Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant

Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Andrzej Konieczny, Jakub Stojanowski, Klaudia Rydzyńska, Mariusz Kusztal, Magdalena Krajewska
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial intelligence machine learning delayed-graft function deceased donors kidney transplantation Medicine R
Acceso en línea:	https://doaj.org/article/38e340ee6f7e4481b04aef70c3085924
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:38e340ee6f7e4481b04aef70c3085924
record_format	dspace
spelling	oai:doaj.org-article:38e340ee6f7e4481b04aef70c30859242021-11-25T18:00:50ZArtificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant10.3390/jcm102252442077-0383https://doaj.org/article/38e340ee6f7e4481b04aef70c30859242021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0383/10/22/5244https://doaj.org/toc/2077-0383Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.Andrzej KoniecznyJakub StojanowskiKlaudia RydzyńskaMariusz KusztalMagdalena KrajewskaMDPI AGarticleartificial intelligencemachine learningdelayed-graft functiondeceased donorskidney transplantationMedicineRENJournal of Clinical Medicine, Vol 10, Iss 5244, p 5244 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence machine learning delayed-graft function deceased donors kidney transplantation Medicine R
spellingShingle	artificial intelligence machine learning delayed-graft function deceased donors kidney transplantation Medicine R Andrzej Konieczny Jakub Stojanowski Klaudia Rydzyńska Mariusz Kusztal Magdalena Krajewska Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
description	Delayed-graft function (DGF) might be responsible for shorter graft survival. Therefore, a clinical tool predicting its occurrence is vital for the risk assessment of transplant outcomes. In a single-center study, we conducted data mining and machine learning experiments, resulting in DGF predictive models based on random forest classifiers (RF) and an artificial neural network called multi-layer perceptron (MLP). All designed models had four common input parameters, determining the best accuracy and discriminant ability: donor’s eGFR, recipient’s BMI, donor’s BMI, and recipient–donor weight difference. RF and MLP designs, using these parameters, achieved an accuracy of 84.38% and an area under curve (AUC) 0.84. The model additionally implementing a donor’s age, gender, and Kidney Donor Profile Index (KDPI) accomplished an accuracy of 93.75% and an AUC of 0.91. The other configuration with the estimated post-transplant survival (EPTS) and the kidney donor risk profile (KDRI) achieved an accuracy of 93.75% and an AUC of 0.92. Using machine learning, we were able to assess the risk of DGF in recipients after kidney transplant from a deceased donor. Our solution is scalable and can be improved during subsequent transplants. Based on the new data, the models can achieve better outcomes.
format	article
author	Andrzej Konieczny Jakub Stojanowski Klaudia Rydzyńska Mariusz Kusztal Magdalena Krajewska
author_facet	Andrzej Konieczny Jakub Stojanowski Klaudia Rydzyńska Mariusz Kusztal Magdalena Krajewska
author_sort	Andrzej Konieczny
title	Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
title_short	Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
title_full	Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
title_fullStr	Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
title_full_unstemmed	Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant
title_sort	artificial intelligence—a tool for risk assessment of delayed-graft function in kidney transplant
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/38e340ee6f7e4481b04aef70c3085924
work_keys_str_mv	AT andrzejkonieczny artificialintelligenceatoolforriskassessmentofdelayedgraftfunctioninkidneytransplant AT jakubstojanowski artificialintelligenceatoolforriskassessmentofdelayedgraftfunctioninkidneytransplant AT klaudiarydzynska artificialintelligenceatoolforriskassessmentofdelayedgraftfunctioninkidneytransplant AT mariuszkusztal artificialintelligenceatoolforriskassessmentofdelayedgraftfunctioninkidneytransplant AT magdalenakrajewska artificialintelligenceatoolforriskassessmentofdelayedgraftfunctioninkidneytransplant
_version_	1718411735920017408

Artificial Intelligence—A Tool for Risk Assessment of Delayed-Graft Function in Kidney Transplant

Ejemplares similares