Aziz Nazha1,2, Rami Komrokji3, Manja Meggendorfer4, Xuefei Jia5, Nathan Radakovich6, Jacob Shreve1, C Beau Hilton6, Yasunubo Nagata7, Betty K Hamilton1, Sudipto Mukherjee1, Najla Al Ali3, Wencke Walter4, Stephan Hutter4, Eric Padron3, David Sallman3, Teodora Kuzmanovic7, Cassandra Kerr7, Vera Adema7, David P Steensma8, Amy Dezern9, Gail Roboz10, Guillermo Garcia-Manero11, Harry Erba12, Claudia Haferlach4, Jaroslaw P Maciejewski7, Torsten Haferlach4, Mikkael A Sekeres13. 1. Leukemia Program, Department of Hematology and Medical Oncology, Cleveland Clinic, Cleveland, OH. 2. Center for Clinical Artificial Intelligence, Cleveland Clinic, Cleveland, OH. 3. Department of Malignant Hematology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL. 4. MLL Munich Leukemia Laboratory, Munich, Germany. 5. Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH. 6. Lerner College of Medicine, Case Western Reserve University, Cleveland, OH. 7. Department of Translational Hematology and Oncology Research, Cleveland Clinic, Cleveland, OH. 8. Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA. 9. Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University, Baltimore, MD. 10. Division of Hematology and Oncology, New York Presbyterian Hospital-Weill Cornell Medical College, New York, NY. 11. Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX. 12. SWOG Cooperative Group, Houston, TX. 13. Sylvester Comprehensive Cancer Center, University of Miami, Miami, FL.
Abstract
PURPOSE: Patients with myelodysplastic syndromes (MDS) have a survival that can range from months to decades. Prognostic systems that incorporate advanced analytics of clinical, pathologic, and molecular data have the potential to more accurately and dynamically predict survival in patients receiving various therapies. METHODS: A total of 1,471 MDS patients with comprehensively annotated clinical and molecular data were included in a training cohort and analyzed using machine learning techniques. A random survival algorithm was used to build a prognostic model, which was then validated in external cohorts. The accuracy of the proposed model, compared with other established models, was assessed using a concordance (c)index. RESULTS: The median age for the training cohort was 71 years. Commonly mutated genes included SF3B1, TET2, and ASXL1. The algorithm identified chromosomal karyotype, platelet, hemoglobin levels, bone marrow blast percentage, age, other clinical variables, seven discrete gene mutations, and mutation number as having prognostic impact on overall and leukemia-free survivals. The model was validated in an independent external cohort of 465 patients, a cohort of patients with MDS treated in a prospective clinical trial, a cohort of patients with paired samples at different time points during the disease course, and a cohort of patients who underwent hematopoietic stem-cell transplantation. CONCLUSION: A personalized prediction model on the basis of clinical and genomic data outperformed established prognostic models in MDS. The new model was dynamic, predicting survival and leukemia transformation probabilities at different time points that are unique for a given patient, and can upstage and downstage patients into more appropriate risk categories.
PURPOSE: Patients with myelodysplastic syndromes (MDS) have a survival that can range from months to decades. Prognostic systems that incorporate advanced analytics of clinical, pathologic, and molecular data have the potential to more accurately and dynamically predict survival in patients receiving various therapies. METHODS: A total of 1,471 MDS patients with comprehensively annotated clinical and molecular data were included in a training cohort and analyzed using machine learning techniques. A random survival algorithm was used to build a prognostic model, which was then validated in external cohorts. The accuracy of the proposed model, compared with other established models, was assessed using a concordance (c)index. RESULTS: The median age for the training cohort was 71 years. Commonly mutated genes included SF3B1, TET2, and ASXL1. The algorithm identified chromosomal karyotype, platelet, hemoglobin levels, bone marrow blast percentage, age, other clinical variables, seven discrete gene mutations, and mutation number as having prognostic impact on overall and leukemia-free survivals. The model was validated in an independent external cohort of 465 patients, a cohort of patients with MDS treated in a prospective clinical trial, a cohort of patients with paired samples at different time points during the disease course, and a cohort of patients who underwent hematopoietic stem-cell transplantation. CONCLUSION: A personalized prediction model on the basis of clinical and genomic data outperformed established prognostic models in MDS. The new model was dynamic, predicting survival and leukemia transformation probabilities at different time points that are unique for a given patient, and can upstage and downstage patients into more appropriate risk categories.
