Practical considerations for social determinant-based disease prediction in the All of Us research program

Association between cumulative social disadvantage, as measured by the social determinants of health score, and epilepsy: a cross-sectional study.

BACKGROUND Social determinants of health (SDoH) shape access to care, health behaviors, and long-term outcomes, yet their cumulative relationship with epilepsy has not been well quantified. This study examined whether a composite SDoH score was associated with epilepsy in adults. METHODS This cross-sectional study used data from the National Health and Nutrition Examination Survey 2013-2018. The SDoH score ranged from 0 to 8 and summarized eight unfavorable social conditions. Epilepsy was identified using medication-based ascertainment. Survey-weighted logistic regression models were applied to evaluate the association between SDoH score and epilepsy. Restricted cubic spline, subgroup, sensitivity, and receiver operating characteristic analyses were also performed. RESULTS A total of 13,119 participants were included, of whom 114 had epilepsy. Participants with epilepsy had a higher mean SDoH score than those without epilepsy (3.41 ± 0.24 vs. 2.35 ± 0.06, P < 0.001). In the fully adjusted model, each 1-point increase in SDoH score was associated with 31% higher odds of epilepsy (OR 1.31, 95% CI 1.16-1.48). Compared with the low-score group (0-2), the adjusted odds ratios were 2.09 (95% CI 1.06-4.15) for scores of 3-5 and 2.67 (95% CI 1.34-5.33) for scores of 6-8. Spline analysis showed a significant overall association without evidence of nonlinearity. Adding SDoH components to demographic variables improved model discrimination (AUC 0.731 vs. 0.589, P for difference <0.001). CONCLUSION Greater cumulative social disadvantage, as reflected by the SDoH score, was associated with higher odds of epilepsy.

The association between social determinants of health and Parkinson's disease prevalence among U.S. adults: A cross-sectional study.

BACKGROUND Social determinants of health (SDOH) encompass the economic, social, and environmental conditions that shape health outcomes. While SDOH are increasingly recognized as fundamental drivers of chronic disease, their relationship with Parkinson's disease (PD) remains poorly characterized. OBJECTIVE To examine the association between individual and cumulative adverse SDOH and PD prevalence in a nationally representative sample of U.S. adults. METHODS We conducted a cross-sectional analysis of 24,018 adults from the 2003-2016 National Health and Nutrition Examination Survey. A cumulative SDOH score (range 0-8) was constructed from eight adverse conditions across employment, income, food security, education, healthcare access, health insurance, housing stability, and marital status. PD was defined by anti-Parkinsonian medication use. Survey-weighted multivariable logistic regression was used, adjusting for demographic, behavioral, and clinical covariates. RESULTS The weighted prevalence of PD was 0.75%. In fully adjusted models, each one-point increase in the cumulative SDOH score was associated with 21% higher odds of PD (OR 1.21; 95% CI 1.12-1.32). Compared to those with no adverse SDOH, individuals with 4-8 adversities had 2.59-fold higher odds of PD (95% CI 1.52-4.41), with a significant relationship. Unemployment, food insecurity, lack of health insurance, housing instability, and unmarried status demonstrated independent associations with PD. CONCLUSIONS Cumulative social disadvantage is independently associated with PD prevalence in U.S. adults. These findings suggest that social context may represent an underrecognized dimension related to PD and warrant further investigation into mechanisms linking social adversity to neurodegenerative disease.

Feasibility Assessment of Extracting Social Determinants of Health From Electronic Medical Records: A Multicenter Study Across Chinese Healthcare Institutions

