Machine learning to compare frequent medical problems of African American and caucasian diabetic kidney patients

Yong Mi Kim, Pranay Kathuria, Dursun Delen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objectives: End-stage renal disease (ESRD), which is primarily a consequence of diabetes mellitus, shows an exemplary health disparity between African American and Caucasian patients in the United States. Because diabetic chronic kidney disease (CKD) patients of these two groups show differences in their medical problems, the markers leading to ESRD are also expected to differ. The purpose of this study was, therefore, to compare their medical complications at various levels of kidney function and to identify markers that can be used to predict ESRD. Methods: The data of type 2 diabetic patients was obtained from the 2012 Cerner database, which totaled 1,038,499 records. The data was then filtered to include only African American and Caucasian outpatients with estimated glomerular filtration rates (eGFR), leaving 4,623 records. A priori machine learning was used to discover frequently appearing medical problems within the filtered data. CKD is defined as abnormalities of kidney structure, present for >3 months. Results: This study found that African Americans have much higher rates of CKDrelated medical problems than Caucasians for all five stages, and prominent markers leading to ESRD were discovered only for the African American group. These markers are high glucose, high systolic blood pressure (BP), obesity, alcohol/drug use, and low hematocrit. Additionally, the roles of systolic BP and diastolic BP vary depending on the CKD stage. Conclusions: This research discovered frequently appearing medical problems across five stages of CKD and further showed that many of the markers reported in previous studies are more applicable to African American patients than Caucasian patients.

Original languageEnglish
Pages (from-to)241-248
Number of pages8
JournalHealthcare Informatics Research
Volume23
Issue number4
DOIs
StatePublished - 1 Oct 2017
Externally publishedYes

Fingerprint

Medical problems
African Americans
Learning systems
Chronic Renal Insufficiency
Chronic Kidney Failure
Blood Pressure
Kidney
Blood pressure
Diabetic Nephropathies
Glomerular Filtration Rate
Hematocrit
Diabetes Mellitus
Outpatients
Obesity
Alcohols
Machine Learning
Databases
Hypertension
Glucose
Health

Keywords

  • Electronic health records
  • Glomerular filtration rate
  • Kidney failure
  • Machine learning
  • Renal insufficiency

Cite this

@article{39dcf40dd37b4cfdb93ed2d22c19e1ee,
title = "Machine learning to compare frequent medical problems of African American and caucasian diabetic kidney patients",
abstract = "Objectives: End-stage renal disease (ESRD), which is primarily a consequence of diabetes mellitus, shows an exemplary health disparity between African American and Caucasian patients in the United States. Because diabetic chronic kidney disease (CKD) patients of these two groups show differences in their medical problems, the markers leading to ESRD are also expected to differ. The purpose of this study was, therefore, to compare their medical complications at various levels of kidney function and to identify markers that can be used to predict ESRD. Methods: The data of type 2 diabetic patients was obtained from the 2012 Cerner database, which totaled 1,038,499 records. The data was then filtered to include only African American and Caucasian outpatients with estimated glomerular filtration rates (eGFR), leaving 4,623 records. A priori machine learning was used to discover frequently appearing medical problems within the filtered data. CKD is defined as abnormalities of kidney structure, present for >3 months. Results: This study found that African Americans have much higher rates of CKDrelated medical problems than Caucasians for all five stages, and prominent markers leading to ESRD were discovered only for the African American group. These markers are high glucose, high systolic blood pressure (BP), obesity, alcohol/drug use, and low hematocrit. Additionally, the roles of systolic BP and diastolic BP vary depending on the CKD stage. Conclusions: This research discovered frequently appearing medical problems across five stages of CKD and further showed that many of the markers reported in previous studies are more applicable to African American patients than Caucasian patients.",
keywords = "Electronic health records, Glomerular filtration rate, Kidney failure, Machine learning, Renal insufficiency",
author = "Kim, {Yong Mi} and Pranay Kathuria and Dursun Delen",
year = "2017",
month = "10",
day = "1",
doi = "10.4258/hir.2017.23.4.241",
language = "English",
volume = "23",
pages = "241--248",
journal = "Healthcare Informatics Research",
issn = "2093-3681",
publisher = "Korean Society of Medical Informatics",
number = "4",

}

Machine learning to compare frequent medical problems of African American and caucasian diabetic kidney patients. / Kim, Yong Mi; Kathuria, Pranay; Delen, Dursun.

