Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

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

JC. Hernández-Boluda, A. Mosquera-Orgueira, L. Gras, L. Koster, J. Tuffnell, N. Kröger, M. Gambella, T. Schroeder, M. Robin, K. Sockel, J. Passweg, IW. Blau, I. Yakoub-Agha, R. Van Dijck, M. Stelljes, H. Sengeloev, J. Vydra, U. Platzbecker, M. de...

. 2025 ; 145 (26) : 3139-3152. [pub] 20250626

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc25015252

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.

Ematologia e Terapie Cellulari IRCCS Ospedale Policlinico San Martino Genova Italy

European Group for Blood and Marrow Transplantation Leiden Study Unit Leiden The Netherlands

Hematology Department Central Clinical Hospital The Medical University of Warsaw Warsaw Poland

Hematology Department Centre Hospitalier Universitaire de Lille INSERM U1286 Infinite Lille France

Hematology Department Erasmus MC Cancer Institute Rotterdam The Netherlands

Hematology Department Federico 2 University of Naples Naples Italy

Hematology Department Hospital Clínico Universitario Instituto de Investigación Sanitaria del Hospital Clínico de Valencia University of Valencia Valencia Spain

Hematology Department Maria Skłodowska Curie National Research Institute of Oncology Gliwice Poland

Hematology Department Medical Clinic and Policlinic Leipzig Germany

Hematology Department Rigshospitalet Copenhagen Denmark

Hematology Department Saint Louis Hospital Bone Marrow Transplantation Unit Paris France

Hematology Department University College London Hospitals National Health Service Trust London United Kingdom

Hematology Department University Hospital Basel Basel Switzerland

Hematology Department University Hospital Essen Duesseldorf Germany

Hematology Department University Hospital of Santiago de Compostela Instituto de Investigación Sanitaria de Santiago de Compostela Santiago de Compostela Spain

Hematology Department University Hospital Technische Universität Dresden Dresden Germany

Hematology Department University Hospital Uppsala Uppsala Sweden

Hematology Department University Medical Center Hamburg Eppendorf Hamburg Germany

Hematology Department University Medical Centre Utrecht The Netherlands

Hematology Department University of Liege Liege Belgium

Hematology Department University of Muenster Muenster Germany

Institute of Hematology and Blood Transfusion Prague Czech Republic

Medizinische Klinik m S Hämatologie Onkologie und Tumorimmunologie Berlin Germany

Unit of Bone Marrow Transplantation Division of Hematology Fondazione IRCCS Policlinico San Matteo Pavia Italy