ABSTRACT Background Social determinants of health (SDoH) are pivotal in influencing health outcomes and disparities across various populations. Real‐world data rich in SDoH information, such as electronic medical records (EMRs), can considerably enhance public health interventions. However, in Chinese medical practice, these non‐clinical factors are often neglected, with many healthcare providers failing to recognize the importance of SDoH information in the improvement of patient care. The objective of this study is to explore the feasibility and effectiveness of extracting SDoH information from Chinese EMRs. Methods We developed a China‐specific SDoH classification framework by integrating findings from relevant research using real‐world data. This framework was applied to over three million patient records from Chinese EMRs to examine the completeness and availability of SDoH‐related attributes within relevant fields. We also developed a quantitative assessment framework for evaluating SDoH information in EMR fields. This two‐dimensional evaluation system measures data completeness and availability using a three‐level hierarchical scoring approach, progressing from basic to advanced criteria. Additionally, we analyzed variations in SDoH information extraction across different healthcare institutions. Results Drawing on the literature and 2000 manually annotated EMRs, we established a standardized framework of SDoH factors, comprising 50 features tailored to the Chinese medical diagnostic and treatment environment. We analyzed over 5.6 million EMRs from 40 hospitals within the National Clinical Research Data Center and found that tables and fields in Chinese EMRs cover all six primary SDoH categories, encompassing 25 out of 50 specific attributes. However, data extraction feasibility was relatively poor, with only seven features being fully extractable, with most “social and community context” data missing. Our evaluation of 43 electronic health record fields containing SDoH data revealed significant disparities between completeness and availability metrics. The composite completeness score averaged 1.47 (95% confidence interval: 1.20–1.73) out of a maximum score of 3. Availability assessments demonstrated notably higher performance with a mean score of 2.14 (95% confidence interval: 1.83–2.44) out of a maximum score of 3. Conclusions This research established a culturally adapted SDoH framework for China and demonstrated the feasibility of extracting SDoH attributes from Chinese EMRs. Although some SDoH information in EMRs still cannot be captured or requires more advanced data processing to be usable, Chinese EMRs contain a wealth of SDoH data, allowing us to use large existing EMR databases to support ongoing SDoH research. Natural language processing technology has a critical role in this process, underscoring the importance of medical informatics and current artificial intelligence techniques in medicine and public health. Our research lays a foundation for future SDoH studies in China, enabling more comprehensive research and encouraging the government and relevant agencies to focus on SDoH interventions.

Assessing the Utility of Social Determinants of Health Data in Suicide Prediction Models.

OBJECTIVE This study seeks to explore the utility of social determinants of health (SDoH) variables in suicide prediction models. We aim to assess the impact of individual- and geographic-level SDoH factors on improving the performance of suicide prediction models and the identification of individuals at high risk for suicide. METHODS A retrospective sample of 1214 deaths by suicide and 815,544 living patients was identified in the Maryland Suicide Data Warehouse (MSDW) and linked to census tract data through geo-coding. Three machine learning algorithms were trained and validated with cross-validation to assess model performance across different data category combinations, including demographics, clinical features, and individual and geographic level SDoH. RESULTS Models incorporating clinical information demonstrated substantial improvements in predictive performance compared with demographic-only baselines across all algorithms. In the absence of clinical data, the addition of individual level SDoH significantly improved performance compared to baseline models, where 73% of individual level SDoH factors were identified as significant. Conversely, geographic level SDoH provided limited improvement in model performance, with only 7% of variables showing significance marginally. CONCLUSIONS Within SDoH data, most individual level SDoH are among the most important risk factors associated with death by suicide, with improvement in model performance over just clinical and demographic information. Geographic level SDoH appeared to have limited added value.

Combined Effects of Social Determinants of Health on Alzheimer's Disease: Insights from Bibliometric and NHANES Analyses.

Phenomic profiles and disease patterns of 1.9 million participants from Our Future Health.

Our Future Health is a prospective study aiming to recruit 5 million UK-resident adults to enable discovery and translation of disease prevention, detection and treatment approaches. So far, more than 2.5 million have enrolled, and baseline phenotypic data are available for >1.9 million participants. Here we provide an assessment of phenotypes-self-reported health-related behaviors, geolocation, diagnoses and medication, in- and outpatient visits, cancer registry and cause of death-and comparison of disease patterns against national estimates and the UK Biobank cohort. Sociodemographic, lifestyle and health-related characteristics reflected UK population patterns; all but one minority ethnic group and the most socioeconomically deprived groups were underrepresented. The prevalence of several major self-reported conditions, particularly mental health conditions such as depression and anxiety, was higher than national estimates and directionally concordant with the UK Biobank (r = 0.78). Associations with known clinical correlates replicated across both cohorts (r = 0.80). Medication-use patterns and cancer prevalence followed expected age-related gradients, with lower lung cancer rates than national data. As recruitment progresses, electronic health records can help specify disease patterns and systematically assess biases.