Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms

Context Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN).Objective This study explored the most suitable classification algorithm for PMN identification, and to...

Full description

Saved in:
Bibliographic Details
Main Authors: Shangmei Cao, Shaozhe Yang, Bolin Chen, Xixia Chen, Xiuhong Fu, Shuifu Tang
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Renal Failure
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/0886022X.2024.2380752
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687671563091968
author Shangmei Cao
Shaozhe Yang
Bolin Chen
Xixia Chen
Xiuhong Fu
Shuifu Tang
author_facet Shangmei Cao
Shaozhe Yang
Bolin Chen
Xixia Chen
Xiuhong Fu
Shuifu Tang
author_sort Shangmei Cao
collection DOAJ
description Context Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN).Objective This study explored the most suitable classification algorithm for PMN identification, and to provide data reference for PMN diagnosis research.Methods A total of 500 patients were referred to Luo-he Central Hospital from 2019 to 2021. All patients were diagnosed with primary glomerular disease confirmed by renal biopsy, contained 322 cases of PMN, the 178 cases of non-PMN. Using the decision tree, random forest, support vector machine, and extreme gradient boosting (Xgboost) to establish a differential diagnosis model for PMN and non-PMN. Based on the true positive rate, true negative rate, false-positive rate, false-negative rate, accuracy, feature work area under the curve (AUC) of subjects, the best performance of the model was chosen.Results The efficiency of the Xgboost model based on the above evaluation indicators was the highest, which the diagnosis of PMN of the sensitivity and specificity, respectively 92% and 96%.Conclusions The differential diagnosis model for PMN was established successfully and the efficiency performance of the Xgboost model was the best. It could be used for the clinical diagnosis of PMN.
format Article
id doaj-art-78b3b26d74fa4d76a57222f224bb84e4
institution DOAJ
issn 0886-022X
1525-6049
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Renal Failure
spelling doaj-art-78b3b26d74fa4d76a57222f224bb84e42025-08-20T03:22:16ZengTaylor & Francis GroupRenal Failure0886-022X1525-60492024-12-0146210.1080/0886022X.2024.2380752Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithmsShangmei Cao0Shaozhe Yang1Bolin Chen2Xixia Chen3Xiuhong Fu4Shuifu Tang5Department of Science and Technology Innovation Center, Luohe Central Hospital, The First Affiliated Hospital of Luohe Medical College, Henan Key Laboratory of Fertility Protection and Aristogenesis, Luohe, ChinaDepartment of Science and Technology Innovation Center, Luohe Central Hospital, The First Affiliated Hospital of Luohe Medical College, Henan Key Laboratory of Fertility Protection and Aristogenesis, Luohe, ChinaDepartment of Science and Technology Innovation Center, Luohe Central Hospital, The First Affiliated Hospital of Luohe Medical College, Henan Key Laboratory of Fertility Protection and Aristogenesis, Luohe, ChinaDivision of Nephrology, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong Province, ChinaDepartment of Science and Technology Innovation Center, Luohe Central Hospital, The First Affiliated Hospital of Luohe Medical College, Henan Key Laboratory of Fertility Protection and Aristogenesis, Luohe, ChinaDivision of Nephrology, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong Province, ChinaContext Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN).Objective This study explored the most suitable classification algorithm for PMN identification, and to provide data reference for PMN diagnosis research.Methods A total of 500 patients were referred to Luo-he Central Hospital from 2019 to 2021. All patients were diagnosed with primary glomerular disease confirmed by renal biopsy, contained 322 cases of PMN, the 178 cases of non-PMN. Using the decision tree, random forest, support vector machine, and extreme gradient boosting (Xgboost) to establish a differential diagnosis model for PMN and non-PMN. Based on the true positive rate, true negative rate, false-positive rate, false-negative rate, accuracy, feature work area under the curve (AUC) of subjects, the best performance of the model was chosen.Results The efficiency of the Xgboost model based on the above evaluation indicators was the highest, which the diagnosis of PMN of the sensitivity and specificity, respectively 92% and 96%.Conclusions The differential diagnosis model for PMN was established successfully and the efficiency performance of the Xgboost model was the best. It could be used for the clinical diagnosis of PMN.https://www.tandfonline.com/doi/10.1080/0886022X.2024.2380752Primary membranous nephropathymachine learning algorithmsdifferential diagnosisanti-PLA2RIgGXgboost model
spellingShingle Shangmei Cao
Shaozhe Yang
Bolin Chen
Xixia Chen
Xiuhong Fu
Shuifu Tang
Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
Renal Failure
Primary membranous nephropathy
machine learning algorithms
differential diagnosis
anti-PLA2R
IgG
Xgboost model
title Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
title_full Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
title_fullStr Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
title_full_unstemmed Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
title_short Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms
title_sort establishing a differential diagnosis model between primary membranous nephropathy and non primary membranous nephropathy by machine learning algorithms
topic Primary membranous nephropathy
machine learning algorithms
differential diagnosis
anti-PLA2R
IgG
Xgboost model
url https://www.tandfonline.com/doi/10.1080/0886022X.2024.2380752
work_keys_str_mv AT shangmeicao establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms
AT shaozheyang establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms
AT bolinchen establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms
AT xixiachen establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms
AT xiuhongfu establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms
AT shuifutang establishingadifferentialdiagnosismodelbetweenprimarymembranousnephropathyandnonprimarymembranousnephropathybymachinelearningalgorithms