Use of machine learning techniques to predict poor survival after hematopoietic cell transplantation for myelofibrosis

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.

Authors

Institutions

Publication Details

Journal
Blood
Published
2025-03-27
DOI
https://doi.org/10.1182/blood.2024027287
Citations
9
Primary Topic
Myeloproliferative Neoplasms: Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
14.63
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Use of machine learning techniques to predict poor survival after hematopoietic cell transplantation for myelofibrosis

Kavita K Raj, Nicolaus Martin Kröger, Jakob Robert Passweg, Davide Crucitti et al.
9 citations
Blood
Myeloproliferative Neoplasms: Diagnosis and Treatment
14.63
article

Use of machine learning techniques to predict poor survival after hematopoietic cell transplantation for myelofibrosis

Kavita K Raj, Nicolaus Martin Kröger, Jakob Robert Passweg, Davide Crucitti, Carlos Pérez Míguez, Matthias Stelljes, Tomasz Czerw, Nicola Polverelli, Marie Robin, Frédéric Baron, Donal P. McLornan, Jan Vydra, Moniek A DeWitte, Luuk Gras, Ibrahim Yakoub‐Agha, Massimiliano Gambella, Igor Wolfgang Blau, Kristina Carlson, Joanna Ewa Drozd-Sokolowska, Thomas A. Schroeder, Juan Carlos Hernández‐Boluda, Katja Sockel, Uwe Platzbecker, Adrián Mosquera Orgueira, Javier Alberto Rojas Martínez, Ruben Van Dijck, Joe Tuffnell, Giorgia Battipaglia, Linda Köster, Henrik Sengeloev
article en
9 citations

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.

BloodVol. 145(26)
University College Hospital (GB), University College London Hospitals NHS Foundation Trust (GB), Uppsala University Hospital (SE), Inserm (FR), University of Liège (BE), Universität Hamburg (DE), Universidade de Santiago de Compostela (ES), University of Münster (DE), Medical University of Warsaw (PL), University Hospital of Basel (CH), Rigshospitalet (DK), University Medical Center Utrecht (NL), Centre Hospitalier Universitaire de Lille (FR), Düsseldorf University Hospital (DE), Hospital Clínico Universitario de Valencia (ES), Institute of Haematology and Blood Transfusion (CZ), European Society for Blood and Marrow Transplantation (NL), Augenstern (DE), University Medical Center Hamburg-Eppendorf (DE), Deutsche Gesellschaft für Hämatologie und Medizinische Onkologie (DE), Federico II University Hospital (IT), Essen University Hospital (DE), National Institute of Oncology (HU), University Hospital Leipzig (DE), Central Clinical Hospital (PL), Hôpital Saint-Louis (FR), Ospedale Policlinico San Martino (IT), Instituto de Investigación Sanitaria de Santiago (ES), Erasmus MC Cancer Institute (NL), The Maria Sklodowska-Curie National Research Institute of Oncology (PL), Policlinico San Matteo Fondazione (IT), Istituti di Ricovero e Cura a Carattere Scientifico (IT), University Hospital Carl Gustav Carus (DE), European Society for Blood and Marrow Transplantation (FR), Heinrich Heine University Düsseldorf (DE), University College London (GB), University of Naples Federico II (IT), Technische Universität Dresden (DE), Charité - Universitätsmedizin Berlin (DE)
Openalex Percentile: Top 1%
Myeloproliferative Neoplasms: Diagnosis and Treatment
14.63
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.