Statistical methods versus machine learning techniques for donor-recipient matching in liver transplantation.

Autor: Guijo-Rubio D; Department of Computer Sciences and Numerical Analysis, University of Córdoba, Córdoba, Spain., Briceño J; Unit of Hepatobiliary Surgery and Liver Transplantation, Hospital Universitario Reina Sofía, IMIBIC, Córdoba, Spain., Gutiérrez PA; Department of Computer Sciences and Numerical Analysis, University of Córdoba, Córdoba, Spain., Ayllón MD; Unit of Hepatobiliary Surgery and Liver Transplantation, Hospital Universitario Reina Sofía, IMIBIC, Córdoba, Spain., Ciria R; Unit of Hepatobiliary Surgery and Liver Transplantation, Hospital Universitario Reina Sofía, IMIBIC, Córdoba, Spain., Hervás-Martínez C; Department of Computer Sciences and Numerical Analysis, University of Córdoba, Córdoba, Spain.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2021 May 21; Vol. 16 (5), pp. e0252068. Date of Electronic Publication: 2021 May 21 (Print Publication: 2021).
DOI: 10.1371/journal.pone.0252068
Abstrakt: Donor-Recipient (D-R) matching is one of the main challenges to be fulfilled nowadays. Due to the increasing number of recipients and the small amount of donors in liver transplantation, the allocation method is crucial. In this paper, to establish a fair comparison, the United Network for Organ Sharing database was used with 4 different end-points (3 months, and 1, 2 and 5 years), with a total of 39, 189 D-R pairs and 28 donor and recipient variables. Modelling techniques were divided into two groups: 1) classical statistical methods, including Logistic Regression (LR) and Naïve Bayes (NB), and 2) standard machine learning techniques, including Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB) or Support Vector Machines (SVM), among others. The methods were compared with standard scores, MELD, SOFT and BAR. For the 5-years end-point, LR (AUC = 0.654) outperformed several machine learning techniques, such as MLP (AUC = 0.599), GB (AUC = 0.600), SVM (AUC = 0.624) or RF (AUC = 0.644), among others. Moreover, LR also outperformed standard scores. The same pattern was reproduced for the others 3 end-points. Complex machine learning methods were not able to improve the performance of liver allocation, probably due to the implicit limitations associated to the collection process of the database.
Competing Interests: The authors have declared that no competing interests exist.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje