Individual-level Social Determinants Of Health Research Articles

Model-based estimation of individual-level social determinants of health and its applications in All of Us.

We introduce a widely applicable model-based approach for estimating individual-level Social Determinants of Health (SDoH) and evaluate its effectiveness using the All of Us Research Program. Our approach utilizes aggregated SDoH datasets to estimate individual-level SDoH, demonstrated with examples of no high school diploma (NOHSDP) and no health insurance (UNINSUR) variables. Models are estimated using American Community Survey data and applied to derive individual-level estimates for All of Us participants. We assess concordance between model-based SDoH estimates and self-reported SDoHs in All of Usand examine associations with undiagnosed hypertension and diabetes. Compared to self-reported SDoHs, the area under the curve for NOHSDP is 0.727 (95% CI, 0.724-0.730) and for UNINSUR is 0.730 (95% CI, 0.727-0.733) among the 329074 All of Us participants, both significantly higher than aggregated SDoHs. The association between model-based NOHSDP and undiagnosed hypertension is concordant with those estimated using self-reported NOHSDP, with a correlation coefficient of 0.649. Similarly, the association between model-based NOHSDP and undiagnosed diabetes is concordant with those estimated using self-reported NOHSDP, with a correlation coefficient of 0.900. The model-based SDoH estimation method offers a scalable and easily standardized approach for estimating individual-level SDoHs. Using the All of Us dataset, we demonstrate reasonable concordance between model-based SDoH estimates and self-reported SDoHs, along with consistent associations with health outcomes. Our findings also underscore the critical role of geographic contexts in SDoH estimation and in evaluating the association between SDoHs and health outcomes.

Assessing associations between individual-level social determinants of health and COVID-19 hospitalizations: investigating racial/ethnic disparities among people living with HIV in the U.S. National COVID Cohort Collaborative (N3C)

Assessing associations between individual-level social determinants of health and COVID-19 hospitalizations: investigating racial/ethnic disparities among people living with HIV in the U.S. National COVID Cohort Collaborative (N3C)

Self-Reported Social Determinants of Health and Area-Level Social Vulnerability

Many health care systems are investing resources in identifying social determinants of health (SDoH) needs and facilitating interventions among the populations they serve. Because self-reported SDoH information is lacking, area-level measures are often used to estimate needs and direct resources. To describe the large-scale deployment of SDoH assessments by a health system and determine the extent to which self-reported SDoH needs identified therein are associated with census tract-level social vulnerability measured using the Social Vulnerability Index (SVI). This cross-sectional study assessed SDoH needs between January 1, 2020, and April 30, 2023, in both payer and clinical care settings. Modalities included telephonic outreach, face-to-face clinical interactions, self-entry into a tablet or kiosk, and web-based survey tools. Participants included individuals who responded to the assessment and had sufficient information for census tract identification. Respondents included both Highmark Health Plan members and nonmembers. Health plan members responded to the assessment through health plan programs or platforms, and both members and nonmembers responded to assessments during inpatient or outpatient encounters with the affiliated health system. Overall and domain-specific SDoH needs self-reported through assessments, and severity and complexity of needs identified. Residential social vulnerability measures included overall SVI and the 4 conceptual themes comprising overall SVI. In total, 841 874 assessments were recorded for 401 697 individuals (55.1% women; median [IQR] age, 55 [41-70] years). Social determinants of health needs were identified in 120 769 assessments (14.3%). Across all SDoH domains, increasing SVI was associated with a higher positivity rate (eg, 11.2% of those residing in the lowest-risk SVI quintile reported a need compared with 22.7% among those residing in the highest-risk quintile). Associations varied by SDoH domain and SVI theme. After adjusting for demographic and screening characteristics, odds of positive screening among those residing in the highest-risk SVI quintile were 1.74 (95% CI, 1.62-1.86) to 3.73 (95% CI, 3.48-4.00) times the odds among those residing in lowest risk quintile. In this cross-sectional study, the overall level of SDoH needs generally corresponded to area-level vulnerability. Some SDoH domains appeared far more sensitive to community characteristics than others. Notably, even among individuals from the highest-risk areas, the positive screening rate was roughly 1 in 4. These findings underscore the importance of individual-level SDoH data for service provision planning and health services research.

Development and validation of mortality prediction models based on the social determinants of health

BackgroundThere is no standardised approach to screening adults for social risk factors. The goal of this study was to develop mortality risk prediction models based on the social determinants of...

