Cargando…

Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model

Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches w...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Hyung-Chul, Yoon, Soo Bin, Yang, Seong-Mi, Kim, Won Ho, Ryu, Ho-Geol, Jung, Chul-Woo, Suh, Kyung-Suk, Lee, Kook Hyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6262324/
https://www.ncbi.nlm.nih.gov/pubmed/30413107
http://dx.doi.org/10.3390/jcm7110428
_version_ 1783375079423344640
author Lee, Hyung-Chul
Yoon, Soo Bin
Yang, Seong-Mi
Kim, Won Ho
Ryu, Ho-Geol
Jung, Chul-Woo
Suh, Kyung-Suk
Lee, Kook Hyun
author_facet Lee, Hyung-Chul
Yoon, Soo Bin
Yang, Seong-Mi
Kim, Won Ho
Ryu, Ho-Geol
Jung, Chul-Woo
Suh, Kyung-Suk
Lee, Kook Hyun
author_sort Lee, Hyung-Chul
collection PubMed
description Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86–0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56–0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.
format Online
Article
Text
id pubmed-6262324
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-62623242018-12-03 Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model Lee, Hyung-Chul Yoon, Soo Bin Yang, Seong-Mi Kim, Won Ho Ryu, Ho-Geol Jung, Chul-Woo Suh, Kyung-Suk Lee, Kook Hyun J Clin Med Article Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86–0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56–0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results. MDPI 2018-11-08 /pmc/articles/PMC6262324/ /pubmed/30413107 http://dx.doi.org/10.3390/jcm7110428 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lee, Hyung-Chul
Yoon, Soo Bin
Yang, Seong-Mi
Kim, Won Ho
Ryu, Ho-Geol
Jung, Chul-Woo
Suh, Kyung-Suk
Lee, Kook Hyun
Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title_full Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title_fullStr Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title_full_unstemmed Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title_short Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model
title_sort prediction of acute kidney injury after liver transplantation: machine learning approaches vs. logistic regression model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6262324/
https://www.ncbi.nlm.nih.gov/pubmed/30413107
http://dx.doi.org/10.3390/jcm7110428
work_keys_str_mv AT leehyungchul predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT yoonsoobin predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT yangseongmi predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT kimwonho predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT ryuhogeol predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT jungchulwoo predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT suhkyungsuk predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel
AT leekookhyun predictionofacutekidneyinjuryafterlivertransplantationmachinelearningapproachesvslogisticregressionmodel