Cargando…

Chronic kidney disease prediction using boosting techniques based on clinical parameters

Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning technique...

Descripción completa

Detalles Bibliográficos
Autores principales: Ganie, Shahid Mohammad, Dutta Pramanik, Pijush Kanti, Mallik, Saurav, Zhao, Zhongming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10691694/
https://www.ncbi.nlm.nih.gov/pubmed/38039306
http://dx.doi.org/10.1371/journal.pone.0295234
_version_ 1785152789100363776
author Ganie, Shahid Mohammad
Dutta Pramanik, Pijush Kanti
Mallik, Saurav
Zhao, Zhongming
author_facet Ganie, Shahid Mohammad
Dutta Pramanik, Pijush Kanti
Mallik, Saurav
Zhao, Zhongming
author_sort Ganie, Shahid Mohammad
collection PubMed
description Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various disease diagnoses and predictions. Ensemble learning approaches have become useful for predicting many complex diseases. In this paper, we utilise the boosting method, one of the popular ensemble learnings, to achieve a higher prediction accuracy for CKD. Five boosting algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, and gradient boosting. We experimented with the CKD data set from the UCI machine learning repository. Various preprocessing steps are employed to achieve better prediction performance, along with suitable hyperparameter tuning and feature selection. We assessed the degree of importance of each feature in the dataset leading to CKD. The performance of each model was evaluated with accuracy, precision, recall, F1-score, Area under the curve-receiving operator characteristic (AUC-ROC), and runtime. AdaBoost was found to have the overall best performance among the five algorithms, scoring the highest in almost all the performance measures. It attained 100% and 98.47% accuracy for training and testing sets. This model also exhibited better precision, recall, and AUC-ROC curve performance.
format Online
Article
Text
id pubmed-10691694
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-106916942023-12-02 Chronic kidney disease prediction using boosting techniques based on clinical parameters Ganie, Shahid Mohammad Dutta Pramanik, Pijush Kanti Mallik, Saurav Zhao, Zhongming PLoS One Research Article Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various disease diagnoses and predictions. Ensemble learning approaches have become useful for predicting many complex diseases. In this paper, we utilise the boosting method, one of the popular ensemble learnings, to achieve a higher prediction accuracy for CKD. Five boosting algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, and gradient boosting. We experimented with the CKD data set from the UCI machine learning repository. Various preprocessing steps are employed to achieve better prediction performance, along with suitable hyperparameter tuning and feature selection. We assessed the degree of importance of each feature in the dataset leading to CKD. The performance of each model was evaluated with accuracy, precision, recall, F1-score, Area under the curve-receiving operator characteristic (AUC-ROC), and runtime. AdaBoost was found to have the overall best performance among the five algorithms, scoring the highest in almost all the performance measures. It attained 100% and 98.47% accuracy for training and testing sets. This model also exhibited better precision, recall, and AUC-ROC curve performance. Public Library of Science 2023-12-01 /pmc/articles/PMC10691694/ /pubmed/38039306 http://dx.doi.org/10.1371/journal.pone.0295234 Text en https://creativecommons.org/publicdomain/zero/1.0/This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 (https://creativecommons.org/publicdomain/zero/1.0/) public domain dedication.
spellingShingle Research Article
Ganie, Shahid Mohammad
Dutta Pramanik, Pijush Kanti
Mallik, Saurav
Zhao, Zhongming
Chronic kidney disease prediction using boosting techniques based on clinical parameters
title Chronic kidney disease prediction using boosting techniques based on clinical parameters
title_full Chronic kidney disease prediction using boosting techniques based on clinical parameters
title_fullStr Chronic kidney disease prediction using boosting techniques based on clinical parameters
title_full_unstemmed Chronic kidney disease prediction using boosting techniques based on clinical parameters
title_short Chronic kidney disease prediction using boosting techniques based on clinical parameters
title_sort chronic kidney disease prediction using boosting techniques based on clinical parameters
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10691694/
https://www.ncbi.nlm.nih.gov/pubmed/38039306
http://dx.doi.org/10.1371/journal.pone.0295234
work_keys_str_mv AT ganieshahidmohammad chronickidneydiseasepredictionusingboostingtechniquesbasedonclinicalparameters
AT duttapramanikpijushkanti chronickidneydiseasepredictionusingboostingtechniquesbasedonclinicalparameters
AT malliksaurav chronickidneydiseasepredictionusingboostingtechniquesbasedonclinicalparameters
AT zhaozhongming chronickidneydiseasepredictionusingboostingtechniquesbasedonclinicalparameters