Cardiovascular Risk Associated With Social Determinants of Health at Individual and Area Levels

The benefit of adding social determinants of health (SDOH) when estimating atherosclerotic cardiovascular disease (ASCVD) risk is unclear. To examine the association of SDOH at both individual and area levels with ASCVD risks, and to assess if adding individual- and area-level SDOH to the pooled cohort equations (PCEs) or the Predicting Risk of CVD Events (PREVENT) equations improves the accuracy of risk estimates. This cohort study included participants data from 4 large US cohort studies. Eligible participants were aged 40 to 79 years without a history of ASCVD. Baseline data were collected from 1995 to 2007; median (IQR) follow-up was 13.0 (9.3-15.0) years. Data were analyzed from September 2023 to February 2024. Individual- and area-level education, income, and employment status. ASCVD was defined as the composite outcome of nonfatal myocardial infarction, death from coronary heart disease, and fatal or nonfatal stroke. A total of 26 316 participants were included (mean [SD] age, 61.0 [9.1] years; 15 494 women [58.9%]; 11 365 Black [43.2%], 703 Chinese American [2.7%], 1278 Hispanic [4.9%], and 12 970 White [49.3%]); 11 764 individuals (44.7%) had at least 1 adverse individual-level SDOH and 10 908 (41.5%) had at least 1 adverse area-level SDOH. A total of 2673 ASCVD events occurred during follow-up. SDOH were associated with increased risk of ASCVD at both the individual and area levels, including for low education (individual: hazard ratio [HR], 1.39 [95% CI, 1.25-1.55]; area: HR, 1.31 [95% CI, 1.20-1.42]), low income (individual: 1.35 [95% CI, 1.25-1.47]; area: HR, 1.28 [95% CI, 1.17-1.40]), and unemployment (individual: HR, 1.61 [95% CI, 1.24-2.10]; area: HR, 1.25 [95% CI, 1.14-1.37]). Adding area-level SDOH alone to the PCEs did not change model discrimination but modestly improved calibration. Furthermore, adding both individual- and area-level SDOH to the PCEs led to a modest improvement in both discrimination and calibration in non-Hispanic Black individuals (change in C index, 0.0051 [95% CI, 0.0011 to 0.0126]; change in scaled integrated Brier score [IBS], 0.396% [95% CI, 0.221% to 0.802%]), and improvement in calibration in White individuals (change in scaled IBS, 0.274% [95% CI, 0.095% to 0.665%]). Adding individual-level SDOH to the PREVENT plus area-level social deprivation index (SDI) equations did not improve discrimination but modestly improved calibration in White participants (change in scaled IBS, 0.182% [95% CI, 0.040% to 0.496%]), Black participants (0.187% [95% CI, 0.039% to 0.501%]), and women (0.289% [95% CI, 0.115% to 0.574%]). In this cohort study, both individual- and area-level SDOH were associated with ASCVD risk; adding both individual- and area-level SDOH to the PCEs modestly improved discrimination and calibration for estimating ASCVD risk for Black individuals, and adding individual-level SDOH to PREVENT plus SDI also modestly improved calibration. These findings suggest that both individual- and area-level SDOH may be considered in future development of ASCVD risk assessment tools, particularly among Black individuals.

Individual-level social determinants of health and allostatic load/chronic toxic stress in men with prostate cancer.

263 Background: Allostatic load (AL)/chronic toxic stress is linked to a higher risk of adverse cancer-specific and cardiac events in prostate cancer (PC) patients especially non-Hispanic Blacks (NHBs). We hypothesize that NHBs experience more adverse social determinants of health (SDOH) that increases this AL. Methods: We included men≥18 years diagnosed with PC (2010-2022). Individual-level SDOH with 19 covariates across 4 domains was obtained. Pre-PC diagnosis AL was calculated as an ordinal measure (0-11). Components and cutoffs for the AL score: Each measure above the cutoff add 1 point to AL. Systolic blood pressure (BP) ≥140 mmHg, diastolic BP ≥90 mmHg, heart rate >100 bpm, total cholesterol (chol) ≥240 mg/dl, high-density lipoprotein chol ≤50 mg/dl, triglycerides ≥150 mg/dl, glycated hemoglobin ≥6.5, body mass index ≥30 kg/m2, glucose ≥110 mg/dl, C-reactive protein >3 mg/L and interleukin-6 >1.8 pg/ml. A gradient-boosting Machine Learning model ranked AL predictors using SHAP scores (SS). Cubic splined from logistic regressions defined SDOH adversity cutoffs. Results: Among 4,258 patients (886 NHB), the median age was 69 (IQR 63-77). Most were former smokers (44.2%), and the median Charlson comorbidity score was 4 (IQR 2-7). In NHBs, the SDOH variables among the top 5 overall predictors of AL were annual income (SS=0.10), neighborhood murder index (SS=0.07), neighborhood median income (SS=0.06), and neighborhood car theft index (SS=0.05). Considering all the SDOH features analyzed, NHBs faced adversity in 12 of 19 SDOH features (63%; Table). Conclusions: SDOH related to the neighborhood, built environment, and economic stability, are crucial predictors of pre-PC diagnosis AL in NHBs. [Table: see text]

