Identification of potential predictors for subtype IgA nephropathy through analyses of blood biochemical indicators

Jing Gao, Juan Cui, Yong Wang, Zhennan Dong, Yaping Tian, Ying Xu

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Background: Immunoglobulin A nephropathy (IgAN), a dominant glomerulonephritis in China, has presented challenges in its early non-invasive diagnosis and accordingly has drawn considerable attention regarding the need to develop effective easy-to-conduct methods. Methods: In this retrospective study, a support vector machine-based classifier was trained to obtain a minimum subset with the highest discerning power between IgAN and non-IgAN cases in China based on 36 biochemical indicators connected with a feature-selection procedure. Results: Our analyses indicated 19 biochemical indicators with differential distributions between IgAN and non-IgAN cases, indicating their potential as classifiers. Further examination for the discerning power of all k-feature combinations indicated a 5-feature combination, ALB. +. CK. +. Cr. +. HDL. +. CA125. +. TB, which gave the best accuracy, 79.71%, in classifying all training data into the 2 subtypes of nephropathy. Moreover, two combinations, ALB. +. CK. +. AFP. +. AST and TP. +. Glu. +. DB. +. CH, were gender-specific, giving the best classification accuracies of 81.90% and 80.22% for male and female patients, respectively. These 3 classifiers achieved classification accuracies of 75.36%, 72.00% and 84.09% in the entire, the male and the female independently validated datasets, respectively. Conclusions: Blood biochemical indicators could distinguish between IgAN and non-IgAN cases with a bioinformatic algorithm, providing a promising method to diagnose the subtypes of nephropathy.

Original languageEnglish (US)
Pages (from-to)441-445
Number of pages5
JournalClinica Chimica Acta
Volume412
Issue number5-6
DOIs
StatePublished - Feb 20 2011
Externally publishedYes

Fingerprint

IGA Glomerulonephritis
Immunoglobulin A
Blood
Classifiers
China
Bioinformatics
Glomerulonephritis
Computational Biology
Support vector machines
Feature extraction
Retrospective Studies

Keywords

  • Biochemical indicator
  • Exhaustive search
  • IgA nephropathy

ASJC Scopus subject areas

  • Biochemistry
  • Clinical Biochemistry
  • Biochemistry, medical

Cite this

Identification of potential predictors for subtype IgA nephropathy through analyses of blood biochemical indicators. / Gao, Jing; Cui, Juan; Wang, Yong; Dong, Zhennan; Tian, Yaping; Xu, Ying.

In: Clinica Chimica Acta, Vol. 412, No. 5-6, 20.02.2011, p. 441-445.

Research output: Contribution to journalArticle

Gao, Jing ; Cui, Juan ; Wang, Yong ; Dong, Zhennan ; Tian, Yaping ; Xu, Ying. / Identification of potential predictors for subtype IgA nephropathy through analyses of blood biochemical indicators. In: Clinica Chimica Acta. 2011 ; Vol. 412, No. 5-6. pp. 441-445.
@article{9e2309a0ac2f4bf4b0af663cf1c22d6a,
title = "Identification of potential predictors for subtype IgA nephropathy through analyses of blood biochemical indicators",
abstract = "Background: Immunoglobulin A nephropathy (IgAN), a dominant glomerulonephritis in China, has presented challenges in its early non-invasive diagnosis and accordingly has drawn considerable attention regarding the need to develop effective easy-to-conduct methods. Methods: In this retrospective study, a support vector machine-based classifier was trained to obtain a minimum subset with the highest discerning power between IgAN and non-IgAN cases in China based on 36 biochemical indicators connected with a feature-selection procedure. Results: Our analyses indicated 19 biochemical indicators with differential distributions between IgAN and non-IgAN cases, indicating their potential as classifiers. Further examination for the discerning power of all k-feature combinations indicated a 5-feature combination, ALB. +. CK. +. Cr. +. HDL. +. CA125. +. TB, which gave the best accuracy, 79.71{\%}, in classifying all training data into the 2 subtypes of nephropathy. Moreover, two combinations, ALB. +. CK. +. AFP. +. AST and TP. +. Glu. +. DB. +. CH, were gender-specific, giving the best classification accuracies of 81.90{\%} and 80.22{\%} for male and female patients, respectively. These 3 classifiers achieved classification accuracies of 75.36{\%}, 72.00{\%} and 84.09{\%} in the entire, the male and the female independently validated datasets, respectively. Conclusions: Blood biochemical indicators could distinguish between IgAN and non-IgAN cases with a bioinformatic algorithm, providing a promising method to diagnose the subtypes of nephropathy.",
keywords = "Biochemical indicator, Exhaustive search, IgA nephropathy",
author = "Jing Gao and Juan Cui and Yong Wang and Zhennan Dong and Yaping Tian and Ying Xu",
year = "2011",
month = "2",
day = "20",
doi = "10.1016/j.cca.2010.11.020",
language = "English (US)",
volume = "412",
pages = "441--445",
journal = "Clinica Chimica Acta",
issn = "0009-8981",
publisher = "Elsevier",
number = "5-6",

