The color of death: race, observed skin tone, and all-cause mortality in the United States

Stewart, Quincy Thomas; Cobb, Ryon J.; Keith, Verna M.

doi:10.1080/13557858.2018.1469735

Cited by 28 publications

(16 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, we note skin tone was determined to be an important predictor of all-cause mortality in the random forest algorithms. This is interestingly supported by a US study on the spectrum of skin tone and mortality [27]. Both residential air pollution and exposure to hazardous materials, consistent with findings from China [28] and Europe [29], are important variables in the deep learning model.…”

Section: Discussionsupporting

confidence: 68%

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches

et al. 2019

View full text Add to dashboard Cite

Background Prognostic modelling using standard methods is well-established, particularly for predicting risk of single diseases. Machine-learning may offer potential to explore outcomes of even greater complexity, such as premature death. This study aimed to develop novel prediction algorithms using machine-learning, in addition to standard survival modelling, to predict premature all-cause mortality. Methods A prospective population cohort of 502,628 participants aged 40–69 years were recruited to the UK Biobank from 2006–2010 and followed-up until 2016. Participants were assessed on a range of demographic, biometric, clinical and lifestyle factors. Mortality data by ICD-10 were obtained from linkage to Office of National Statistics. Models were developed using deep learning, random forest and Cox regression. Calibration was assessed by comparing observed to predicted risks; and discrimination by area under the ‘receiver operating curve’ (AUC). Findings 14,418 deaths (2.9%) occurred over a total follow-up time of 3,508,454 person-years. A simple age and gender Cox model was the least predictive (AUC 0.689, 95% CI 0.681–0.699). A multivariate Cox regression model significantly improved discrimination by 6.2% (AUC 0.751, 95% CI 0.748–0.767). The application of machine-learning algorithms further improved discrimination by 3.2% using random forest (AUC 0.783, 95% CI 0.776–0.791) and 3.9% using deep learning (AUC 0.790, 95% CI 0.783–0.797). These ML algorithms improved discrimination by 9.4% and 10.1% respectively from a simple age and gender Cox regression model. Random forest and deep learning achieved similar levels of discrimination with no significant difference. Machine-learning algorithms were well-calibrated, while Cox regression models consistently over-predicted risk. Conclusions Machine-learning significantly improved accuracy of prediction of premature all-cause mortality in this middle-aged population, compared to standard methods. This study illustrates the value of machine-learning for risk prediction within a traditional epidemiological study design, and how this approach might be reported to assist scientific verification.

show abstract

Section: Discussionsupporting

confidence: 68%

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches

et al. 2019

View full text Add to dashboard Cite

show abstract

“…There are also associations between skin tone and physical-health outcomes such as hypertension (Klag, Wheton, Coresh, Grim, & Kuller, 1991; Klonoff & Landrine, 2000; Sweet, McDade, Kiefe, & Liu, 2007; Tyroler & James, 1978) and mortality (Knap et al, 1995; Stewart, Cobb, & Keith, 2018). Klonoff and Landrine (2000) investigated darker complexioned individuals’ rates of hypertension and found that darker skinned African Americans are more likely to experience racist events and are more likely to develop hypertension.…”

Section: Skin-tone Traumamentioning

confidence: 99%

Skin-Tone Trauma: Historical and Contemporary Influences on the Health and Interpersonal Outcomes of African Americans

Landor

Smith

2019

Perspect Psychol Sci

View full text Add to dashboard Cite

Empirical evidence demonstrates that racism is a source of traumatic stress for racial/ethnic minorities, particularly African Americans. Like race and racism, skin tone and experiences of colorism—an often overlooked form of discrimination that privileges lighter skinned over darker skinned individuals, although not uniformly, may also result in traumatic stress. This article proposes a new conceptual model of skin-tone trauma. The model depicts how historical and contemporary underpinnings of colorism lead to colorist incidents that may directly and indirectly, by eliciting traumatic stress reactions, lead to negative effects on the health and interpersonal relationships of African Americans. Key tenets of critical race and intersectionality theories are used to highlight the complexities of skin-tone trauma as a result of intersectional identities on the basis of existing social hierarchies. Last, we present suggestions for researchers, as well as recommendations and strategies for practitioners, to unmask “skin-tone wounds” and promote healing for individuals, families, and communities that suffer from skin-tone trauma. Skin-tone trauma should be acknowledged by researchers, scholars, and practitioners to better understand and assess the widespread scope of trauma in the African American community.

show abstract

“…The GSS is a veritable goldmine for population health researchers because it contains variables not available in any other dataset. The GSS-NDI has been used in studies linking social characteristics such as exposure to individual-and institutional-level discrimination, sexual minority status, happiness, political ideology, emotion suppression, observed skin tone, and other statuses, attitudes, and behaviors with adult mortality risk (Chapman et al 2013;Lawrence et al 2015;Lee et al 2015;Morey et al 2018;Muennig et al 2013;Pabayo et al 2015;Stewart et al 2018). Researchers could not have established these associations with any other nationally-representative datasets.…”

Section: Survey-linked Mortality Filesmentioning

confidence: 99%

Comparability of Mortality Estimates from Social Surveys and Vital Statistics Data in the United States

Brown

Lariscy

Kalousová

2018

Popul Res Policy Rev

View full text Add to dashboard Cite

Social surveys prospectively linked with death records provide invaluable opportunities for the study of the relationship between social and economic circumstances and mortality. Although survey-linked mortality files play a prominent role in U.S. health disparities research, it is unclear how well mortality estimates from these datasets align with one another and whether they are comparable with U.S. vital statistics data. We conduct the first study that systematically compares mortality estimates from several widely-used survey-linked mortality files and U.S. vital statistics data. Our results show that mortality rates and life expectancies from the National Health Interview Survey Linked Mortality Files, Health and Retirement Study, Americans' Changing Lives study, and U.S. vital statistics data are similar. Mortality rates are slightly lower and life expectancies are slightly higher in these linked datasets relative to vital statistics data. Compared with vital statistics and other survey-linked datasets, General Social Survey-National Death Index life expectancy estimates are much lower at younger adult ages and much higher at older adult ages. Cox proportional hazard models regressing all-cause mortality risk on age, gender, race, educational attainment, and marital status conceal the issues with the General Social Survey-National Death Index that are observed in our comparison of absolute measures of mortality risk. We provide recommendations for researchers who use survey-linked mortality files.

show abstract

The color of death: race, observed skin tone, and all-cause mortality in the United States

Cited by 28 publications

References 77 publications

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches

Prediction of premature all-cause mortality: A prospective general population cohort study comparing machine-learning and standard epidemiological approaches

Skin-Tone Trauma: Historical and Contemporary Influences on the Health and Interpersonal Outcomes of African Americans

Comparability of Mortality Estimates from Social Surveys and Vital Statistics Data in the United States

Contact Info

Product

Resources

About