Exploring racial disparity in obesity: A mediation analysis considering geo-coded environmental factors

Yu, Qingzhao; Scribner, Richard; Leonardi, Claudia; Zhang, Lu; Park, Chi; Chen, Liwei; Simonsen, Neal

doi:10.1016/j.sste.2017.02.001

Cited by 38 publications

(30 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 Rural Blacks have lower SES 14 and life expectancy 13 than both rural Whites and urban Blacks. Rural Blacks also have higher rates of the same chronic diseases that increase the risk of death should one contract COVID-19 (heart disease, diabetes, and respiratory diseases) [15][16][17][18][19][20] and shamefully low access to health care. 21,22 Blacks are also more likely to work in service occupations that require face-to-face contact with customers 23 and are more likely than Whites to live in multigenerational homes and with extended kin, 24 conditions that reduce the ability to socially distance and increase the risk of disease transmission.…”

mentioning

confidence: 99%

COVID‐19 Death Rates Are Higher in Rural Counties With Larger Shares of Blacks and Hispanics

Cheng

Sun

Monnat

2020

The Journal of Rural Health

113

109

View full text Add to dashboard Cite

This study compared the average daily increase in COVID-19 mortality rates by county racial/ethnic composition (percent non-Hispanic Black and percent Hispanic) among US rural counties. Methods: COVID-19 daily death counts for 1,976 US nonmetropolitan counties for the period March 2-July 26, 2020, were extracted from USAFacts and merged with county-level American Community Survey and Area Health Resource File data. Covariates included county percent poverty, age composition, adjacency to a metropolitan county, health care supply, and state fixed effects. Mixed-effects negative binomial regression with random intercepts to account for repeated observations within counties were used to predict differences in the average daily increase in the COVID-19 mortality rate across quartiles of percent Black and percent Hispanic. Findings: Since early March, the average daily increase in the COVID-19 mortality rate has been significantly higher in rural counties with the highest percent Black and percent Hispanic populations. Compared to counties in the bottom quartile, counties in the top quartile of percent Black have an average daily increase that is 70% higher (IRR = 1.70, CI: 1.48-1.95, P < .001), and counties in the top quartile of percent Hispanic have an average daily increase that is 50% higher (IRR = 1.50, CI: 1.33-1.69, P < .001), net of covariates. Conclusion: COVID-19 mortality risk is not distributed equally across the rural United States, and the COVID-19 race penalty is not restricted to cities. Among rural counties, the average daily increase in COVID-19 mortality rates has been significantly higher in counties with the largest shares of Black and Hispanic residents.

show abstract

mentioning

confidence: 99%

COVID‐19 Death Rates Are Higher in Rural Counties With Larger Shares of Blacks and Hispanics

Cheng

Sun

Monnat

2020

The Journal of Rural Health

113

109

View full text Add to dashboard Cite

show abstract

“…They also established the relationship between the proposed definitions of direct or indirect effect and the natural direct or indirect effect for binary exposure variables. Later, the definitions have been implemented to explore racial and ethnic health disparities by [ 19 , 20 ] and extended to deal with time-to-event outcomes ([ 21 ]) and for multiple exposures and multivariate outcomes ([ 22 ]). In this paper, we extend the method to the context of multilevel models.…”

Section: Third-variable Analysis With Multilevel Additive Modelsmentioning

confidence: 99%

“…Finally, we implement the method in a real data example: to explore the racial disparity in body mass index (BMI). In a previous research, we found that on average, non-Hispanic blacks have a higher BMI and higher rate of obesity compared with non-Hispanic whites [ 19 , 22 ] using the 2003-2006 National Health and Nutrition Examination Survey (NHANES). We are interested to see how the disparities can be explained by both individual and environmental factors.…”

Section: Explore the Racial Disparity In Obesitymentioning

confidence: 99%

See 1 more Smart Citation

Third-variable effect analysis with multilevel additive models

2020

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Third-variable effect refers to the effect transmitted by third-variables that intervene in the relationship between an exposure and a response variable. Third-variable effect analysis has been broadly studied in many fields. However, it remains a challenge for researchers to differentiate indirect effect of individual factor from multiple third-variables, especially when the involving variables are of hierarchical structure. Yu et al. (2014) defined third-variable effects that were consistent for all different types of response (categorical or continuous), exposure, or third-variables. With these definitions, multiple third-variables can be considered simultaneously, and the indirect effects carried by individual third-variables can be separated from the total effect. In this paper, we extend the definitions of third-variable effects to multilevel data structures, where multilevel additive models are adapted to model the variable relationships. And then third-variable effects can be estimated at different levels. Moreover, transformations on variables are allowed to present nonlinear relationships among variables. We compile an R package mlma , to carry out the proposed multilevel third-variable analysis. Simulations show that the proposed method can effectively differentiate and estimate third-variable effects from different levels. Further, we implement the method to explore the racial disparity in body mass index accounting for both environmental and individual level risk factors.

show abstract

“…It was first necessary to determine whether the ML models were adequately calibrated in 'test' cohorts different from the ML modeldiscovery 'training' cohorts. Controlling for age distribution, geographic differences, gender, common contraindications for the treatment-of-interest (discharge beta-blocker post-CAB), and other factors [34][35][36][37][38][39][40][41][42] is important, to insure adequate statistical power for these assessments and to mitigate confounding [27,43]. Establishing that the ML model was adequately well-calibrated for each racial group prior to performing procedures to evaluate the presence of discrimination or disparities was performed using the Hosmer-Lemeshow test by model score deciles.…”

Section: Evaluation Approachmentioning

confidence: 99%

Preventing Disparities: Bayesian and Frequentist Methods for Assessing Fairness in Machine-Learning Decision-Support Models

McNair¹

2018

New Insights Into Bayesian Inference

View full text Add to dashboard Cite

Machine-learning (ML) methods are finding increasing application to guide human decision-making in many fields. Such guidance can have important consequences, including treatments and outcomes in health care. Recently, growing attention has focused on the potential that machine-learning might automatically learn unjust or discriminatory, but unrecognized or undisclosed, patterns that are manifested in available observational data and the human processes that gave rise to them, and thereby inadvertently perpetuating and propagating injustices that are embodied in the historical data. We applied two frequentist methods that have long been utilized in the courts and elsewhere for the purpose of ascertaining fairness (Cochran-Mantel-Haenszel test and beta regression) and one Bayesian method (Bayesian Model Averaging). These methods revealed that our ML model for guiding physicians' prescribing discharge beta-blocker medication for post-coronary artery bypass patients do not manifest significant untoward race-associated disparity. The methods also showed that our ML model for directing repeat performance of MRI imaging in children with medulloblastoma did manifest racial disparities that are likely associated with ethnic differences in informed consent and desire for information in the context of serious malignancies. The relevance of these methods to ascertaining and assuring fairness in other ML-based decision-support model-development and-curation contexts is discussed.

show abstract

Exploring racial disparity in obesity: A mediation analysis considering geo-coded environmental factors

Cited by 38 publications

References 38 publications

COVID‐19 Death Rates Are Higher in Rural Counties With Larger Shares of Blacks and Hispanics

COVID‐19 Death Rates Are Higher in Rural Counties With Larger Shares of Blacks and Hispanics

Third-variable effect analysis with multilevel additive models

Preventing Disparities: Bayesian and Frequentist Methods for Assessing Fairness in Machine-Learning Decision-Support Models

Contact Info

Product

Resources

About