Title :

Artificial intelligence methods to estimate overall mortality and non-relapse mortality following allogeneic HCT in the modern era: an EBMT-TCWP study.

Author(s) :

Rius-Sansalvador, B. [Auteur]
University of Barcelona
Moreno, V. [Auteur]
University of Barcelona
Peczynski, C. [Auteur]
CHU Saint-Antoine [AP-HP]
Polge, E. [Auteur]
CHU Saint-Antoine [AP-HP]
Galimard, J. E. [Auteur]
Kröger, N. [Auteur]
Universitaetsklinikum Hamburg-Eppendorf = University Medical Center Hamburg-Eppendorf [Hamburg] [UKE]
Blaise, D. [Auteur]
Institut Paoli-Calmettes [IPC]
Peffault De Latour, R. [Auteur]
Hopital Saint-Louis [AP-HP] [AP-HP]
Institut Universitaire d'Hématologie [IUH]
Kulagin, A. [Auteur]
Pavlov First Saint Petersburg State Medical University [St. Petersburg]
Mousavi, A. [Auteur]
Shariati Hospital [Tehran, Islamic Republic of Iran]
Stelljes, M. [Auteur]
University Hospital Münster - Universitaetsklinikum Muenster [Germany] [UKM]
Hamladji, R. M. [Auteur]
Middeke, J. M. [Auteur]
University Hospital Carl Gustav Carus [Dresden, Germany]
Salmenniemi, U. [Auteur]
Sengeloev, H. [Auteur]
Rigshospitalet [Copenhagen]
Forcade, E. [Auteur]
Centre Hospitalier Universitaire de Bordeaux [CHU Bordeaux]
Platzbecker, U. [Auteur]
University Hospital Leipzig = Universitätsklinikum Leipzig
Reményi, P. [Auteur]
Dél-pesti Centrumkórház - Országos Hematológiai és Infektológiai Intézet [Budapest, Hungary]
Angelucci, E. [Auteur]
Chevallier, P. [Auteur]
Centre Hospitalier Universitaire de Nantes = Nantes University Hospital [CHU Nantes]
Yakoub-Agha, Ibrahim [Auteur]
Institut de Recherche Translationnelle sur l'Inflammation (INFINITE) - U1286
Craddock, C. [Auteur]
Queens Elizabeth Hospital [Birmingham]
Ciceri, F. [Auteur]
Ospedale San Raffaele
Schroeder, T. [Auteur]
University Hospital Essen [AöR]
Aljurf, M. [Auteur]
King Faisal Specialist Hospital and Resarch Centre [Riyadh, Saudi Arabia] [KFSHRC]
Ch, K. [Auteur]
Medizinische Hochschule Hannover = Hannover Medical School [MHH]
Moiseev, I. [Auteur]
Pavlov First Saint Petersburg State Medical University [St. Petersburg]
Penack, O. [Auteur]
Charité - UniversitätsMedizin = Berlin University Medicine
Schoemans, H. [Auteur]
University Hospitals Leuven [Leuven]
Mohty, M. [Auteur]
CHU Saint-Antoine [AP-HP]
Glass, B. [Auteur]
Helios Klinikum [Erfurt]
Sureda, A. [Auteur]
University of Barcelona
Basak, G. [Auteur]
Medical University of Warsaw - Poland
Peric, Z. [Auteur]
University of Zagreb

Journal title :

Bone Marrow Transplantation

Abbreviated title :

Bone Marrow Transplant

Publication date :

2023-11-27

ISSN :

1476-5365

HAL domain(s) :

Sciences du Vivant [q-bio]

English abstract : [en]

Allogeneic haematopoietic cell transplantation (alloHCT) has curative potential counterbalanced by its toxicity. Prognostic scores fail to include current era patients and alternative donors. We examined adult patients ...
Show more >Allogeneic haematopoietic cell transplantation (alloHCT) has curative potential counterbalanced by its toxicity. Prognostic scores fail to include current era patients and alternative donors. We examined adult patients from the EBMT registry who underwent alloHCT between 2010 and 2019 for oncohaematological disease. Our primary objective was to develop a new prognostic score for overall mortality (OM), with a secondary objective of predicting non-relapse mortality (NRM) using the OM score. AI techniques were employed. The model for OM was trained, optimized, and validated using 70%, 15%, and 15% of the data set, respectively. The top models, “gradient boosting” for OM (AUC = 0.64) and “elasticnet” for NRM (AUC = 0.62), were selected. The analysis included 33,927 patients. In the final prognostic model, patients with the lowest score had a 2-year OM and NRM of 18 and 13%, respectively, while those with the highest score had a 2-year OM and NRM of 82 and 93%, respectively. The results were consistent in the subset of the haploidentical cohort (n = 4386). Our score effectively stratifies the risk of OM and NRM in the current era but do not significantly improve mortality prediction. Future prognostic scores can benefit from identifying biological or dynamic markers post alloHCT.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Administrative institution(s) :

Université de Lille
Inserm
CHU Lille

Collections :

• Institut de Recherche Translationnelle sur l'Inflammation (INFINITE) - U1286

Submission date :

2024-02-06T22:19:31Z
2024-03-21T09:27:14Z