Abstract 12346: Atherosclerotic Cardiovascular Disease Risk Associated With Social Determinants of Health at Individual and Area Levels

Introduction: Adverse social determinants of health (SDOH) are associated with an increased risk for atherosclerotic cardiovascular disease (ASCVD). However, it is unclear if the ASCVD risks associated with area-level SDOH are similar to those with individual-level measures. Further, SDOH are not included in the Pooled Cohort Equations (PCEs) when estimating 10-year ASCVD risk. Studies have shown that PCEs systematically underestimate risk for socially deprived individuals. Aims To examine the association of individual- and area-level SDOH including education, income, and employment with incident ASCVD. Also, we assessed if adding SDOH to the PCEs improves risk prediction accuracy. Methods: We pooled data from four cohorts: Jackson Heart Study, Multi-Ethnic Study of Atherosclerosis, Framingham Heart Study Offspring Cohort, and Reasons for Geographic and Racial Differences in Stroke Study. We excluded participants with a history of ASCVD. Individual-level SDOH were based on participants’ self-report and area-level SDOH were derived by linking participants’ addresses to US Census tract data. We used Cox proportional hazards models to assess the associations between SDOH and ASCVD. We also assessed the changes in discrimination (Harrell’s C-index) and calibration (Integrated Brier Score) after adding SDOH to risk prediction models. Results: We analyzed data from 27,603 participants (mean age 61.4 years, 59% women, and 49% White). During a median follow-up of 13 years, 2,839 incident ASCVD events occurred. Both individual- and area-level SDOH were associated with ASCVD ( Figure, Panel A ). Adding both individual- and area-level SDOH to risk prediction modestly improved model discrimination and calibration in Black men and women ( Figure, Panels B & C ), and also improved calibration in non-Black women. Conclusions: The findings suggest that SDOH may be considered in the development of future ASCVD risk assessment tools, particularly among Black individuals.

Individual-Level Social Determinants of Health (SDOH) Measures and Treatment Complications in Acute Leukemia