In: Healthcare Informatics Research, Vol. 23, No. 4, 01.10.2017, p. 241-248.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning to compare frequent medical problems of African American and caucasian diabetic kidney patients

AU - Kim, Yong Mi

AU - Kathuria, Pranay

AU - Delen, Dursun

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Objectives: End-stage renal disease (ESRD), which is primarily a consequence of diabetes mellitus, shows an exemplary health disparity between African American and Caucasian patients in the United States. Because diabetic chronic kidney disease (CKD) patients of these two groups show differences in their medical problems, the markers leading to ESRD are also expected to differ. The purpose of this study was, therefore, to compare their medical complications at various levels of kidney function and to identify markers that can be used to predict ESRD. Methods: The data of type 2 diabetic patients was obtained from the 2012 Cerner database, which totaled 1,038,499 records. The data was then filtered to include only African American and Caucasian outpatients with estimated glomerular filtration rates (eGFR), leaving 4,623 records. A priori machine learning was used to discover frequently appearing medical problems within the filtered data. CKD is defined as abnormalities of kidney structure, present for >3 months. Results: This study found that African Americans have much higher rates of CKDrelated medical problems than Caucasians for all five stages, and prominent markers leading to ESRD were discovered only for the African American group. These markers are high glucose, high systolic blood pressure (BP), obesity, alcohol/drug use, and low hematocrit. Additionally, the roles of systolic BP and diastolic BP vary depending on the CKD stage. Conclusions: This research discovered frequently appearing medical problems across five stages of CKD and further showed that many of the markers reported in previous studies are more applicable to African American patients than Caucasian patients.

AB - Objectives: End-stage renal disease (ESRD), which is primarily a consequence of diabetes mellitus, shows an exemplary health disparity between African American and Caucasian patients in the United States. Because diabetic chronic kidney disease (CKD) patients of these two groups show differences in their medical problems, the markers leading to ESRD are also expected to differ. The purpose of this study was, therefore, to compare their medical complications at various levels of kidney function and to identify markers that can be used to predict ESRD. Methods: The data of type 2 diabetic patients was obtained from the 2012 Cerner database, which totaled 1,038,499 records. The data was then filtered to include only African American and Caucasian outpatients with estimated glomerular filtration rates (eGFR), leaving 4,623 records. A priori machine learning was used to discover frequently appearing medical problems within the filtered data. CKD is defined as abnormalities of kidney structure, present for >3 months. Results: This study found that African Americans have much higher rates of CKDrelated medical problems than Caucasians for all five stages, and prominent markers leading to ESRD were discovered only for the African American group. These markers are high glucose, high systolic blood pressure (BP), obesity, alcohol/drug use, and low hematocrit. Additionally, the roles of systolic BP and diastolic BP vary depending on the CKD stage. Conclusions: This research discovered frequently appearing medical problems across five stages of CKD and further showed that many of the markers reported in previous studies are more applicable to African American patients than Caucasian patients.

KW - Electronic health records

KW - Glomerular filtration rate

KW - Kidney failure

KW - Machine learning

KW - Renal insufficiency

UR - http://www.scopus.com/inward/record.url?scp=85045403316&partnerID=8YFLogxK

U2 - 10.4258/hir.2017.23.4.241

DO - 10.4258/hir.2017.23.4.241

M3 - Article

AN - SCOPUS:85045403316

VL - 23

SP - 241

EP - 248

JO - Healthcare Informatics Research

JF - Healthcare Informatics Research

SN - 2093-3681

IS - 4

ER -