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

Áreas de investigación:

• Applications - Donor-recipient matching in liver transplants
• Applications - Health

Año:

2021

Tipo de publicación:

Artículo

Palabras clave:

machine learning, statistical techniques, donor-recipient matching, liver transplant, transplantation, liver, liver transplantation, UNOS database, UNOS

Autores:

• Guijo-Rubio, David
• Briceño, Javier
• Gutiérrez, Pedro Antonio
• Ayllón, Maria Dolores
• Ciria, Rubén
• Hervás-Martínez, César

Journal:

PLoS One

Volumen:

16

Número:

5

Páginas:

e0252068

Mes:

Mayo

BibTex:

@article{PlosGuijo2021, author = "David Guijo-Rubio and Javier Brice{\~n}o and Pedro Antonio Guti{\'e}rrez and Maria Dolores Ayll{\'o}n and Rub{\'e}n Ciria and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "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 Na{\"i}ve 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.", awards = "JCR(2021): 3.752 Position: 29/73 (Q2) Category: MULTIDISCIPLINARY SCIENCES", comments = "JCR(2021): 3.752 Position: 29/73 (Q2) Category: MULTIDISCIPLINARY SCIENCES", doi = "10.1371/journal.pone.0252068", journal = "PLoS One", keywords = "machine learning, statistical techniques, donor-recipient matching, liver transplant, transplantation, liver, liver transplantation, UNOS database, UNOS", month = "Mayo", note = "JCR(2021): 3.752 Position: 29/73 (Q2) Category: MULTIDISCIPLINARY SCIENCES", number = "5", pages = " e0252068", title = "{S}tatistical methods versus machine learning techniques for donor-recipient matching in liver transplantation", url = "doi.org/10.1371/journal.pone.0252068", volume = "16", year = "2021", }

Nota:

JCR(2021): 3.752 Position: 29/73 (Q2) Category: MULTIDISCIPLINARY SCIENCES

Abstract:

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.

Comentarios:

JCR(2021): 3.752 Position: 29/73 (Q2) Category: MULTIDISCIPLINARY SCIENCES