An exploratory decision tree analysis to predict cardiovascular disease risk in African American women

Heather J. Leach, Daniel P. O'Connor, Richard J. Simpson, Hanadi S. Rifai, Scherezade K. Mama, Rebecca Lee

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Objective: African American (AA) women are at greater risk for cardiovascular disease (CVD) compared to White women, which can be attributed to disparities in risk factors. The built environment may contribute to improving CVD risk factors by increasing physical activity (PA). This study used recursive partitioning, a multivariate decision tree risk classification approach, to determine which built environment characteristics contributed to the classification of AA women as having 4 or more CVD risk factors at optimal levels. Method: Recursive partitioning has the ability to detect interactions and does not have sample size limitations to detect effects. The Classification and Regression Trees (CR&T) growing method was used to group participants as having 4 or more versus 3 or fewer risk factors at optimal levels. Risk factors were smoking, body mass index (BMI), PA, healthy diet, cholesterol, glucose, and blood pressure. Built environment predictors were presence and quality of neighborhood PA resources (PARs), walkability, traffic safety, and crime. Results: Participants (N = 30, mean age of 54.1 ± 7.5) all had at least 1 risk factor at the optimal level, none had all 7, and 66.7% had 4 or more risk factors at optimal levels. The CR&T identified participants with few, low-quality neighborhood PARs and who were older than 55 as least likely to have 4 or more CVD risk factors at optimal levels. Conclusion: Being younger than 55 years old and having many, high-quality neighborhood PARs may predict lower risk for CVD in AA women. Results should be used in future studies with larger sample sizes to inform logistic regression models.

Original languageEnglish (US)
Pages (from-to)397-402
Number of pages6
JournalHealth Psychology
Volume35
Issue number4
DOIs
StatePublished - Apr 1 2016

Fingerprint

Decision Trees
Decision Support Techniques
African Americans
Cardiovascular Diseases
Exercise
Sample Size
Logistic Models
Aptitude
Crime
Body Mass Index
Smoking
Cholesterol
Blood Pressure
Safety
Glucose

Keywords

  • African American
  • Built environment
  • Cardiovascular disease risk
  • Physical activity
  • Women

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Applied Psychology

Cite this

An exploratory decision tree analysis to predict cardiovascular disease risk in African American women. / Leach, Heather J.; O'Connor, Daniel P.; Simpson, Richard J.; Rifai, Hanadi S.; Mama, Scherezade K.; Lee, Rebecca.

In: Health Psychology, Vol. 35, No. 4, 01.04.2016, p. 397-402.

Research output: Contribution to journalArticle

Leach, Heather J. ; O'Connor, Daniel P. ; Simpson, Richard J. ; Rifai, Hanadi S. ; Mama, Scherezade K. ; Lee, Rebecca. / An exploratory decision tree analysis to predict cardiovascular disease risk in African American women. In: Health Psychology. 2016 ; Vol. 35, No. 4. pp. 397-402.
@article{fe531ee5c57940dfb99724e86c24cdbb,
title = "An exploratory decision tree analysis to predict cardiovascular disease risk in African American women",
abstract = "Objective: African American (AA) women are at greater risk for cardiovascular disease (CVD) compared to White women, which can be attributed to disparities in risk factors. The built environment may contribute to improving CVD risk factors by increasing physical activity (PA). This study used recursive partitioning, a multivariate decision tree risk classification approach, to determine which built environment characteristics contributed to the classification of AA women as having 4 or more CVD risk factors at optimal levels. Method: Recursive partitioning has the ability to detect interactions and does not have sample size limitations to detect effects. The Classification and Regression Trees (CR&T) growing method was used to group participants as having 4 or more versus 3 or fewer risk factors at optimal levels. Risk factors were smoking, body mass index (BMI), PA, healthy diet, cholesterol, glucose, and blood pressure. Built environment predictors were presence and quality of neighborhood PA resources (PARs), walkability, traffic safety, and crime. Results: Participants (N = 30, mean age of 54.1 ± 7.5) all had at least 1 risk factor at the optimal level, none had all 7, and 66.7{\%} had 4 or more risk factors at optimal levels. The CR&T identified participants with few, low-quality neighborhood PARs and who were older than 55 as least likely to have 4 or more CVD risk factors at optimal levels. Conclusion: Being younger than 55 years old and having many, high-quality neighborhood PARs may predict lower risk for CVD in AA women. Results should be used in future studies with larger sample sizes to inform logistic regression models.",
keywords = "African American, Built environment, Cardiovascular disease risk, Physical activity, Women",
author = "Leach, {Heather J.} and O'Connor, {Daniel P.} and Simpson, {Richard J.} and Rifai, {Hanadi S.} and Mama, {Scherezade K.} and Rebecca Lee",
year = "2016",
month = "4",
day = "1",
doi = "10.1037/hea0000267",
language = "English (US)",
volume = "35",
pages = "397--402",
journal = "Health Psychology",
issn = "0278-6133",
publisher = "American Psychological Association Inc.",
number = "4",