Authors: Peter L Greenberg; Richard M Stone; Aref Al-Kali; Stefan K Barta; Rafael Bejar; John M Bennett; Hetty Carraway; Carlos M De Castro; H Joachim Deeg; Amy E DeZern; Amir T Fathi; Olga Frankfurt; Karin Gaensler; Guillermo Garcia-Manero; Elizabeth A Griffiths; David Head; Ruth Horsfall; Robert A Johnson; Mark Juckett; Virginia M Klimek; Rami Komrokji; Lisa A Kujawski; Lori J Maness; Margaret R O'Donnell; Daniel A Pollyea; Paul J Shami; Brady L Stein; Alison R Walker; Peter Westervelt; Amer Zeidan; Dorothy A Shead; Courtney Smith Journal: J Natl Compr Canc Netw Date: 2017-01 Impact factor: 11.908
Authors: A Nazha; K Al-Issa; B K Hamilton; T Radivoyevitch; A T Gerds; S Mukherjee; V Adema; A Zarzour; N Abuhadra; B J Patel; C M Hirsch; A Advani; B Przychodzen; H E Carraway; J P Maciejewski; M A Sekeres Journal: Leukemia Date: 2017-08-18 Impact factor: 11.528
Authors: Rafael Bejar; Kristen Stevenson; Omar Abdel-Wahab; Naomi Galili; Björn Nilsson; Guillermo Garcia-Manero; Hagop Kantarjian; Azra Raza; Ross L Levine; Donna Neuberg; Benjamin L Ebert Journal: N Engl J Med Date: 2011-06-30 Impact factor: 91.245
Authors: Daniel A Arber; Attilio Orazi; Robert Hasserjian; Jürgen Thiele; Michael J Borowitz; Michelle M Le Beau; Clara D Bloomfield; Mario Cazzola; James W Vardiman Journal: Blood Date: 2016-04-11 Impact factor: 22.113
Authors: Michael Pfeilstöcker; Heinz Tuechler; Guillermo Sanz; Julie Schanz; Guillermo Garcia-Manero; Francesc Solé; John M Bennett; David Bowen; Pierre Fenaux; Francois Dreyfus; Hagop Kantarjian; Andrea Kuendgen; Luca Malcovati; Mario Cazzola; Jaroslav Cermak; Christa Fonatsch; Michelle M Le Beau; Marilyn L Slovak; Alessandro Levis; Michael Luebbert; Jaroslaw Maciejewski; Sigrid Machherndl-Spandl; Silvia M M Magalhaes; Yasushi Miyazaki; Mikkael A Sekeres; Wolfgang R Sperr; Reinhard Stauder; Sudhir Tauro; Peter Valent; Teresa Vallespi; Arjan A van de Loosdrecht; Ulrich Germing; Detlef Haase; Peter L Greenberg Journal: Blood Date: 2016-06-22 Impact factor: 22.113
Authors: A Nazha; M Narkhede; T Radivoyevitch; D J Seastone; B J Patel; A T Gerds; S Mukherjee; M Kalaycio; A Advani; B Przychodzen; H E Carraway; J P Maciejewski; M A Sekeres Journal: Leukemia Date: 2016-05-20 Impact factor: 11.528
Authors: Elli Papaemmanuil; Moritz Gerstung; Luca Malcovati; Sudhir Tauro; Gunes Gundem; Peter Van Loo; Chris J Yoon; Peter Ellis; David C Wedge; Andrea Pellagatti; Adam Shlien; Michael John Groves; Simon A Forbes; Keiran Raine; Jon Hinton; Laura J Mudie; Stuart McLaren; Claire Hardy; Calli Latimer; Matteo G Della Porta; Sarah O'Meara; Ilaria Ambaglio; Anna Galli; Adam P Butler; Gunilla Walldin; Jon W Teague; Lynn Quek; Alex Sternberg; Carlo Gambacorti-Passerini; Nicholas C P Cross; Anthony R Green; Jacqueline Boultwood; Paresh Vyas; Eva Hellstrom-Lindberg; David Bowen; Mario Cazzola; Michael R Stratton; Peter J Campbell Journal: Blood Date: 2013-09-12 Impact factor: 22.113
Authors: T Haferlach; Y Nagata; V Grossmann; Y Okuno; U Bacher; G Nagae; S Schnittger; M Sanada; A Kon; T Alpermann; K Yoshida; A Roller; N Nadarajah; Y Shiraishi; Y Shiozawa; K Chiba; H Tanaka; H P Koeffler; H-U Klein; M Dugas; H Aburatani; A Kohlmann; S Miyano; C Haferlach; W Kern; S Ogawa Journal: Leukemia Date: 2013-11-13 Impact factor: 11.528
Authors: Amer M Zeidan; Jan Philipp Bewersdorf; Rena Buckstein; Mikkael A Sekeres; David P Steensma; Uwe Platzbecker; Sanam Loghavi; Jacqueline Boultwood; Rafael Bejar; John M Bennett; Uma Borate; Andrew M Brunner; Hetty Carraway; Jane E Churpek; Naval G Daver; Matteo Della Porta; Amy E DeZern; Fabio Efficace; Pierre Fenaux; Maria E Figueroa; Peter Greenberg; Elizabeth A Griffiths; Stephanie Halene; Robert P Hasserjian; Christopher S Hourigan; Nina Kim; Tae Kon Kim; Rami S Komrokji; Vijay Kutchroo; Alan F List; Richard F Little; Ravi Majeti; Aziz Nazha; Stephen D Nimer; Olatoyosi Odenike; Eric Padron; Mrinal M Patnaik; Gail J Roboz; David A Sallman; Guillermo Sanz; Maximilian Stahl; Daniel T Starczynowski; Justin Taylor; Zhuoer Xie; Mina Xu; Michael R Savona; Andrew H Wei; Omar Abdel-Wahab; Valeria Santini Journal: Leukemia Date: 2022-10-20 Impact factor: 12.883
Authors: Bruno Fattizzo; Giorgia Virginia Levati; Juri Alessandro Giannotta; Giulio Cassanello; Lilla Marcella Cro; Anna Zaninoni; Marzia Barbieri; Giorgio Alberto Croci; Nicoletta Revelli; Wilma Barcellini Journal: Front Oncol Date: 2022-03-22 Impact factor: 6.244
Authors: Yao Qin; Hang Zhang; Lin Feng; Haichen Wei; Yuling Wu; Chaoran Jiang; Zhihong Xu; Huanling Zhu; Ting Liu Journal: Ann Med Date: 2022-12 Impact factor: 5.348