Javier Briceño1, Manuel Cruz-Ramírez2, Martín Prieto3, Miguel Navasa4, Jorge Ortiz de Urbina5, Rafael Orti6, Miguel-Ángel Gómez-Bravo7, Alejandra Otero8, Evaristo Varo9, Santiago Tomé9, Gerardo Clemente10, Rafael Bañares10, Rafael Bárcena11, Valentín Cuervas-Mons12, Guillermo Solórzano13, Carmen Vinaixa3, Angel Rubín3, Jordi Colmenero4, Andrés Valdivieso5, Rubén Ciria6, César Hervás-Martínez2, Manuel de la Mata6. 1. Liver Transplantation Unit, CIBERehd, IMIBIC, Hospital Reina Sofía, Córdoba, Spain. Electronic address: javibriceno@hotmail.com. 2. Department of Computer Science and Numerical Analysis, University of Córdoba, Spain. 3. Liver Transplantation Unit, CIBERehd, Hospital La Fe, Valencia, Spain. 4. Liver Transplantation Unit, Hospital Clínic, Barcelona, Spain. 5. Liver Transplantation Unit, Hospital de Cruces, Bilbao, Spain. 6. Liver Transplantation Unit, CIBERehd, IMIBIC, Hospital Reina Sofía, Córdoba, Spain. 7. Liver Transplantation Unit, Hospital Virgen del Rocío, Sevilla, Spain. 8. Liver Transplantation Unit, Hospital Juan Canalejo, A Coruña, Spain. 9. Liver Transplantation Unit, Hospital Clínico Universitario, Santiago de Compostela, Spain. 10. Liver Transplantation Unit, Hospital Gregorio Marañón, Madrid, Spain. 11. Liver Transplantation Unit, Hospital Ramón y Cajal, Madrid, Spain. 12. Liver Transplantation Unit, Hospital Puerta de Hierro, Madrid, Spain. 13. Liver Transplantation Unit, Hospital Infanta Cristina, Badajoz, Spain.
Abstract
BACKGROUND & AIMS: There is an increasing discrepancy between the number of potential liver graft recipients and the number of organs available. Organ allocation should follow the concept of benefit of survival, avoiding human-innate subjectivity. The aim of this study is to use artificial-neural-networks (ANNs) for donor-recipient (D-R) matching in liver transplantation (LT) and to compare its accuracy with validated scores (MELD, D-MELD, DRI, P-SOFT, SOFT, and BAR) of graft survival. METHODS: 64 donor and recipient variables from a set of 1003 LTs from a multicenter study including 11 Spanish centres were included. For each D-R pair, common statistics (simple and multiple regression models) and ANN formulae for two non-complementary probability-models of 3-month graft-survival and -loss were calculated: a positive-survival (NN-CCR) and a negative-loss (NN-MS) model. The NN models were obtained by using the Neural Net Evolutionary Programming (NNEP) algorithm. Additionally, receiver-operating-curves (ROC) were performed to validate ANNs against other scores. RESULTS: Optimal results for NN-CCR and NN-MS models were obtained, with the best performance in predicting the probability of graft-survival (90.79%) and -loss (71.42%) for each D-R pair, significantly improving results from multiple regressions. ROC curves for 3-months graft-survival and -loss predictions were significantly more accurate for ANN than for other scores in both NN-CCR (AUROC-ANN=0.80 vs. -MELD=0.50; -D-MELD=0.54; -P-SOFT=0.54; -SOFT=0.55; -BAR=0.67 and -DRI=0.42) and NN-MS (AUROC-ANN=0.82 vs. -MELD=0.41; -D-MELD=0.47; -P-SOFT=0.43; -SOFT=0.57, -BAR=0.61 and -DRI=0.48). CONCLUSIONS: ANNs may be considered a powerful decision-making technology for this dataset, optimizing the principles of justice, efficiency and equity. This may be a useful tool for predicting the 3-month outcome and a potential research area for future D-R matching models.
BACKGROUND & AIMS: There is an increasing discrepancy between the number of potential liver graft recipients and the number of organs available. Organ allocation should follow the concept of benefit of survival, avoiding human-innate subjectivity. The aim of this study is to use artificial-neural-networks (ANNs) for donor-recipient (D-R) matching in liver transplantation (LT) and to compare its accuracy with validated scores (MELD, D-MELD, DRI, P-SOFT, SOFT, and BAR) of graft survival. METHODS: 64 donor and recipient variables from a set of 1003 LTs from a multicenter study including 11 Spanish centres were included. For each D-R pair, common statistics (simple and multiple regression models) and ANN formulae for two non-complementary probability-models of 3-month graft-survival and -loss were calculated: a positive-survival (NN-CCR) and a negative-loss (NN-MS) model. The NN models were obtained by using the Neural Net Evolutionary Programming (NNEP) algorithm. Additionally, receiver-operating-curves (ROC) were performed to validate ANNs against other scores. RESULTS: Optimal results for NN-CCR and NN-MS models were obtained, with the best performance in predicting the probability of graft-survival (90.79%) and -loss (71.42%) for each D-R pair, significantly improving results from multiple regressions. ROC curves for 3-months graft-survival and -loss predictions were significantly more accurate for ANN than for other scores in both NN-CCR (AUROC-ANN=0.80 vs. -MELD=0.50; -D-MELD=0.54; -P-SOFT=0.54; -SOFT=0.55; -BAR=0.67 and -DRI=0.42) and NN-MS (AUROC-ANN=0.82 vs. -MELD=0.41; -D-MELD=0.47; -P-SOFT=0.43; -SOFT=0.57, -BAR=0.61 and -DRI=0.48). CONCLUSIONS: ANNs may be considered a powerful decision-making technology for this dataset, optimizing the principles of justice, efficiency and equity. This may be a useful tool for predicting the 3-month outcome and a potential research area for future D-R matching models.
Authors: Lawrence Lau; Yamuna Kankanige; Benjamin Rubinstein; Robert Jones; Christopher Christophi; Vijayaragavan Muralidharan; James Bailey Journal: Transplantation Date: 2017-04 Impact factor: 4.939
Authors: Nikhilesh R Mazumder; Kofi Atiemo; Matthew Kappus; Giuseppe Cullaro; Matthew E Harinstein; Daniela Ladner; Elizabeth Verna; Jennifer Lai; Josh Levitsky Journal: Transplantation Date: 2020-02 Impact factor: 5.385
Authors: Joris J Blok; Hein Putter; Herold J Metselaar; Robert J Porte; Federica Gonella; Jeroen de Jonge; Aad P van den Berg; Josephine van der Zande; Jacob D de Boer; Bart van Hoek; Andries E Braat Journal: Transplant Direct Date: 2018-08-21
Authors: Georgios Kantidakis; Hein Putter; Carlo Lancia; Jacob de Boer; Andries E Braat; Marta Fiocco Journal: BMC Med Res Methodol Date: 2020-11-16 Impact factor: 4.615