Background Population studies demonstrate widening survival disparities in AML survival. In our previous analysis, census tract-based measures of socioeconomic status accounted for most of the AML death disparity for non-Hispanic Black (NHB) and Hispanic patients (pts) suggesting that patients' social and physical environments contribute to poor AML endpoints (Abraham et al. Blood 2022). However, these data are retrospective and only provide neighborhood-level information. We prospectively collected individual level data on SDOH and linked this to treatment delivery and complications. Methods Patients were prospectively enrolled from two institutions: a comprehensive cancer center and a minority-serving cancer center for a planned 2 year follow-up. A mixed-methods approach utilized validated questionnaires and semi-structured interviews administered to patients 30-90 days from diagnosis and data was collected on adherence, falls, infections, ER visits, hospitalizations, and ICU admission. Quantitative measures included patient neighborhood and environmental living conditions (AHC HRSN), health literacy (CHLT-6), financial toxicity (COST-FACIT), medication affordability/adherence (ARMS), and mental health (PHQ-4). Quantitative data was supplemented with qualitative data from semi-structured interviews from a subset of patients. We used linear regression to estimate statistical differences in means between groups. Results We report results from 52 patients, predominantly with AML and high-risk MDS followed for up to 6 months. Baseline characteristics are summarized in Table 1. Median age was 62 years. 38% were non-Hispanic White (NHW), 25% NHB, and 23% Hispanic and lived in socioeconomically diverse census tracts. Half the cohort had a high school education or less. 40% had an annual income level < $25,000. 40% pts had a Charlson comorbidity index (CCI) ≥ 5. On the AHC HRSN tool, housing and food insecurity were reported in 10% and 15%, respectively, 40% reported difficulty paying for basic needs and 22% loneliness/isolation. In terms of care delivery, pts aged ≥ 65 years were more likely to miss clinic visits (p=0.026) and chemotherapy treatments (p=0.005). Non-white (p=0.13) pts and those on public insurance (p=0.04) were also more likely to miss clinic visits. Education level, income, and marital status were not associated with missed visits/treatments. Assessing treatment complications 60% of ER visits occurred with annual household incomes under $50,000 (p=0.048). Education and insurance were also linked to treatment morbidity, with 75% of ICU admissions having a high school education or less (p=0.09) and 83% having Medicare or Medicaid (p=0.087). Rates of mechanical ventilation mirrored these findings. Education was associated with lower rates of discharge to SNF or SAR, 72% of college or higher-educated pts were discharged home (p=0.035). Fall rates and infectious complications did not differ based on SDOH. Interestingly age and CCI did not distinguish between any of these treatment complications. Validated patient reported measures of social vulnerability were next examined as predictors of treatment adherence and complications (Table 2). The mean COSTFACIT was 9.8 lower (95% CI -17.6 to -1.93) in those with ER visits than those without ER visits (p=0.061). The mean CHLT-6 score was 0.96 lower (95% CI -1.8 to -0.09) in pts admitted to the ICU (p = 0.03). The PHQ-4 score did not differ based on any complication. Discussion This study represents the first attempt to prospectively link patient reported SDOH to treatment delivery and early complications in leukemia and provides valuable insights into targetable barriers to overcome disparities. Age was the most significant risk factor for missed clinic visits and chemotherapy doses. Older pts may benefit from navigators, caregiver engagement, tailored education given increased reliance on complex outpatient regimens. Treatment complications were strongly associated with SDOH, including education and household income. These findings suggest that pre-treatment ‘fitness’ assessments and greater home-based visits during treatment may mitigate ER visits and life-threatening complications. Importantly, quantitative SDOH measures such as COST-FACIT and CHLT-6 can prospectively identify patients at risk of early complications and become an important tool to triage these resources.

11 Social Determinants of Health in Pediatric Brain Tumor Survivors: Associations between Neighborhood Opportunity and Neurocognitive and Psychological Outcomes

Objective:A growing body of research demonstrates that social determinants of health (SDOH) are important predictors of neurocognitive and psychological outcomes in survivors of pediatric brain tumor (PBT). Existing research has focused primarily on individual level SDOH (e.g., family income, education, insurance status). Thus, more information is needed to understand community level factors which may contribute to health inequities in PBT survivors. This study aimed to examine the effects of specific aspects of neighborhood opportunity on cognitive and emotional/behavioral outcomes among PBT survivors.Participants and Methods:The sample included clinically-referred PBT survivors who completed a neuropsychological evaluation (N=199, Mage=11.63, SD= 4.63, 56.8% male, 71.8% White). Data included an age-appropriate Wechsler Scale and parent-report questionnaires (Behavior Rating Inventory of Executive Function, Child Behavior Checklist). Nationally-normed Child Opportunity Index (COI) scores were extracted for each participant from electronic medical records based on home address using Census tract geocoding. The COI measures neighborhood-level quality of environmental and social conditions that contribute to positive health. It includes three component scores assessing distinct aspects of opportunity, which include educational opportunity (e.g., educational quality, resources, and outcomes), health/environmental opportunity (e.g., access to healthy food, healthcare, and greenspace) and social/economic opportunity (e.g., income, employment, poverty). Stepwise linear regression models were examined to identify significant predictors of cognitive/psychological outcomes associated with PBT; the three COI indices were entered as predictors and retained in the model if they significantly contribute to variance in the outcome.Results:Lower educational opportunity was associated with lower processing speed performance (Wechsler Processing Speed Index: t = 2.47, p = 0.02) and increased parent-reported executive functioning problems (BRIEF GEC: t = -2.25, p = 0.03; BRIEF Working Memory: t = -2.45, p = 0.02) and externalizing problems (CBCL Externalizing: t = -2.19, p = 0.03). Lower social/economic opportunity was associated with lower working memory performance (Wechsler Working Memory Index: t = 2.63, p < 0.01) and increased parent-reported internalizing problems (CBCL Internalizing: t = -2.38, p = 0.02). Health/environmental opportunity did not emerge as a primary predictor of any of the examined cognitive/psychological outcomes. Exploratory analyses examining the impact of age on associations between COI and cognitive/psychological outcomes found a significant moderation effect of age on the relationship between educational opportunity and processing speed (t = 2.35, p = 0.02) such that this association was stronger at older ages. There were no other moderation effects by age.Conclusions:Consistent with a growing body of literature demonstrating the impact of social and environmental contexts to health outcomes, these results show inequities in neurocognitive and psychosocial outcomes in PBT survivors related to neighborhood-level SDOH. Examination of specific neighborhood factors highlight educational and social/economic factors as particularly important contributors to neurocognitive/psychological risk for survivors. The identification of these specific and potentially modifiable risk factors is crucial to inform individual-level problem-prevention following oncological treatment, as well as community-level policy and advocacy efforts.

