Collection and Use of Social Determinants of Health Data in Inpatient General Internal Medicine Wards: A Scoping Review

Perspectives on Using Artificial Intelligence to Derive Social Determinants of Health Data From Medical Records in Canada: Large Multijurisdictional Qualitative Study

BACKGROUND

Data on the social determinants of health could be used to improve care, support quality improvement initiatives, and track progress toward health equity. However, this data collection is not widespread. Artificial intelligence (AI), specifically natural language processing and machine learning, could be used to derive social determinants of health data from electronic medical records. This could reduce the time and resources required to obtain social determinants of health data.

OBJECTIVE

This study aimed to understand perspectives of a diverse sample of Canadians on the use of AI to derive social determinants of health information from electronic medical record data, including benefits and concerns.

METHODS

Using a qualitative description approach, in-depth interviews were conducted with 195 participants purposefully recruited from Ontario, Newfoundland and Labrador, Manitoba, and Saskatchewan. Transcripts were analyzed using an inductive and deductive content analysis.

RESULTS

A total of 4 themes were identified. First, AI was described as the inevitable future, facilitating more efficient, accessible social determinants of health information and use in primary care. Second, participants expressed concerns about potential health care harms and a distrust in AI and public systems. Third, some participants indicated that AI could lead to a loss of the human touch in health care, emphasizing a preference for strong relationships with providers and individualized care. Fourth, participants described the critical importance of consent and the need for strong safeguards to protect patient data and trust.

CONCLUSIONS

These findings provide important considerations for the use of AI in health care, and particularly when health care administrators and decision makers seek to derive social determinants of health data.

Health Equity in the Care of Adult Critical Illness Survivors

There is evidence that people who fare worse in recovery do so, not only because of their illness, but also because of social and structural determinants. For example, food insecurity and poor nutrition, unemployment, poverty, social isolation and loneliness, limited social support, and poor access to medical care represent marked obstacles to recovery. Those who experience social or structural disadvantage have a poor start to their critical illness journey and are more vulnerable to adverse material conditions that contribute to and worsen their health outcomes.

Standardizing social determinants of health data: a proposal for a comprehensive screening tool to address health equity a systematic review

Social determinants of health (SDoH) significantly impacts health outcomes and disparities. While the Centers for Medicare and Medicaid Services has mandated hospitals to collect standardized SDoH data, existing tools lack key elements. This systematic review identified 78 studies and 20 screening tools addressing various SDoH domains. However, most tools were missing several key domains and lacked standardization. We propose a comprehensive tool meeting essential criteria: validated questions, brevity, actionability, cultural appropriateness, workflow integration, and community linkage. Our tool addresses gaps in available tools and incorporates standardized and validated questions to enable patient-centered screening for diverse social and environmental determinants of health. It uniquely includes detailed race/ethnicity data collection, housing characteristics, physical activity assessment, access to healthy food measures, and environmental exposure evaluation. The tool aims to provide actionable data for immediate interventions while informing broader population health strategies and policy initiatives. By offering a holistic assessment of SDoH across multiple domains, our tool enables standardized data collection, risk stratification, and focused initiatives to address health inequities at both individual and population levels. Further research is needed to develop evidence-based pathways for integrating SDoH data into real-world patient care workflows, improve risk prediction algorithms, address health-related social needs, and reduce disparities.

Evidence gaps among systematic reviews examining the relationship of race, ethnicity, and social determinants of health with adult inpatient quality measures

Background

The field of healthcare epidemiology is increasingly focused on identifying, characterizing, and addressing social determinants of health (SDOH) to address inequities in healthcare quality. To identify evidence gaps, we examined recent systematic reviews examining the association of race, ethnicity, and SDOH with inpatient quality measures.

Methods

We searched Medline via OVID for English language systematic reviews from 2010 to 2022 addressing race, ethnicity, or SDOH domains and inpatient quality measures in adults using specific topic questions. We imported all citations to Covidence (www.covidence.org, Veritas Health Innovation) and removed duplicates. Two blinded reviewers assessed all articles for inclusion in 2 phases: title/abstract, then full-text review. Discrepancies were resolved by a third reviewer.

Results

Of 472 systematic reviews identified, 39 were included. Of these, 23 examined all-cause mortality; 6 examined 30-day readmission rates; 4 examined length of stay, 4 examined falls, 2 examined surgical site infections (SSIs) and one review examined risk of venous thromboembolism. The most evaluated SDOH measures were sex (n = 9), income and/or employment status (n = 9), age (n = 6), race and ethnicity (n = 6), and education (n = 5). No systematic reviews assessed medication use errors or healthcare-associated infections. We found very limited assessment of other SDOH measures such as economic stability, neighborhood, and health system access.

Conclusion

A limited number of systematic reviews have examined the association of race, ethnicity and SDOH measures with inpatient quality measures, and existing reviews highlight wide variability in reporting. Future systematic evaluations of SDOH measures are needed to better understand the relationships with inpatient quality measures.

Social Determinants of Health in Digital Health Policies: an International Environmental Scan

INTRODUCTION

Social Determinants of Health (SDoH) include factors such as economic stability, education, social and community context, healthcare access, and the physical environment, which shape an individual's health and well-being. Given that the inclusion of SDoH factors is essential in improving the quality and equity of digital health, this study aims to examine how SDoH is incorporated within digital health policies internationally.

