Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223493
Title: Machine Learning Algorithms in Controlled Donation After Circulatory Death Under Normothermic Regional Perfusion: A Graft Survival Prediction Model
Author: Calleja Lozano, Rafael
Rivera Gavilán, Marcos
Guijo Rubio, David
Hessheimer, Amelia Judith
Rosa, Gloria de la
Gastaca, Mikel
Otero Ferreiro, Alejandra
Ramírez Romero, Pablo
Boscà Robledo, Andrea
Santoyo, Julio
Marín Gómez, Luís Miguel
Villar del Moral, Jesús
Fundora, Yilian
Lladó Garriga, Laura
Loinaz, Carmelo
Jiménez Garrido, Manuel
Rodríguez Laíz, Gonzalo
López Baena, José Ángel
Charco, Ramón
Varo, Evaristo
Rotellar Sastre, Fernando
Alonso, Ayaya
Rodríguez Sanjuan, Juan Carlos
Blanco-Fernández, Gerardo
Nuño, Javier
Pacheco Sánchez, David
Coll, Elisabeth
Domínguez Gil, Beatriz
Fondevila Campo, Constantino
Ayllón, María Dolors
Durán Martínez, Manuel
Ciria, Rubén
Gutiérrez, Pedro Antonio
Gómez Orellana, Antonio
Hervás Martínez, Cesar
Briceño, Javier
Keywords: Aprenentatge automàtic
Donants d'òrgans
Machine learning
Organ donors
Issue Date: Jul-2025
Publisher: Lippincott, Williams & Wilkins
Abstract: Background. Several scores have been developed to stratify the risk of graft loss in controlled donation after circulatory death (cDCD). However, their performance is unsatisfactory in the Spanish population, where most cDCD livers are recovered using normothermic regional perfusion (NRP). Consequently, we explored the role of different machine learning-based classifiers as predictive models for graft survival. A risk stratification score integrated with the model of end-stage liver disease score in a donor-recipient (D-R) matching system was developed. Methods. This retrospective multicenter cohort study used 539 D-R pairs of cDCD livers recovered with NRP, including 20 donor, recipient, and NRP variables. The following machine learning-based classifiers were evaluated: logistic regression, ridge classifier, support vector classifier, multilayer perceptron, and random forest. The endpoints were the 3- and 12-mo graft survival rates. A 3- and 12-mo risk score was developed using the best model obtained. Results. Logistic regression yielded the best performance at 3 mo (area under the receiver operating characteristic curve = 0.82) and 12 mo (area under the receiver operating characteristic curve = 0.83). A D-R matching system was proposed on the basis of the current model of end-stage liver disease score and cDCD-NRP risk score. Conclusions. The satisfactory performance of the proposed score within the study population suggests a significant potential to support liver allocation in cDCD-NRP grafts. External validation is challenging, but this methodology may be explored in other regions.
Note: Reproducció del document publicat a: https://doi.org/10.1097/tp.0000000000005312
It is part of: Transplantation, 2025, vol. 109, num.7, p. e362-e370
URI: https://hdl.handle.net/2445/223493
Related resource: https://doi.org/10.1097/tp.0000000000005312
ISSN: 0041-1337
Appears in Collections:Articles publicats en revistes (Cirurgia i Especialitats Medicoquirúrgiques)
Articles publicats en revistes (Institut d'lnvestigació Biomèdica de Bellvitge (IDIBELL))

Files in This Item:
File Description SizeFormat 
899460.pdf868.81 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons