TY - GEN
T1 - Prediction of clinical events in hemodialysis patients using an artificial neural network
AU - Putra, Firdani Rianda
AU - Nursetyo, Aldilas Achmad
AU - Thakur, Saurabh Singh
AU - Roy, Ram Babu
AU - Syed-Abdul, Shabbir
AU - Malwade, Shwetambara
AU - Lia, 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 - Advanced chronic kidney disease (CKD) requires routine renal replacement therapy (RRT) that involves hemodialysis (HD) which may cause increased risk of muscle spasms, cardiovascular events, and death. We used Artificial Neural Network (ANN) method to predict clinical events during the HD sessions. The vital signs, captured using a non-contact bed-sensor, and demographic information from the electronic medical records for 109 patients enrolled in the study was used. Weka Workbench software was used to train and validate the ANN model. The prediction model was built using a Multilayer perceptron (MLP) algorithm as part of the ANN with 10-fold cross-validation. The model showed mean precision and recall of 93.45% and AUC of 96.7%. Age was the most important variable for static feature and heart rate for dynamic feature. This model can be used to predict the risk of clinical events among HD patients and can support decision-making for healthcare professionals.
AB - Advanced chronic kidney disease (CKD) requires routine renal replacement therapy (RRT) that involves hemodialysis (HD) which may cause increased risk of muscle spasms, cardiovascular events, and death. We used Artificial Neural Network (ANN) method to predict clinical events during the HD sessions. The vital signs, captured using a non-contact bed-sensor, and demographic information from the electronic medical records for 109 patients enrolled in the study was used. Weka Workbench software was used to train and validate the ANN model. The prediction model was built using a Multilayer perceptron (MLP) algorithm as part of the ANN with 10-fold cross-validation. The model showed mean precision and recall of 93.45% and AUC of 96.7%. Age was the most important variable for static feature and heart rate for dynamic feature. This model can be used to predict the risk of clinical events among HD patients and can support decision-making for healthcare professionals.
KW - Electronic health records
KW - Neural networks
KW - Renal dialysis
UR - http://www.scopus.com/inward/record.url?scp=85071420486&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071420486&partnerID=8YFLogxK
U2 - 10.3233/SHTI190539
DO - 10.3233/SHTI190539
M3 - Conference contribution
C2 - 31438236
AN - SCOPUS:85071420486
T3 - Studies in Health Technology and Informatics
SP - 1570
EP - 1571
BT - MEDINFO 2019
A2 - Seroussi, Brigitte
A2 - Ohno-Machado, Lucila
A2 - Ohno-Machado, Lucila
A2 - Seroussi, Brigitte
PB - IOS Press
T2 - 17th World Congress on Medical and Health Informatics, MEDINFO 2019
Y2 - 25 August 2019 through 30 August 2019
ER -