syndromes. Exp Hematol Oncol. 2015;5:12.

    Article  PubMed  Google Scholar 

  43. Mazzi S, Lordier L, Debili N, Raslova H, Vainchenker W. Megakaryocyte and polyploidization. Exp Hematol. 2018;57:1–13.

    Article  CAS  PubMed  Google Scholar 

  44. Rauch PJ, Ellegast JM, Widmer CC, Fritsch K, Goede JS, Valk PJ, et al. MPL expression on AML blasts predicts peripheral blood neutropenia and thrombocytopenia. Blood. 2016;128:2253–7.

    Article  CAS  PubMed  Google Scholar 

  45. Miraki-Moud F, Anjos-Afonso F, Hodby KA, Griessinger E, Rosignoli G, Lillington D, et al. Acute myeloid leukemia does not deplete normal hematopoietic stem cells but induces cytopenias by impeding their differentiation. Proc Natl Acad Sci USA. 2013;110:13576–81.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Pei S, Pollyea DA, Gustafson A, Stevens BM, Minhajuddin M, Fu R, et al. Monocytic subclones confer resistance to venetoclax-based therapy in acute myeloid leukemia patients. Cancer Discov 2020;10:536–51.

  47. Chandradevan R, Aljudi AA, Drumheller BR, Kunananthaseelan N, Amgad M, Gutman DA, et al. Machine-based detection and classification for bone marrow aspirate differential counts: initial development focusing on nonneoplastic cells. Lab Invest. 2020;100:98–109.

    Article  PubMed  Google Scholar 

  48. Mobadersany P, Yousefi S, Amgad M, Gutman DA, Barnholtz-Sloan JS, Velazquez Vega JE, et al. Predicting cancer outcomes from histology and genomics using convolutional networks. Proc Natl Acad Sci USA. 2018;115:E2970–E2979.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  49. Brück OE, Lallukka-Brück SE, Hohtari HR, Ianevski A, Ebeling FT, Kovanen PE, et al. Machine learning of bone marrow histopathology identifies genetic and clinical determinants in patients with MDS. Blood Cancer Discov. 2021;2:238–49.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

RI is supported by grants from Association Laurette Fugain, Association Princesse Margot, Association pour la Recherche contre le Cancer, Fondation Leucémie Espoir, and Ligue Contre le Cancer.

Author information

Author notes

  1. These authors contributed equally: Raphael Itzykson, Thomas Cluzeau.

Authors and Affiliations

  1. Laboratoire d’Hématologie, Hôpital Saint-Louis, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France

    Matthieu Duchmann

  2. Université de Paris, Génomes, biologie cellulaire et thérapeutique U944, INSERM, CNRS, 75010, Paris, France

    Matthieu Duchmann & Raphael Itzykson

  3. Département d’Hématologie et Immunologie biologiques, Hôpital Henri-Mondor, Assistance Publique-Hôpitaux de Paris, Créteil, France

    Orianne Wagner-Ballon, Bouchra Badaoui, Nicolas Freynet & Emmanuel Benayoun

  4. INSERM U955 IMRB, UPEC, Créteil, France

    Orianne Wagner-Ballon

  5. Service d’Hématologie Biologique, CHU Lille, Lille, France

    Thomas Boyer, Elise Fournier & Aline Renneville

  6. Service d’Hématologie Biologique, CHU Amiens-Picardie, Amiens, France

    Thomas Boyer

  7. UMR9020 CNRS - UMR-S1277 INSERM, Lille, France

    Meyling Cheok

  8. Service d’Hématologie biologique, Hôpital Dupuytren, Limoges, France

    Estelle Guerin

  9. UMR CNRS 7276/INSERM 1262, CHU Limoges, Limoges, France

    Estelle Guerin

  10. Université Lille, CNRS, INSERM, CHU Lille, IRCL, UMR9020 - UMR1277 - Canther - Cancer Heterogeneity, Plasticity and Resistance to Therapies, 59000, Lille, France