}

TY - JOUR

T1 - Identification of potential predictors for subtype IgA nephropathy through analyses of blood biochemical indicators

AU - Gao, Jing

AU - Cui, Juan

AU - Wang, Yong

AU - Dong, Zhennan

AU - Tian, Yaping

AU - Xu, Ying

PY - 2011/2/20

Y1 - 2011/2/20

N2 - Background: Immunoglobulin A nephropathy (IgAN), a dominant glomerulonephritis in China, has presented challenges in its early non-invasive diagnosis and accordingly has drawn considerable attention regarding the need to develop effective easy-to-conduct methods. Methods: In this retrospective study, a support vector machine-based classifier was trained to obtain a minimum subset with the highest discerning power between IgAN and non-IgAN cases in China based on 36 biochemical indicators connected with a feature-selection procedure. Results: Our analyses indicated 19 biochemical indicators with differential distributions between IgAN and non-IgAN cases, indicating their potential as classifiers. Further examination for the discerning power of all k-feature combinations indicated a 5-feature combination, ALB. +. CK. +. Cr. +. HDL. +. CA125. +. TB, which gave the best accuracy, 79.71%, in classifying all training data into the 2 subtypes of nephropathy. Moreover, two combinations, ALB. +. CK. +. AFP. +. AST and TP. +. Glu. +. DB. +. CH, were gender-specific, giving the best classification accuracies of 81.90% and 80.22% for male and female patients, respectively. These 3 classifiers achieved classification accuracies of 75.36%, 72.00% and 84.09% in the entire, the male and the female independently validated datasets, respectively. Conclusions: Blood biochemical indicators could distinguish between IgAN and non-IgAN cases with a bioinformatic algorithm, providing a promising method to diagnose the subtypes of nephropathy.

AB - Background: Immunoglobulin A nephropathy (IgAN), a dominant glomerulonephritis in China, has presented challenges in its early non-invasive diagnosis and accordingly has drawn considerable attention regarding the need to develop effective easy-to-conduct methods. Methods: In this retrospective study, a support vector machine-based classifier was trained to obtain a minimum subset with the highest discerning power between IgAN and non-IgAN cases in China based on 36 biochemical indicators connected with a feature-selection procedure. Results: Our analyses indicated 19 biochemical indicators with differential distributions between IgAN and non-IgAN cases, indicating their potential as classifiers. Further examination for the discerning power of all k-feature combinations indicated a 5-feature combination, ALB. +. CK. +. Cr. +. HDL. +. CA125. +. TB, which gave the best accuracy, 79.71%, in classifying all training data into the 2 subtypes of nephropathy. Moreover, two combinations, ALB. +. CK. +. AFP. +. AST and TP. +. Glu. +. DB. +. CH, were gender-specific, giving the best classification accuracies of 81.90% and 80.22% for male and female patients, respectively. These 3 classifiers achieved classification accuracies of 75.36%, 72.00% and 84.09% in the entire, the male and the female independently validated datasets, respectively. Conclusions: Blood biochemical indicators could distinguish between IgAN and non-IgAN cases with a bioinformatic algorithm, providing a promising method to diagnose the subtypes of nephropathy.

KW - Biochemical indicator

KW - Exhaustive search

KW - IgA nephropathy

UR - http://www.scopus.com/inward/record.url?scp=78650865289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650865289&partnerID=8YFLogxK

U2 - 10.1016/j.cca.2010.11.020

DO - 10.1016/j.cca.2010.11.020

M3 - Article

C2 - 21112320

AN - SCOPUS:78650865289

VL - 412

SP - 441

EP - 445

JO - Clinica Chimica Acta

JF - Clinica Chimica Acta

SN - 0009-8981

IS - 5-6

ER -