Incorporating Social Determinants of Health in Electronic Health Records: Qualitative Study of Current Practices Among Top Vendors

Abstract

Background Social determinants of health (SDH) are increasingly seen as important to understanding patient health and identifying appropriate interventions to improve health outcomes in what is a complex interplay between health system-, community-, and individual-level factors. Objective The objective of the paper was to investigate the development of electronic health record (EHR) software products that allow health care providers to identify and address patients’ SDH in health care settings. Methods We conducted interviews with six EHR vendors with large market shares in both ambulatory and inpatient settings. We conducted thematic analysis of the interviews to (1) identify their motivations to develop such software products, (2) describe their products and uses, and (3) identify facilitators and challenges to collection and use of SDH data—through their products or otherwise—either at the point of care or in population health interventions. Results Our findings indicate that vendor systems and their functionalities are influenced by client demand and initiative, federal initiatives, and the vendors’ strategic vision about opportunities in the health care system. Among the small sample of vendors with large market shares, SDH is a new area for growth, and the vendors range in the number and sophistication of their SDH-related products. To enable better data analytics, population health management, and interoperability of SDH data, vendors recognized the need for more standardization of SDH performance measures across various federal and state programs, better mapping of SDH measures to multiple types of codes, and development of more codes for all SDH measures of interest. Conclusions Vendors indicate they are actively developing products to facilitate the collection and use of SDH data for their clients and are seeking solutions to data standardization and interoperability challenges through internal product decisions and collaboration with policymakers. Due to a lack of policy standards around SDH data, product-specific decisions may end up being de facto policies given the market shares of particular vendors. However, commercial vendors appear ready to collaboratively discuss policy solutions such as standards or guidelines with each other, health care systems, and government agencies in order to further promote integration of SDH data into the standard of care for all health systems.

Artificial intelligence approaches to predicting and detecting cognitive decline in older adults: A conceptual review

“…ML algorithms can deal with very large numbers of potential input features (e.g., Nori et al, 2019) used over 10,000 clinical, pharmaceutical, and demographic variables) and rapidly develop predictive models without specific selection of variables, enabling automated selection of high value predictors. However, EHR data alone have relatively limited predictive power when analyzed in the absence of other social determinants of health (e.g., population-based sociodemographic data) (Freij et al, 2019).…”

“…Ongoing efforts to continually curate large-scale datasets like the ADNI and the UK Biobank databases will be key to the clinical success of AI, though they are costly and labor-intensive. Some claims and EHR companies are currently in search of feasible and legal ways to link these data with health risk assessments, sociodemographic data, and vital signs on a broad basis to create a more holistic picture of patients' health (Freij et al, 2019). Furthermore, large-scale availability of novel features may be limited by proven clinical utility.…”

Addressing Social Determinants of Health Within Healthcare Delivery Systems: a Framework to Ground and Inform Health Outcomes

“…instance, electronic health record (EHR) platforms including EPIC are increasingly incorporating unmet social need screening domains, data from which can identify who gets screened and document the unmet social needs that are identified. 38 Indicators of utilization (preventable hospitalizations, urgent care use) and adherence (prescription refills, appointment keeping) can be derived from administrative claims data. However, in two instances-patient connection to resources and unmet social need reduction-EHR and/or administrative data will be insufficient.…”

Including Social and Behavioral Determinants in Predictive Models: Trends, Challenges, and Opportunities

“…Once a single health care system renders SBDH data useful through advanced data science, they must find ways to disseminate these advances. The lack of standardization of SBDH data and collection processes prevents the interoperability and integration of modeling into diverse platforms [ 91 , 92 ] and impacts the creation of SBDH products for EHRs [ 94 ]. For greater interoperability, we need a standard, practical coding system for SBDH factors that goes beyond vendor-specific coding [ 91 , 92 ].…”