}

TY - JOUR

T1 - An exploratory decision tree analysis to predict cardiovascular disease risk in African American women

AU - Leach, Heather J.

AU - O'Connor, Daniel P.

AU - Simpson, Richard J.

AU - Rifai, Hanadi S.

AU - Mama, Scherezade K.

AU - Lee, Rebecca

PY - 2016/4/1

Y1 - 2016/4/1

N2 - Objective: African American (AA) women are at greater risk for cardiovascular disease (CVD) compared to White women, which can be attributed to disparities in risk factors. The built environment may contribute to improving CVD risk factors by increasing physical activity (PA). This study used recursive partitioning, a multivariate decision tree risk classification approach, to determine which built environment characteristics contributed to the classification of AA women as having 4 or more CVD risk factors at optimal levels. Method: Recursive partitioning has the ability to detect interactions and does not have sample size limitations to detect effects. The Classification and Regression Trees (CR&T) growing method was used to group participants as having 4 or more versus 3 or fewer risk factors at optimal levels. Risk factors were smoking, body mass index (BMI), PA, healthy diet, cholesterol, glucose, and blood pressure. Built environment predictors were presence and quality of neighborhood PA resources (PARs), walkability, traffic safety, and crime. Results: Participants (N = 30, mean age of 54.1 ± 7.5) all had at least 1 risk factor at the optimal level, none had all 7, and 66.7% had 4 or more risk factors at optimal levels. The CR&T identified participants with few, low-quality neighborhood PARs and who were older than 55 as least likely to have 4 or more CVD risk factors at optimal levels. Conclusion: Being younger than 55 years old and having many, high-quality neighborhood PARs may predict lower risk for CVD in AA women. Results should be used in future studies with larger sample sizes to inform logistic regression models.

AB - Objective: African American (AA) women are at greater risk for cardiovascular disease (CVD) compared to White women, which can be attributed to disparities in risk factors. The built environment may contribute to improving CVD risk factors by increasing physical activity (PA). This study used recursive partitioning, a multivariate decision tree risk classification approach, to determine which built environment characteristics contributed to the classification of AA women as having 4 or more CVD risk factors at optimal levels. Method: Recursive partitioning has the ability to detect interactions and does not have sample size limitations to detect effects. The Classification and Regression Trees (CR&T) growing method was used to group participants as having 4 or more versus 3 or fewer risk factors at optimal levels. Risk factors were smoking, body mass index (BMI), PA, healthy diet, cholesterol, glucose, and blood pressure. Built environment predictors were presence and quality of neighborhood PA resources (PARs), walkability, traffic safety, and crime. Results: Participants (N = 30, mean age of 54.1 ± 7.5) all had at least 1 risk factor at the optimal level, none had all 7, and 66.7% had 4 or more risk factors at optimal levels. The CR&T identified participants with few, low-quality neighborhood PARs and who were older than 55 as least likely to have 4 or more CVD risk factors at optimal levels. Conclusion: Being younger than 55 years old and having many, high-quality neighborhood PARs may predict lower risk for CVD in AA women. Results should be used in future studies with larger sample sizes to inform logistic regression models.

KW - African American

KW - Built environment

KW - Cardiovascular disease risk

KW - Physical activity

KW - Women

UR - http://www.scopus.com/inward/record.url?scp=84963954531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963954531&partnerID=8YFLogxK

U2 - 10.1037/hea0000267

DO - 10.1037/hea0000267

M3 - Article

VL - 35

SP - 397

EP - 402

JO - Health Psychology

JF - Health Psychology

SN - 0278-6133

IS - 4

ER -