    Laurène Fenwarth & Claude Preudhomme

  11. Laboratoire d’Hématologie, Hôpital Avicenne, Assistance Publique-Hôpitaux de Paris, Université Sorbonne Paris Cité, Bobigny, France

    Daniel Lusina

  12. Laboratoire d’Hématologie, Hôpital André Mignot, Centre Hospitalier de Versailles, Le Chesnay, France

    Isabel Garcia

  13. Département d’Hématologie Clinique, Hôpital Avicenne, Assistance Publique-Hôpitaux de Paris, Bobigny, France

    Claude Gardin

  14. Département d’Hématologie Clinique, Hôpital Saint-Louis, Assistance Publique-Hôpitaux de Paris, Université de Paris, Paris, France

    Pierre Fenaux & Raphael Itzykson

  15. Département d’Hématologie clinique, Hôpital Henri-Mondor, Assistance Publique-Hôpitaux de Paris, Créteil, France

    Cécile Pautas

  16. CHU Lille, Service des Maladies du Sang, 59000, Lille, France

    Bruno Quesnel

  17. Département d’Hématologie Clinique, CHU Limoges, Limoges, France

    Pascal Turlure

  18. Laboratoire de Cytogénétique, Hôpital André Mignot, Centre Hospitalier de Versailles, Le Chesnay, France

    Christine Terré

  19. Département d’Hématologie Clinique, Hospices Civils de Lyon, Hôpital Lyon-Sud, Pierre Bénite, France

    Xavier Thomas

  20. Département d’Hématologie Clinique, Hôpital André Mignot, Centre Hospitalier de Versailles, Le Chesnay, France

    Juliette Lambert

  21. Département d’Hématologie Clinique, Hôpital Saint-Louis, Assistance Publique-Hôpitaux de Paris, EA-3518, Institut de Recherche Saint-Louis, Université de Paris, Paris, France

    Hervé Dombret

  22. Département d’Hématologie, Université Côte d’Azur, CHU de Nice, Nice, France

    Thomas Cluzeau

Authors
  1. Matthieu Duchmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Orianne Wagner-Ballon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Boyer
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Meyling Cheok
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Elise Fournier
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Estelle Guerin
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Laurène Fenwarth
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Bouchra Badaoui
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Nicolas Freynet
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Emmanuel Benayoun
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Daniel Lusina
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Isabel Garcia
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Claude Gardin
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Pierre Fenaux
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Cécile Pautas
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Bruno Quesnel
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Pascal Turlure
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Christine Terré
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Xavier Thomas
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Juliette Lambert
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Aline Renneville
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Claude Preudhomme
    View author publications

    You can also search for this author in PubMed Google Scholar

  23. Hervé Dombret
    View author publications

    You can also search for this author in PubMed Google Scholar

  24. Raphael Itzykson
    View author publications

    You can also search for this author in PubMed Google Scholar

  25. Thomas Cluzeau
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

MD, RI, and TC conceived, the study and drafted the manuscript. MD and RI performed the analyses. OWB supervised the morphology review. TB, EG, EB, DL, BB, NF, and IG performed morphology assessments. EF, LF, AR, and CP performed molecular genetics. MC performed microarray analyses. CG, PF, CP, BQ, PT, XT, and JL accrued patients. CT performed central cytogenetics review. HD supervised ALFA studies. All authors revised the manuscript and approved its final version.

Corresponding authors

Correspondence to Raphael Itzykson or Thomas Cluzeau.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duchmann, M., Wagner-Ballon, O., Boyer, T. et al. Machine learning identifies the independent role of dysplasia in the prediction of response to chemotherapy in AML. Leukemia 36, 656–663 (2022). https://doi.org/10.1038/s41375-021-01435-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41375-021-01435-7

This article is cited by

Search

Advanced search

Quick links