Social Determinant of Health Impact on Diabetes Device Use and Clinical Outcomes in Youth with Type 1 Diabetes

Background. Youth with Type 1 diabetes (T1D) who are Black, Hispanic, or lower socioeconomic status (SES) have lower rates of diabetes device use, higher hemoglobin A1c (HbA1c), and higher rates of diabetic ketoacidosis (DKA). However, the associations of individual-level social determinants of health (SDoH) and neighborhood-level factors with device use and clinical outcomes are unknown. Area deprivation index (ADI) is a neighborhood level measure of SES reported in deciles (range 1–10 with 10 representing most deprived neighborhood). Methods. We evaluated the association of ADI and other SDoH factors with pump/continuous glucose monitor (CGM) use, HbA1c, and DKA in 1,461 youth with T1D (50% female, age 12.8 ± 3.6 years, HbA1c 8.7 ± 2.1%, 52% pump, 70% CGM) seen between October 1, 2020 and September 30, 2021 at a large pediatric diabetes center. Multiple logistic regression and multiple linear regression analyses were used to determine statistically significant associations adjusting for potential confounders. Results. Youth were less likely to use an insulin pump if they lived in a higher ADI neighborhood, were Black or Hispanic, had Medicaid or were uninsured, or received government assistance (e.g., Supplemental Security Income, Supplemental Nutritional Assistance Program). Youth were less likely to use a CGM if they lived in a higher ADI neighborhood, were Black or Hispanic, had Medicaid or were uninsured. Youth had higher risk of DKA event in the past year if they used government assistance, whereas pump and CGM use were associated with lower DKA risk. HbA1c (%) increased by 0.09 (95% CI: 0.05, 0.13) per unit increase in ADI. HbA1c was 0.62 lower (95% CI: −0.82, −0.42) in pump users vs. nonusers and 0.78 lower (95% CI: −0.99, −0.56) in CGM users vs. nonusers. Conclusions. Interventions that tailor care plans to address SDoH in families living in deprived neighborhoods may be needed to increase successful technology uptake, optimize HbA1c, and prevent DKA.

Using PROGRESS-plus to identify current approaches to the collection and reporting of equity-relevant data: a scoping review

ObjectivesOur objectives were to identify what and how data relating to the social determinants of health are collected and reported in equity-relevant studies and map these data to the PROGRESS-Plus framework. Study Design and SettingWe performed a scoping review. We ran two systematic searches of MEDLINE and Embase for equity-relevant studies published during 2021. We included studies in any language without limitations to participant characteristics. Included studies were required to have collected and reported at least two participant variables relevant to evaluating individual-level social determinants of health. We applied the PROGRESS-Plus framework to identify and organize these data. ResultsWe extracted data from 200 equity-relevant studies, providing 962 items defined by PROGRESS-Plus. A median of 4 (interquartile range = 2) PROGRESS-Plus items were reported in the included studies. 92% of studies reported age; 78% reported sex/gender; 65% reported educational attainment; 49% reported socioeconomic status; 45% reported race; 44% reported social capital; 33% reported occupation; 14% reported place and 9% reported religion. ConclusionOur synthesis demonstrated that researchers currently collect a limited range of equity-relevant data, but usefully provides a range of examples spanning PROGRESS-Plus to inform the development of improved, standardized practices.

Social determinants of health and disparate disability accumulation in a cohort of Black, Hispanic, and White patients with multiple sclerosis.

