Social determinants of health and premature death among adults in the USA from 1999 to 2018: a national cohort study

Abstract

Background: Racial and ethnic disparities in mortality persist in the US population. We studied the contribution of social determinants of health (SDoH) to racial and ethnic disparities in premature death.

Methods: A nationally representative sample of individuals aged 20-74 years who participated in the US National Health and Nutrition Examination Survey (NHANES) between 1999 and 2018 were included. Self-reported SDoH (employment, family income, food security, education, access to health care, health insurance, housing instability, and being married or living with a partner) were collected in each survey cycle. Participants were categorised into four groups of race and ethnicity: Black, Hispanic, White, and other. Deaths were ascertained from linkage to the National Death Index with follow-up until 2019. Multiple mediation analysis was used to assess simultaneous contributions of each individual SDoH to racial disparities in premature all-cause mortality.

Findings: We included 48 170 NHANES participants in our analyses, consisting of 10 543 (21·9%) Black participants, 13 211 (27·4%) Hispanic participants, 19 629 (40·7%) White participants, and 4787 (9·9%) participants of other racial and ethnic groups. Mean survey-weighted age was 44·3 years (95% CI 44·0-44·6), 51·3% (50·9-51·8) of participants were women, and 48·7% (48·2-49·1) were men. 3194 deaths before age 75 years were recorded (930 Black participants, 662 Hispanic participants, 1453 White participants, and 149 other participants). Black adults had significantly higher premature mortality than other racial and ethnic groups (p<0·0001): premature death rates per 100 000 person-years were 852 (95% CI 727-1000) for Black adults, 445 (349-574) for Hispanic adults, 546 (474-630) for White adults, and 521 (336-821) for other adults. Unemployment, lower family income, food insecurity, less than high school education, no private health insurance, and not being married nor living with a partner were significantly and independently associated with premature death. Dose-response associations were observed between cumulative number of unfavourable SDoH and premature all-cause mortality: hazard ratios (HRs) were 1·93 (95% CI 1·61-2·31) for those with one unfavourable SDoH, 2·24 (1·87-2·68) for those with two, 3·98 (3·34-4·73) for those with three, 4·78 (3·98-5·74) for those with four, 6·08 (5·06-7·31) for those with five, and 7·82 (6·60-9·26) for those with six or more unfavourable SDoH (p<0·0001 for linear trend). After adjusting for SDoH, HRs for premature all-cause mortality for Black adults compared with White adults decreased from 1·59 (1·44-1·76) to 1·00 (0·91-1·10), suggesting complete mediation of this racial difference in mortality.

Interpretation: Unfavourable SDoH are associated with increased rates of premature death and contribute to differences between Black and White racial groups in premature all-cause mortality in the US population. Innovative public health policies and interventions targeting SDoH are needed to reduce premature deaths and health disparities in this population.

Funding: US National Institutes of Health.

Figure 1:. Premature all-cause mortality in US adults aged 20–74 years by gender and race and ethnicity

Kaplan-Meier curves show cumulative mortality by age and race and ethnicity. Numbers at risk are unweighted observed frequencies. Cumulative mortality rates were estimated with use of imputation-adjusted survey weights. Bar chart shows age-gender-adjusted deaths per 100 000 person-years (standardised to the 2010 US Census population) by race and ethnicity; error bars are 95% CIs.

Figure 2:. Premature all-cause mortality and HRs in US adults aged 20–74 years according to the number of unfavourable SDoH

Kaplan-Meier curves show cumulative mortality by age and number of unfavourable SDoH. Numbers at risk are unweighted observed frequencies. Cumulative mortality rates were estimated with use of imputation-adjusted survey weights. Bar chart shows HRs of premature all-cause mortality associated with number of unfavourable SDoH, adjusted for age, gender, and race and ethnicity; error bars are 95% CIs. HR=hazard ratio. SDoH=social determinants of health.