A two‐stage neural network prediction of chronic kidney disease

Abstract Accurate detection of chronic kidney disease (CKD) plays a pivotal role in early diagnosis and treatment. Measured glomerular filtration rate (mGFR) is considered the benchmark indicator in measuring the kidney function. However, due to the high resource cost of measuring mGFR, it is usuall...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hongquan Peng, Haibin Zhu, Chi Wa Ao Ieong, Tao Tao, Tsung Yang Tsai, Zhi Liu
Formato: article
Lenguaje:EN
Publicado: Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/2bc7a33df5da469f899c68063f4b7664
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:2bc7a33df5da469f899c68063f4b7664
record_format dspace
spelling oai:doaj.org-article:2bc7a33df5da469f899c68063f4b76642021-11-05T12:35:39ZA two‐stage neural network prediction of chronic kidney disease1751-88571751-884910.1049/syb2.12031https://doaj.org/article/2bc7a33df5da469f899c68063f4b76642021-09-01T00:00:00Zhttps://doi.org/10.1049/syb2.12031https://doaj.org/toc/1751-8849https://doaj.org/toc/1751-8857Abstract Accurate detection of chronic kidney disease (CKD) plays a pivotal role in early diagnosis and treatment. Measured glomerular filtration rate (mGFR) is considered the benchmark indicator in measuring the kidney function. However, due to the high resource cost of measuring mGFR, it is usually approximated by the estimated glomerular filtration rate, underscoring an urgent need for more precise and stable approaches. With the introduction of novel machine learning methodologies, prediction performance is shown to be significantly improved across all available data, but the performance is still limited because of the lack of models in dealing with ultra‐high dimensional datasets. This study aims to provide a two‐stage neural network approach for prediction of GFR and to suggest some other useful biomarkers obtained from the blood metabolites in measuring GFR. It is a composite of feature shrinkage and neural network when the number of features is much larger than the number of training samples. The results show that the proposed method outperforms the existing ones, such as convolutionneural network and direct deep neural network.Hongquan PengHaibin ZhuChi Wa Ao IeongTao TaoTsung Yang TsaiZhi LiuWileyarticleBiology (General)QH301-705.5ENIET Systems Biology, Vol 15, Iss 5, Pp 163-171 (2021)
institution DOAJ
collection DOAJ
language EN
topic Biology (General)
QH301-705.5
spellingShingle Biology (General)
QH301-705.5
Hongquan Peng
Haibin Zhu
Chi Wa Ao Ieong
Tao Tao
Tsung Yang Tsai
Zhi Liu
A two‐stage neural network prediction of chronic kidney disease
description Abstract Accurate detection of chronic kidney disease (CKD) plays a pivotal role in early diagnosis and treatment. Measured glomerular filtration rate (mGFR) is considered the benchmark indicator in measuring the kidney function. However, due to the high resource cost of measuring mGFR, it is usually approximated by the estimated glomerular filtration rate, underscoring an urgent need for more precise and stable approaches. With the introduction of novel machine learning methodologies, prediction performance is shown to be significantly improved across all available data, but the performance is still limited because of the lack of models in dealing with ultra‐high dimensional datasets. This study aims to provide a two‐stage neural network approach for prediction of GFR and to suggest some other useful biomarkers obtained from the blood metabolites in measuring GFR. It is a composite of feature shrinkage and neural network when the number of features is much larger than the number of training samples. The results show that the proposed method outperforms the existing ones, such as convolutionneural network and direct deep neural network.
format article
author Hongquan Peng
Haibin Zhu
Chi Wa Ao Ieong
Tao Tao
Tsung Yang Tsai
Zhi Liu
author_facet Hongquan Peng
Haibin Zhu
Chi Wa Ao Ieong
Tao Tao
Tsung Yang Tsai
Zhi Liu
author_sort Hongquan Peng
title A two‐stage neural network prediction of chronic kidney disease
title_short A two‐stage neural network prediction of chronic kidney disease
title_full A two‐stage neural network prediction of chronic kidney disease
title_fullStr A two‐stage neural network prediction of chronic kidney disease
title_full_unstemmed A two‐stage neural network prediction of chronic kidney disease
title_sort two‐stage neural network prediction of chronic kidney disease
publisher Wiley
publishDate 2021
url https://doaj.org/article/2bc7a33df5da469f899c68063f4b7664
work_keys_str_mv AT hongquanpeng atwostageneuralnetworkpredictionofchronickidneydisease
AT haibinzhu atwostageneuralnetworkpredictionofchronickidneydisease
AT chiwaaoieong atwostageneuralnetworkpredictionofchronickidneydisease
AT taotao atwostageneuralnetworkpredictionofchronickidneydisease
AT tsungyangtsai atwostageneuralnetworkpredictionofchronickidneydisease
AT zhiliu atwostageneuralnetworkpredictionofchronickidneydisease
AT hongquanpeng twostageneuralnetworkpredictionofchronickidneydisease
AT haibinzhu twostageneuralnetworkpredictionofchronickidneydisease
AT chiwaaoieong twostageneuralnetworkpredictionofchronickidneydisease
AT taotao twostageneuralnetworkpredictionofchronickidneydisease
AT tsungyangtsai twostageneuralnetworkpredictionofchronickidneydisease
AT zhiliu twostageneuralnetworkpredictionofchronickidneydisease
_version_ 1718444278889316352