TY - GEN
T1 - Graft rejection prediction following kidney transplantation using machine learning techniques
T2 - 17th World Congress on Medical and Health Informatics, MEDINFO 2019
AU - Nursetyo, Aldilas Achmad
AU - Syed-Abdul, Shabbir
AU - Uddin, Mohy
AU - Li, Yu Chuan
N1 - Publisher Copyright:
© 2019 International Medical Informatics Association (IMIA) and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).
PY - 2019/8/21
Y1 - 2019/8/21
N2 - Kidney transplantation is recommended for patients with End-Stage Renal Disease (ESRD). However, complications, such as graft rejection are hard to predict due to donor and recipient variability. This study discusses the role of machine learning (ML) in predicting graft rejection following kidney transplantation, by reviewing the available related literature. PubMed, DBLP, and Scopus databases were searched to identify studies that utilized ML methods, in predicting outcome following kidney transplants. Fourteen studies were included. This study reviewed the deployment of ML in 109,317 kidney transplant patients from 14 studies. We extracted five different ML algorithms from reviewed studies. Decision Tree (DT) algorithms revealed slightly higher performance with overall mean Area Under the Curve (AUC) for DT (79.5% + 0.06) was higher than Artificial Neural Network (ANN) (78.2% + 0.08). For predicting graft rejection, ANN and DT were at the top among ML models that had higher accuracy and AUC.
AB - Kidney transplantation is recommended for patients with End-Stage Renal Disease (ESRD). However, complications, such as graft rejection are hard to predict due to donor and recipient variability. This study discusses the role of machine learning (ML) in predicting graft rejection following kidney transplantation, by reviewing the available related literature. PubMed, DBLP, and Scopus databases were searched to identify studies that utilized ML methods, in predicting outcome following kidney transplants. Fourteen studies were included. This study reviewed the deployment of ML in 109,317 kidney transplant patients from 14 studies. We extracted five different ML algorithms from reviewed studies. Decision Tree (DT) algorithms revealed slightly higher performance with overall mean Area Under the Curve (AUC) for DT (79.5% + 0.06) was higher than Artificial Neural Network (ANN) (78.2% + 0.08). For predicting graft rejection, ANN and DT were at the top among ML models that had higher accuracy and AUC.
KW - Graft Rejection
KW - Kidney Transplantation
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85071456154&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071456154&partnerID=8YFLogxK
U2 - 10.3233/SHTI190173
DO - 10.3233/SHTI190173
M3 - Conference contribution
C2 - 31437875
AN - SCOPUS:85071456154
T3 - Studies in Health Technology and Informatics
SP - 10
EP - 14
BT - MEDINFO 2019
A2 - Seroussi, Brigitte
A2 - Ohno-Machado, Lucila
A2 - Ohno-Machado, Lucila
A2 - Seroussi, Brigitte
PB - IOS Press
Y2 - 25 August 2019 through 30 August 2019
ER -