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc25015252
003      
CZ-PrNML
005      
20250731090853.0
007      
ta
008      
250708s2025 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1182/blood.2024027287 $2 doi
035    __
$a (PubMed)40145857
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Hernández-Boluda, Juan Carlos $u Hematology Department, Hospital Clínico Universitario, Instituto de Investigación Sanitaria del Hospital Clínico de Valencia, University of Valencia, Valencia, Spain $1 https://orcid.org/0000000242893113
245    10
$a Use of machine learning techniques to predict poor survival after hematopoietic cell transplantation for myelofibrosis / $c JC. Hernández-Boluda, A. Mosquera-Orgueira, L. Gras, L. Koster, J. Tuffnell, N. Kröger, M. Gambella, T. Schroeder, M. Robin, K. Sockel, J. Passweg, IW. Blau, I. Yakoub-Agha, R. Van Dijck, M. Stelljes, H. Sengeloev, J. Vydra, U. Platzbecker, M. de Witte, F. Baron, K. Carlson, J. Rojas, C. Pérez Míguez, D. Crucitti, K. Raj, J. Drozd-Sokolowska, G. Battipaglia, N. Polverelli, T. Czerw, DP. McLornan
520    9_
$a 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.
650    _2
$a lidé $7 D006801
650    12
$a strojové učení $7 D000069550
650    12
$a primární myelofibróza $x terapie $x mortalita $7 D055728
650    12
$a transplantace hematopoetických kmenových buněk $x mortalita $7 D018380
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a lidé středního věku $7 D008875
650    _2
$a senioři $7 D000368
650    _2
$a dospělí $7 D000328
650    _2
$a prognóza $7 D011379
650    _2
$a míra přežití $7 D015996
655    _2
$a časopisecké články $7 D016428
700    1_
$a Mosquera-Orgueira, Adrián $u Hematology Department. University Hospital of Santiago de Compostela, Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain $1 https://orcid.org/0000000348386750
700    1_
$a Gras, Luuk $u European Group for Blood and Marrow Transplantation Leiden Study Unit, Leiden, The Netherlands
700    1_
$a Koster, Linda $u European Group for Blood and Marrow Transplantation Leiden Study Unit, Leiden, The Netherlands
700    1_
$a Tuffnell, Joe $u European Group for Blood and Marrow Transplantation Leiden Study Unit, Leiden, The Netherlands
700    1_
$a Kröger, Nicolaus $u Hematology Department, University Medical Center Hamburg-Eppendorf, Hamburg, Germany $1 https://orcid.org/0000000151039966
700    1_
$a Gambella, Massimiliano $u Ematologia e Terapie Cellulari, IRCCS Ospedale Policlinico San Martino, Genova, Italy
700    1_
$a Schroeder, Thomas $u Hematology Department, University Hospital Essen, Duesseldorf, Germany
700    1_
$a Robin, Marie $u Hematology Department, Saint-Louis Hospital, Bone Marrow Transplantation Unit, Paris, France $1 https://orcid.org/0000000313889876
700    1_
$a Sockel, Katja $u Hematology Department, University Hospital Technische Universität Dresden, Dresden, Germany
700    1_
$a Passweg, Jakob $u Hematology Department, University Hospital Basel, Basel, Switzerland $1 https://orcid.org/0000000170923351
700    1_
$a Blau, Igor Wolfgang $u Medizinische Klinik m. S. Hämatologie, Onkologie und Tumorimmunologie, Berlin, Germany
700    1_
$a Yakoub-Agha, Ibrahim $u Hematology Department, Centre Hospitalier Universitaire de Lille, INSERM U1286, Infinite, Lille, France $1 https://orcid.org/0000000345248782
700    1_
$a Van Dijck, Ruben $u Hematology Department, Erasmus MC Cancer Institute, Rotterdam, The Netherlands $1 https://orcid.org/0000000347487648
700    1_
$a Stelljes, Mattias $u Hematology Department, University of Muenster, Muenster, Germany $1 https://orcid.org/0000000293315145
700    1_
$a Sengeloev, Henrik $u Hematology Department, Rigshospitalet, Copenhagen, Denmark
700    1_
$a Vydra, Jan $u Institute of Hematology and Blood Transfusion, Prague, Czech Republic $1 https://orcid.org/0000000242743895
700    1_
$a Platzbecker, Uwe $u Hematology Department, Medical Clinic and Policlinic, Leipzig, Germany $1 https://orcid.org/0000000318633239 $7 xx0239891
700    1_
$a de Witte, Moniek $u Hematology Department, University Medical Centre, Utrecht, The Netherlands
700    1_
$a Baron, Frédéric $u Hematology Department, University of Liege, Liege, Belgium $1 https://orcid.org/0000000229443812
700    1_
$a Carlson, Kristina $u Hematology Department, University Hospital Uppsala, Uppsala, Sweden $1 https://orcid.org/0000000203031350
700    1_
$a Rojas, Javier $u Hematology Department. University Hospital of Santiago de Compostela, Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain
700    1_
$a Pérez Míguez, Carlos $u Hematology Department. University Hospital of Santiago de Compostela, Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain $1 https://orcid.org/0009000479729431
700    1_
$a Crucitti, Davide $u Hematology Department. University Hospital of Santiago de Compostela, Instituto de Investigación Sanitaria de Santiago de Compostela, Santiago de Compostela, Spain $1 https://orcid.org/0009000694589793
700    1_
$a Raj, Kavita $u Hematology Department, University College London Hospitals National Health Service Trust, London, United Kingdom $1 https://orcid.org/000000028258354X
700    1_
$a Drozd-Sokolowska, Joanna $u Hematology Department, Central Clinical Hospital, The Medical University of Warsaw, Warsaw, Poland $1 https://orcid.org/0000000245626264
700    1_
$a Battipaglia, Giorgia $u Hematology Department, Federico II University of Naples, Naples, Italy $1 https://orcid.org/0000000252011786
700    1_
$a Polverelli, Nicola $u Unit of Bone Marrow Transplantation, Division of Hematology, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy $1 https://orcid.org/0000000162979697
700    1_
$a Czerw, Tomasz $u Hematology Department, Maria Skłodowska-Curie National Research Institute of Oncology, Gliwice, Poland $1 https://orcid.org/0000000331084035
700    1_
$a McLornan, Donal P $u Hematology Department, University College London Hospitals National Health Service Trust, London, United Kingdom
773    0_
$w MED00000807 $t Blood $x 1528-0020 $g Roč. 145, č. 26 (2025), s. 3139-3152
856    41
$u https://pubmed.ncbi.nlm.nih.gov/40145857 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20250708 $b ABA008
991    __
$a 20250731090848 $b ABA008
999    __
$a ok $b bmc $g 2366237 $s 1252377
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2025 $b 145 $c 26 $d 3139-3152 $e 20250626 $i 1528-0020 $m Blood $n Blood $x MED00000807
LZP    __
$a Pubmed-20250708

Najít záznam

Citační ukazatele

Možnosti archivace