A classification model to predict the rate of decline of kidney function

Ersoy Subasi; Munevver Mine Subasi; Peter L. Hammer; John Roboz; Michael Lipkowitz

A classification model to predict the rate of decline of kidney function

Ersoy Subasi, Munevver Mine Subasi, Peter L. Hammer, John Roboz, Michael Lipkowitz

Research output: Contribution to conference › Paper › peer-review

Abstract

The African American Study of Chronic Kidney Disease and Hypertension (AASK), a randomized double-blinded treatment trial, was motivated by the high rate of hypertension-related renal disease in the African American population and the scarcity of effective therapies. This study describes a pattern based classification approach to predict the rate of decline of kidney function and to differentiate between proteomic samples of rapid and slow progressors. An accurate classification model consisting of 7 out of 5,751 serum proteomic features is constructed by applying the Logical Analysis of Data (LAD) methodology. The LAD discriminant is used to identify the patients in different risk groups. The LAD risk scores assigned to 116 AASK outperforms the risk scores assigned by proteinuria, one of the best predictors of chronic kidney disease.

Original language	English
State	Published - 2016
Event	2016 International Symposium on Artificial Intelligence and Mathematics, ISAIM 2016 - Fort Lauderdale, United States Duration: 4 Jan 2016 → 6 Jan 2016

Conference

Conference	2016 International Symposium on Artificial Intelligence and Mathematics, ISAIM 2016
Country/Territory	United States
City	Fort Lauderdale
Period	4/01/16 → 6/01/16

Cite this

@conference{41640e1db7a24a57a258e3dfa44ad913,

title = "A classification model to predict the rate of decline of kidney function",

abstract = "The African American Study of Chronic Kidney Disease and Hypertension (AASK), a randomized double-blinded treatment trial, was motivated by the high rate of hypertension-related renal disease in the African American population and the scarcity of effective therapies. This study describes a pattern based classification approach to predict the rate of decline of kidney function and to differentiate between proteomic samples of rapid and slow progressors. An accurate classification model consisting of 7 out of 5,751 serum proteomic features is constructed by applying the Logical Analysis of Data (LAD) methodology. The LAD discriminant is used to identify the patients in different risk groups. The LAD risk scores assigned to 116 AASK outperforms the risk scores assigned by proteinuria, one of the best predictors of chronic kidney disease.",

author = "Ersoy Subasi and Subasi, {Munevver Mine} and Hammer, {Peter L.} and John Roboz and Michael Lipkowitz",

note = "Publisher Copyright: {\textcopyright} 2016 University of Virginia. All rights reserved.; 2016 International Symposium on Artificial Intelligence and Mathematics, ISAIM 2016 ; Conference date: 04-01-2016 Through 06-01-2016",

year = "2016",

language = "English",

}

TY - CONF

T1 - A classification model to predict the rate of decline of kidney function

AU - Subasi, Ersoy

AU - Subasi, Munevver Mine

AU - Hammer, Peter L.

AU - Roboz, John

AU - Lipkowitz, Michael

PY - 2016

Y1 - 2016

N2 - The African American Study of Chronic Kidney Disease and Hypertension (AASK), a randomized double-blinded treatment trial, was motivated by the high rate of hypertension-related renal disease in the African American population and the scarcity of effective therapies. This study describes a pattern based classification approach to predict the rate of decline of kidney function and to differentiate between proteomic samples of rapid and slow progressors. An accurate classification model consisting of 7 out of 5,751 serum proteomic features is constructed by applying the Logical Analysis of Data (LAD) methodology. The LAD discriminant is used to identify the patients in different risk groups. The LAD risk scores assigned to 116 AASK outperforms the risk scores assigned by proteinuria, one of the best predictors of chronic kidney disease.

AB - The African American Study of Chronic Kidney Disease and Hypertension (AASK), a randomized double-blinded treatment trial, was motivated by the high rate of hypertension-related renal disease in the African American population and the scarcity of effective therapies. This study describes a pattern based classification approach to predict the rate of decline of kidney function and to differentiate between proteomic samples of rapid and slow progressors. An accurate classification model consisting of 7 out of 5,751 serum proteomic features is constructed by applying the Logical Analysis of Data (LAD) methodology. The LAD discriminant is used to identify the patients in different risk groups. The LAD risk scores assigned to 116 AASK outperforms the risk scores assigned by proteinuria, one of the best predictors of chronic kidney disease.

UR - http://www.scopus.com/inward/record.url?scp=85083946960&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85083946960

T2 - 2016 International Symposium on Artificial Intelligence and Mathematics, ISAIM 2016

Y2 - 4 January 2016 through 6 January 2016

ER -

A classification model to predict the rate of decline of kidney function

Abstract

Conference

Fingerprint

Cite this