Black and Hispanic patients with multiple sclerosis (MS) have been shown to accumulate greater multiple sclerosis-associated disability (MSAD) than White patients. Disparities in social determinants of health (SDOH) among these groups have also been reported. To determine the extent to which associations of race and ethnicity with MSAD may be attributable to differences in SDOH. Retrospective chart analysis of patients at an academic MS center grouped by self-identified Black (n = 95), Hispanic (n = 93), and White (n = 98) race/ethnicity. Individual patient addresses were geocoded and matched with neighborhood-level area deprivation index (ADI) and social vulnerability index (SVI). Average Expanded Disability Status Scale (EDSS) scores at last-recorded evaluations of White patients (1.7 ± 2.0) were significantly lower than Black (2.8 ± 2.4, p = 0.001) and Hispanic (2.6 ± 2.6, p = 0.020) patients. Neither Black race nor Hispanic ethnicity was significantly associated with EDSS in multivariable linear regression models that included individual-level SDOH indicators and either ADI or SVI. Black race and Hispanic ethnicity are not significantly associated with EDSS in models that include individual and neighborhood-level SDOH indicators. Further research should elucidate mechanisms by which structural inequities affect MS disease course.

Social determinants of health impact mortality from HCC and cholangiocarcinoma: a population-based cohort study.

The social determinants of health can pose barriers to accessing cancer screening and treatment and have been associated with cancer mortality. However, it is not clear whether area deprivation is independently associated with mortality in HCC and cholangiocarcinoma when controlling for individual-level social determinants of health. The cohort included individuals over 18 years old diagnosed with HCC (N=3460) or cholangiocarcinoma (N=781) and reported to the Indiana State Cancer Registry from 2009 to 2017. Area disadvantage was measured using the social deprivation index (SDI). SDI was obtained by linking addresses to the American Community Survey. Individual social determinants of health included race, ethnicity, sex, marital status, and insurance type. The primary outcome was mortality while controlling for SDI and individual social determinants of health by means of Cox proportional hazard modeling. In HCC, living in a neighborhood in the fourth quartile of census-track SDI (most deprived) was associated with higher mortality (HR: 1.14, 95% CI, 1.003-1.30, p=0.04) than living in a first quartile SDI neighborhood. Being uninsured (HR: 1.64, 95% CI, 1.30-2.07, p<0.0001) and never being married (HR: 1.31, 95% CI, 1.15-1.48, p<0.0001) were also associated with mortality in HCC. In cholangiocarcinoma, SDI was not associated with mortality. Social deprivation was independently associated with mortality in HCC but not cholangiocarcinoma. Further research is needed to better understand how to intervene on both area and individual social determinants of health and develop interventions to address these disparities.

A Machine Learning Approach to Support Urgent Stroke Triage Using Administrative Data and Social Determinants of Health at Hospital Presentation: Retrospective Study

The key to effective stroke management is timely diagnosis and triage. Machine learning (ML) methods developed to assist in detecting stroke have focused on interpreting detailed clinical data such as clinical notes and diagnostic imaging results. However, such information may not be readily available when patients are initially triaged, particularly in rural and underserved communities. This study aimed to develop an ML stroke prediction algorithm based on data widely available at the time of patients' hospital presentations and assess the added value of social determinants of health (SDoH) in stroke prediction. We conducted a retrospective study of the emergency department and hospitalization records from 2012 to 2014 from all the acute care hospitals in the state of Florida, merged with the SDoH data from the American Community Survey. A case-control design was adopted to construct stroke and stroke mimic cohorts. We compared the algorithm performance and feature importance measures of the ML models (ie, gradient boosting machine and random forest) with those of the logistic regression model based on 3 sets of predictors. To provide insights into the prediction and ultimately assist care providers in decision-making, we used TreeSHAP for tree-based ML models to explain the stroke prediction. Our analysis included 143,203 hospital visits of unique patients, and it was confirmed based on the principal diagnosis at discharge that 73% (n=104,662) of these patients had a stroke. The approach proposed in this study has high sensitivity and is particularly effective at reducing the misdiagnosis of dangerous stroke chameleons (false-negative rate <4%). ML classifiers consistently outperformed the benchmark logistic regression in all 3 input combinations. We found significant consistency across the models in the features that explain their performance. The most important features are age, the number of chronic conditions on admission, and primary payer (eg, Medicare or private insurance). Although both the individual- and community-level SDoH features helped improve the predictive performance of the models, the inclusion of the individual-level SDoH features led to a much larger improvement (area under the receiver operating characteristic curve increased from 0.694 to 0.823) than the inclusion of the community-level SDoH features (area under the receiver operating characteristic curve increased from 0.823 to 0.829). Using data widely available at the time of patients' hospital presentations, we developed a stroke prediction model with high sensitivity and reasonable specificity. The prediction algorithm uses variables that are routinely collected by providers and payers and might be useful in underresourced hospitals with limited availability of sensitive diagnostic tools or incomplete data-gathering capabilities.

