Personalized Prediction Model to Risk Stratify Patients With Myelodysplastic Syndromes

• DOI: 10.1200/jco.20.02810
• Publication Date: 2021-08-18T19:59:27Z
• Authors: Aziz Nazha; Rami Komrokji; Manja Meggendorfer; Xuefei Jia; Nathan Radakovich; Jacob Shreve; C. Beau Hilton; Yasunubo Nagata; Betty K. Hamilton; Sudipto Mukherjee; Najla Al Ali; Wencke Walter; Stephan Hutter; Eric Padron; David Sallman; Teodora Kuzmanovic; Cassandra Kerr; Vera Adema; David P. Steensma; Amy Dezern; Gail Roboz; Guillermo Garcia-...; Harry Erba; Claudia Haferlach; Jaroslaw P. Macie...; Torsten Haferlach; Mikkael A. Sekeres
• Keywords: Adult; Aged, 80 and over; Male; Models, Statistical; Hematopoietic Stem Cell Transplantation; Genomics; Middle Aged; Prognosis; 3. Good health; 03 medical and health sciences; Cell Transformation, Neoplastic; Clinical Trials, Phase II as Topic; 0302 clinical medicine; Myelodysplastic Syndromes; Mutation; Biomarkers, Tumor; Disease Progression; Humans; Female; Prospective Studies; Algorithms; Aged; Follow-Up Studies

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.