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 | Size | Format | |
---|---|---|---|---|
899460.pdf | 868.81 kB | Adobe PDF | View/Open |
This item is licensed under a
Creative Commons License