Abstract 11546: Racial Disparities in Zip-Code Level Social Determinants of Health and Cardiovascular Outcomes in Females With Breast Cancer

Introduction: Cardiovascular disease (CVD) prevalence and cancer mortality are higher in non-Hispanic Blacks (NHB) relative to other racial subpopulations. Hypothesis: Among females with BC (≥18 years), there are racial differences in cardiac events (CEV) which can be explained by adverse social determinants of health (SDOH). Methods: Data were obtained from a Cleveland area integrated health care systems informatics platform. (2005-2019). Zip-code level demographic features were extracted using the SDOH Database from the Agency for Healthcare Research and Quality. The CEVs included were heart failure (HF), acute coronary syndrome (ACS), and ischemic stroke (IS). Multivariable Cox proportional hazards regression models were used to examine racial disparities in CEVs. Race-stratified (NHB and non-Hispanic Whites [NHW]) multivariable logistic regression was performed to assess the role of each SDOH in association with CEV. Results: This study included 9,022 females with breast cancer (BC) of which 18.8% were NHB, and 48.7% had a CEV. The racial differences in CEV and the role of zip-code level SDOH are presented in Table 1. These racial differences were not explained by the proportion of people unemployed in the zip code (p=0.42, race*unemployment % [cross-product]), proportional of people in the zip code with only a high school diploma (p=0.66, race*education % [cross-product]), and proportion of people in the zip code who use public transport (p=0.24, race * transport % [cross-product]). Conclusion: There are racial differences in the risk of ACS and IS after a BC diagnosis, but this does not seem to be explained by the 3 adverse zip-code level SDOH included in this study. Therefore, studies with individual-level SDOH and including other domains are necessary to better understand their relationship with CEVs.

Temporal variation in individual social risk factors associated with testing positive for SARS-CoV-2 among veterans in the veterans health administration

PurposeMarginalized communities have been disproportionally impacted by SARS-CoV-2. How the associations between social determinants of health and the risk of SARS-CoV-2 infection shifted across time is unknown. In this evaluation, we examine individual-level social determinants of health as social risk factors for SARS-CoV-2 infection across the first 12 months of the pandemic among US Veterans.MethodsWe conducted a retrospective cohort analysis of 946,358 Veterans who sought testing or treatment for SARS-CoV-2 infection in U.S. Department of Veterans Affairs medical facilities. We estimated risk ratios for testing positive by social risk factors, adjusting for demographics, comorbidities, and time. Adjusted models were stratified by pandemic phase to assess temporal fluctuations in social risks.ResultsApproximately 19% of Veterans tested positive for SARS-CoV-2. Larger household size was a persistent risk factor and this association increased over time. Early in the pandemic, lower county-level population density was associated with lower SARS-CoV-2 infection risk, but between June 1 and August 31, 2020, this trend reversed.ConclusionsTemporal fluctuations in social risks associated with Veterans’ SARS-CoV-2 infection suggest the need for ongoing, real-time tracking as the social and medical environment continues to evolve.

The Role of Social Determinants of Health in Moral Injury: Implications and Future Directions.

Purpose of ReviewExposure to potentially morally injurious events (PMIEs) and the development of moral injury have yet to be conceptualized as they relate to social determinants of health (SDoH).Recent Findings.In this paper, the extant literature on moral injury and SDoH is reviewed. Specific individual-level SDoH, including gender, sex, sexual orientation, race, and ethnicity, are explored relative to PMIEs and moral injury. The relationship among environmental SDoH, including childhood environment, justice involvement, and homelessness, is described.SummaryAssessment and treatment implications are discussed, and future research directions highlighting the need for additional work addressing health inequities in moral injury are presented.

Impact of social determinants of health on improving the LACE index for 30-day unplanned readmission prediction.

