Machine Learning Models and Statistical Measures for Predicting the Progression of IgA Nephropathy

Junhyug Noh; Dharani Punithan; Hajeong Lee; Jungpyo Lee; Yonsu Kim; Dongki Kim; Ri Bob McKay

doi:10.1142/S0218194015400227

Machine Learning Models and Statistical Measures for Predicting the Progression of IgA Nephropathy

Junhyug Noh, Dharani Punithan^*, Hajeong Lee, Jungpyo Lee, Yonsu Kim, Dongki Kim, Ri Bob McKay

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

We predict the progression of Immunoglobulin A Nephropathy using three classification methods: Classification and Regression Trees, Logistic Regression, and Feed-Forward Artificial Neural Networks. We treat it as a classification problem, of predicting progression to end-stage renal disease in the ten years following initial diagnosis. We compared classifier performance using ROC analysis. All three methods yielded good classifiers, with AUC between 0.85 and 0.95. The results were generally in-line with expectations, with poor kidney performance on presentation, and evident macroscopic and microscopic damage, all associated with poorer prognosis.

Original language	English
Pages (from-to)	829-849
Number of pages	21
Journal	International Journal of Software Engineering and Knowledge Engineering
Volume	25
Issue number	5
DOIs	https://doi.org/10.1142/S0218194015400227
Publication status	Published - 30 Jun 2015
Externally published	Yes

Access to Document

10.1142/S0218194015400227

Cite this

@article{24bde0c16a6f470aaf72692d31fcc75b,

title = "Machine Learning Models and Statistical Measures for Predicting the Progression of IgA Nephropathy",

abstract = "We predict the progression of Immunoglobulin A Nephropathy using three classification methods: Classification and Regression Trees, Logistic Regression, and Feed-Forward Artificial Neural Networks. We treat it as a classification problem, of predicting progression to end-stage renal disease in the ten years following initial diagnosis. We compared classifier performance using ROC analysis. All three methods yielded good classifiers, with AUC between 0.85 and 0.95. The results were generally in-line with expectations, with poor kidney performance on presentation, and evident macroscopic and microscopic damage, all associated with poorer prognosis.",

keywords = "Area Under Curve (AUC), Classification and Regression Trees (CART), Closest-Top-Left (CTL), End-Stage Renal Disease (ESRD), Immunoglobulin A Nephropathy (IgAN), Logistic Regression, Missing Completely At Random (MCAR), Neural Networks, Receiver Operating Characteristic (ROC), Youden's index",

author = "Junhyug Noh and Dharani Punithan and Hajeong Lee and Jungpyo Lee and Yonsu Kim and Dongki Kim and McKay, {Ri Bob}",

note = "Publisher Copyright: {\textcopyright} 2015 World Scientific Publishing Company.",

year = "2015",

month = jun,

day = "30",

doi = "10.1142/S0218194015400227",

language = "English",

volume = "25",

pages = "829--849",

journal = "International Journal of Software Engineering and Knowledge Engineering",

issn = "0218-1940",

publisher = "World Scientific Publishing Co. Pte Ltd",

number = "5",

}

TY - JOUR

T1 - Machine Learning Models and Statistical Measures for Predicting the Progression of IgA Nephropathy

AU - Noh, Junhyug

AU - Punithan, Dharani

AU - Lee, Hajeong

AU - Lee, Jungpyo

AU - Kim, Yonsu

AU - Kim, Dongki

AU - McKay, Ri Bob

PY - 2015/6/30

Y1 - 2015/6/30

N2 - We predict the progression of Immunoglobulin A Nephropathy using three classification methods: Classification and Regression Trees, Logistic Regression, and Feed-Forward Artificial Neural Networks. We treat it as a classification problem, of predicting progression to end-stage renal disease in the ten years following initial diagnosis. We compared classifier performance using ROC analysis. All three methods yielded good classifiers, with AUC between 0.85 and 0.95. The results were generally in-line with expectations, with poor kidney performance on presentation, and evident macroscopic and microscopic damage, all associated with poorer prognosis.

AB - We predict the progression of Immunoglobulin A Nephropathy using three classification methods: Classification and Regression Trees, Logistic Regression, and Feed-Forward Artificial Neural Networks. We treat it as a classification problem, of predicting progression to end-stage renal disease in the ten years following initial diagnosis. We compared classifier performance using ROC analysis. All three methods yielded good classifiers, with AUC between 0.85 and 0.95. The results were generally in-line with expectations, with poor kidney performance on presentation, and evident macroscopic and microscopic damage, all associated with poorer prognosis.

KW - Area Under Curve (AUC)

KW - Classification and Regression Trees (CART)

KW - Closest-Top-Left (CTL)

KW - End-Stage Renal Disease (ESRD)

KW - Immunoglobulin A Nephropathy (IgAN)

KW - Logistic Regression

KW - Missing Completely At Random (MCAR)

KW - Neural Networks

KW - Receiver Operating Characteristic (ROC)

KW - Youden's index

UR - http://www.scopus.com/inward/record.url?scp=84942581596&partnerID=8YFLogxK

U2 - 10.1142/S0218194015400227

DO - 10.1142/S0218194015400227

M3 - Article

SN - 0218-1940

VL - 25

SP - 829

EP - 849

JO - International Journal of Software Engineering and Knowledge Engineering

JF - International Journal of Software Engineering and Knowledge Engineering

IS - 5

ER -

Machine Learning Models and Statistical Measures for Predicting the Progression of IgA Nephropathy

Abstract

Access to Document

Other files and links

Fingerprint

Cite this