Use of machine learning techniques to predict poor survival after hematopoietic cell transplantation for myelofibrosis
Abstract
Abstract With the incorporation of effective therapies for myelofibrosis (MF), accurately predicting outcomes after allogeneic hematopoietic cell transplantation (allo-HCT) is crucial for determining the optimal timing for this procedure. Using data from 5183 patients with MF who underwent first allo-HCT between 2005 and 2020 at European Society for Blood and Marrow Transplantation centers, we examined different machine learning (ML) models to predict overall survival after transplant. The cohort was divided into a training set (75%) and a test set (25%) for model validation. A random survival forests (RSF) model was developed based on 10 variables: patient age, comorbidity index, performance status, blood blasts, hemoglobin, leukocytes, platelets, donor type, conditioning intensity, and graft-versus-host disease prophylaxis. Its performance was compared with a 4-level Cox regression–based score and other ML-based models derived from the same data set, and with the Center for International Blood and Marrow Transplant Research score. The RSF outperformed all comparators, achieving better concordance indices across both primary and postessential thrombocythemia/polycythemia vera MF subgroups. The robustness and generalizability of the RSF model was confirmed by Akaike information criterion and time-dependent receiver operating characteristic area under the curve metrics in both sets. Although all models were prognostic for nonrelapse mortality, the RSF provided better curve separation, effectively identifying a high-risk group comprising 25% of patients. In conclusion, ML enhances risk stratification in patients with MF undergoing allo-HCT, paving the way for personalized medicine. A web application (https://gemfin.click/ebmt) based on the RSF model offers a practical tool to identify patients at high risk for poor transplantation outcomes, supporting informed treatment decisions and advancing individualized care.
Article Details
Authors (30)
Juan Carlos Hernández-Boluda
8Hospital Clínico Universitario, Instituto de Investigación Sanitaria, University of Valencia, Valencia, Spain
Adrián Mosquera-Orgueira
2Hematology Department. University Hospital of Santiago de Compostela, Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
Luuk Gras
2EBMT Leiden Study Unit, Leiden, Netherlands
Linda Koster
2EBMT Leiden Study Unit, Leiden, Netherlands
Joe Tuffnell
3EBMT Leiden Study Unit, Leiden, Netherlands
Nicolaus Kröger
From the Department of Stem Cell Transplantation, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
Massimiliano Gambella
11Department of Hematology and Cellular Therapy, IRCCS Ospedale Policlinico San Martino, Genova, Italy
Thomas Schroeder
21University Medical Center Essen/Germany, Essen, Germany
Marie Robin
9Hôpital Saint Louis (APHP), Service d'hématologie, Paris, France
Katja Sockel
4Department of Internal Medicine I, University Hospital Dresden, Dresden University of Technology, Dresden, Germany
Jakob Passweg
8University Hospital Basel, Basel, Switzerland
Igor Wolfgang Blau
14Charité University Medicine Berlin, Medical Clinic, Berlin, Germany
Ibrahim Yakoub-Agha
9CHU de Lille, Univ Lille, INSERM U1286, Infinite, 59000 Lille, Lille, France
Ruben Van Dijck
1Erasmus University Medical Center, Hematology, Rotterdam, Netherlands
Mattias Stelljes
13Hematology Department, University of Muenster, Muenster, Germany
Henrik Sengeloev
11Department of Hematology, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
Jan Vydra
6Institute of Hematology and Blood Transfusion, Prague, Czech Republic
Uwe Platzbecker
Moniek de Witte
17Hematology Department, University Medical Centre, Utrecht, The Netherlands
Frédéric Baron
Kristina Carlson
10University Hospital Uppsala, Uppsala, Sweden
Javier Rojas
10Hospital Regional de Talca, Talca, Chile
Carlos Pérez Míguez
1Health Research Institute of Santiago de Compostela, Computational and Genomic Hematology (GrHeCo-Xen), Santiago de Compostela, Spain
Davide Crucitti
1Health Research Institute of Santiago de Compostela, Computational and Genomic Hematology (GrHeCo-Xen), Santiago de Compostela, Spain
Kavita Raj
20University College London Hospitals NHS Trust, London, United Kingdom
Joanna Drozd-Sokolowska
1Medical University of Warsaw, Department of Hematology, Transplantation and Internal Medicine, Warsaw, Poland
Giorgia Battipaglia
5Department of Clinical Medicine and Surgery, University Federico II, Hematology, Naples, Italy
Nicola Polverelli
1Unit of Bone Marrow Transplantation and Cellular Therapies - Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
Tomasz Czerw
24Hematology Department, Maria Skłodowska-Curie National Research Institute of Oncology, Gliwice, Poland
Donal P. McLornan
14Department of Haematology and Stem Cell Transplantation, University College London Hospitals NHS Foundation Trust, London, United Kingdom