ObjectiveEarly and accurate prediction of patients at risk of readmission is key to reducing costs and improving outcomes. LACE is a widely used score to predict 30-day readmissions. We examine whether adding social determinants of health (SDOH) to LACE can improve its predictive performance.MethodsThis is a retrospective study that included all inpatient encounters in the state of Maryland in 2019. We constructed predictive models by fitting Logistic Regression (LR) on LACE and different sets of SDOH predictors. We used the area under the curve (AUC) to evaluate discrimination and SHapley Additive exPlanations values to assess feature importance.ResultsOur study population included 316 558 patients of whom 35 431 (11.19%) patients were readmitted after 30 days. Readmitted patients had more challenges with individual-level SDOH and were more likely to reside in communities with poor SDOH conditions. Adding a combination of individual and community-level SDOH improved LACE performance from AUC = 0.698 (95% CI [0.695–0.7]; ref) to AUC = 0.708 (95% CI [0.705–0.71]; P < .001). The increase in AUC was highest in black patients (+1.6), patients aged 65 years or older (+1.4), and male patients (+1.4).DiscussionWe demonstrated the value of SDOH in improving the LACE index. Further, the additional predictive value of SDOH on readmission risk varies by subpopulations. Vulnerable populations like black patients and the elderly are likely to benefit more from the inclusion of SDOH in readmission prediction.ConclusionThese findings provide potential SDOH factors that health systems and policymakers can target to reduce overall readmissions.

Social Vulnerability Is Associated with Poorer Outcomes in Preschool Children With Recurrent Wheezing Despite Standardized and Supervised Medical Care

Social determinants of health are associated with disparate asthma outcomes in school-age children. Social determinants have not been studied in preschool children with recurrent wheezing. We hypothesized that preschool children with recurrent wheezing at highest risk of social vulnerability would have more frequent symptoms and exacerbations when followed over 1 year, despite receiving standardized and supervised asthma care. A multicenter population of adherent preschool children receiving standardized and supervised care for wheezing was stratified by a composite measure of social vulnerability based on individual-level variables. Primary outcomes included days with upper respiratory infections and days with asthma symptom flares. Other outcomes included symptom scores during upper respiratory infections and respiratory symptom flare days, exacerbation occurrence, quality of life during the exacerbation, and hospitalization. Preschool children at highest risk of social vulnerability did not have more frequent upper respiratory infections, respiratory symptoms, or exacerbations, but instead had more severe symptoms during upper respiratory infections and respiratory flare days, as well as more severe exacerbations with significantly poorer caregiver quality of life. Children at highest risk of social vulnerability also lived in poorer housing conditions with differing exposures and self-reported triggers. Individual-level social determinants of health reflecting social vulnerability are associated with poorer outcomes in preschool children with recurrent wheezing despite access to supervised and standardized care. Comprehensive assessment of social determinants of health is warranted in even the youngest children with wheezing, because mitigation of these social inequities is an essential first step toward improving outcomes in pediatric patients.

Association Between Neighborhood Disadvantage and Pediatric Readmissions.

Although individual-level social determinants of health (SDH) are known to influence 30-day readmission risk, contextual-level associations with readmission are poorly understood among children. This study explores associations between neighborhood disadvantage measured by Area Deprivation Index (ADI) and pediatric 30-day readmissions. This retrospective cohort study included discharges of patients aged < 20years from Maryland's 2013-2016 all-payer dataset. The ADI, which quantifies 17 indicators of neighborhood socioeconomic disadvantage within census block groups, is used as a proxy for contextual-level SDH. Readmissions were identified with the 30-day Pediatric All-Condition Readmissions measure. Associations between ADI and readmission were identified with generalized estimating equations adjusted for patient demographics and clinical severity (Chronic Condition Indicator [CCI], Pediatric Medical Complexity Algorithm [PMCA], Index Hospital All Patients Refined Diagnosis Related Groups [APR-DRG]), and hospital discharge volume. Discharges (n = 138,998) were mostly female (52.7%), publicly insured (55.1%), urban-dwelling (93.0%), with low clinical severity levels (0-1 CCIs [82.3%], minor APR-DRG severity [48.4%]). Overall readmission rate was 4.0%. Compared to the least disadvantaged ADI quartile, readmissions for the most disadvantaged quartile were significantly more likely (aOR 1.19, 95% CI 1.09-1.30). After adjustment, readmissions were associated with public insurance and indicators of medical complexity (higher number of CCIs, complex-chronic disease PMCA, and APR-DRG severity). In this all-payer, statewide sample, living in the most socioeconomically disadvantaged neighborhoods independently predicted pediatric readmission. While the relative magnitude of neighborhood disadvantage was modest compared to medical complexity, disadvantage is modifiable and thus represents an important consideration for prevention and risk stratification efforts.