METHODS

An environmental scan of digital health policies was conducted, including relevant documents from multiple countries and global organizations. Key content related to SDoH was extracted from the documents, and a content analysis was conducted to identify seven different SDoH domains (i.e., target audience, SDoH inclusion, addressing health inequities, SDoH-related key performance indicators, data collection on SDoH, interoperability standards, and data privacy and security). Data were aggregated at the global and continental levels to integrate and synthesize information from different countries and regions.

RESULTS

A total of 28 digital health policies or strategies were identified across 16 international regions. The comparative analysis of health policies regarding SDoH reveals a pronounced disparity between the continental regions. Although the World Health Organization recognizes the significance of key performance indicators for monitoring SDoH and emphasizes the assessment of national digital health maturity, there's a noticeable lack of continent-specific policies reflecting these global initiatives at the continental level.

CONCLUSION

While some regional digital health strategies recognize SDoH, integration varies, and standardization is lacking. Future research should focus on data collection frameworks and comprehensive insights for policymakers.

Screening for Health-Related Social Needs and Collaboration With External Partners Among US Hospitals

Importance

In recent years, hospitals and health systems have reported increasing rates of screening for patients' individual and community social needs, but few studies have explored the national landscape of screening and interventions directed at addressing health-related social needs (HRSNs) and social determinants of health (SDOH).

Objective

To evaluate the associations of hospital characteristics and area-level socioeconomic indicators to quantify the presence and intensity of hospitals' screening practices, interventions, and collaborative external partnerships that seek to measure and ameliorate patients' HRSNs and SDOH.

Design, Setting, and Participants

This cross-sectional study used national data from the American Hospital Association Annual Survey Database for fiscal year 2020. General-service, acute-care, nonfederal hospitals were included in the study's final sample, representing nationally diverse hospital settings. Data were analyzed from July 2022 to February 2023.

Exposures

Organizational characteristics and area-level socioeconomic indicators.

Main Outcomes and Measures

The outcomes of interest were hospital-reported patient screening of and strategies to address 8 HRSNs and 14 external partnership types to address SDOH. Composite scores for screening practices and external partnership types were calculated, and ordinary least-square regression analyses tested associations of organizational characteristics with outcome measures.

Results

Of 2858 US hospital respondents (response rate, 67.0%), most hospitals (79.2%; 95% CI, 77.7%-80.7%) reported screening patients for at least 1 HRSN, with food insecurity or hunger needs (66.1%; 95% CI, 64.3%-67.8%) and interpersonal violence (66.4%; 95% CI, 64.7%-68.1%) being the most commonly screened social needs. Most hospitals (79.4%; 95% CI, 66.3%-69.7%) reported having strategies and programs to address patients' HRSNs; notably, most hospitals (52.8%; 95% CI, 51.0%-54.5%) had interventions for transportation barriers. Hospitals reported a mean of 4.03 (95% CI, 3.85-4.20) external partnership types to address SDOH and 5.69 (5.50-5.88) partnership types to address HRSNs, with local or state public health departments and health care practitioners outside of the health system being the most common. Hospitals with accountable care contracts (ACCs) and bundled payment programs (BPPs) reported higher screening practices (ACC: β = 1.03; SE = 0.13; BPP: β = 0.72; SE = 0.14), interventions (ACC: β = 1.45; SE = 0.12; BPP: β = 0.61; SE = 0.13), and external partnership types to address HRSNs (ACC: β = 2.07; SE = 0.23; BPP: β = 1.47; SE = 0.24) and SDOH (ACC: β = 2.64; SE = 0.20; BPP: β = 1.57; SE = 0.21). Compared with nonteaching, government-owned, and for-profit hospitals, teaching and nonprofit hospitals were also more likely to report more HRSN-directed activities. Patterns based on geographic and area-level socioeconomic indicators did not emerge.

Conclusions and Relevance

This cross-sectional study found that most US hospitals were screening patients for multiple HRSNs. Active participation in value-based care, teaching hospital status, and nonprofit status were the characteristics most consistently associated with greater overall screening activities and number of related partnership types. These results support previously posited associations about which types of hospitals were leading screening uptake and reinforce understanding of the role of hospital incentives in supporting health equity efforts.

"Addressing the bigger picture": A qualitative study of internal medicine patients' perspectives on social needs data collection and use

BACKGROUND

There is increasing interest in collecting sociodemographic and social needs data in hospital settings to inform patient care and health equity. However, few studies have examined inpatients' views on this data collection and what should be done to address social needs. This study describes internal medicine inpatients' perspectives on the collection and use of sociodemographic and social needs information.

METHODS

A qualitative interpretive description methodology was used. Semi-structured interviews were conducted with 18 patients admitted to a large academic hospital in Toronto, Canada. Participants were recruited using maximum variation sampling for diverse genders, races, and those with and without social needs. Interviews were coded using a predominantly inductive approach and a thematic analysis was conducted.

RESULTS

Patients expressed that sociodemographic and social needs data collection is important to offer actionable solutions to address their needs. Patients described a gap between their ideal care which would attend to social needs, versus the reality that hospital-based teams are faced with competing priorities and pressures that make it unfeasible to provide such care. They also believed that this data collection could facilitate more holistic, integrated care. Patients conveyed a need to have a trusting and transparent relationship with their provider to alleviate concerns surrounding bias, discrimination, and confidentiality. Lastly, they indicated that sociodemographic and social needs data could be useful to inform care, support research to inspire social change, and assist them with navigating community resources or creating in-hospital programs to address unmet social needs.

CONCLUSIONS

While the collection of sociodemographic and social needs information in hospital settings is generally acceptable, there were varied views on whether hospital staff should intervene, as their priority is medical care. The results can inform the implementation of social data collection and interventions in hospital settings.