Hostname: page-component-586b7cd67f-t7fkt Total loading time: 0 Render date: 2024-11-22T07:33:07.710Z Has data issue: false hasContentIssue false

Realizing the potential of social determinants data in EHR systems: A scoping review of approaches for screening, linkage, extraction, analysis, and interventions

Published online by Cambridge University Press:  10 October 2024

Chenyu Li
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
Danielle L. Mowery
Affiliation:
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
Xiaomeng Ma
Affiliation:
Institute of Health Policy Management and Evaluations, University of Toronto, Toronto, ON, Canada
Rui Yang
Affiliation:
Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore
Ugurcan Vurgun
Affiliation:
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA
Sy Hwang
Affiliation:
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA
Hayoung K. Donnelly
Affiliation:
Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, USA
Harsh Bandhey
Affiliation:
Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Yalini Senathirajah
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
Shyam Visweswaran
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
Eugene M. Sadhu
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
Zohaib Akhtar
Affiliation:
Kellogg School of Management, Northwestern University, Evanston, IL, USA
Emily Getzen
Affiliation:
Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
Philip J. Freda
Affiliation:
Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
Qi Long
Affiliation:
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
Michael J. Becich*
Affiliation:
Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
*
Corresponding author: M. J. Becich; Email: [email protected]
Rights & Permissions [Opens in a new window]

Abstract

Background:

Social determinants of health (SDoH), such as socioeconomics and neighborhoods, strongly influence health outcomes. However, the current state of standardized SDoH data in electronic health records (EHRs) is lacking, a significant barrier to research and care quality.

Methods:

We conducted a PubMed search using “SDOH” and “EHR” Medical Subject Headings terms, analyzing included articles across five domains: 1) SDoH screening and assessment approaches, 2) SDoH data collection and documentation, 3) Use of natural language processing (NLP) for extracting SDoH, 4) SDoH data and health outcomes, and 5) SDoH-driven interventions.

Results:

Of 685 articles identified, 324 underwent full review. Key findings include implementation of tailored screening instruments, census and claims data linkage for contextual SDoH profiles, NLP systems extracting SDoH from notes, associations between SDoH and healthcare utilization and chronic disease control, and integrated care management programs. However, variability across data sources, tools, and outcomes underscores the need for standardization.

Discussion:

Despite progress in identifying patient social needs, further development of standards, predictive models, and coordinated interventions is critical for SDoH-EHR integration. Additional database searches could strengthen this scoping review. Ultimately, widespread capture, analysis, and translation of multidimensional SDoH data into clinical care is essential for promoting health equity.

Type
Review Article
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
Copyright
© The Author(s), 2024. Published by Cambridge University Press on behalf of Association for Clinical and Translational Science

Introduction

The concept of social determinants of health (SDoH) recognizes that health is shaped not only by biological factors or access to medical care but also by the social, economic, and physical conditions that shape people’s lives [Reference Braveman1]. Research in disciplines such as public health, sociology, economics, and medicine shows that the circumstances in which people live have a significant impact on shaping patterns of health and well-being [Reference Marmot2]. The World Health Organization (WHO) defines SDoH as “the conditions in which people are born, grow, live, work, and age, along with the wider set of forces and systems shaping the conditions of daily life” [3] (WHO SDoH concepts see Table 1). These determinants are broadly categorized into five interdependent domains that form the structural and social hierarchies in society: economic stability, neighborhood and built environment, health care access, education access and quality, and social and community context [4,5].

Table 1. World Health Organization (WHO)–Social Determinants of Health (SDoH) data components. EHR = electronic health record.

Specifically, adverse SDoH like poverty, unequal access to education, lack of public resources in neighborhoods, high crime rates, racial segregation, and pollution are all strongly associated with higher rates of morbidity, mortality, and health risk behaviors across populations [Reference Braveman1]. On the other hand, protective and promoting SDoH like higher household income, safe green spaces, strong social support, affordable nutrition options, and accessible transportation, have been linked to positive health indicators ranging from self-rated health status to lower diabetes and longer life expectancy [Reference Daniel, Bornstein and Kane6].

Health outcomes are greatly influenced by more than just clinical encounters; indeed, research suggests that only about 20% of a person’s health outcomes can be attributed to clinical care [Reference Whitman, De Lew, Chappel, Aysola, Zuckerman and Sommers7,Reference Hood, Gennuso, Swain and Catlin8], the majority of health outcomes are determined by a combination of individual behaviors and various external factors that are collectively referred to as SDoH. These “causes of the causes” of health are estimated to account for up to 55% of population health variation in high-income countries, though some estimates suggest they may account for as much as 70–80% [Reference Hood, Gennuso, Swain and Catlin8]. Aspects of physical environment, socioeconomic status, race, and gender contribute to systemic inequities that manifest as adverse outcomes. This makes social determinants fundamental considerations for achieving health equity and improving overall population health [Reference Braveman1].

SDoH-driven translational research: deriving and translating health data to actionable knowledge into clinical care

Incorporating SDoH into clinical practice is essential for health equity, but these determinants are rarely consistently recorded in electronic health records (EHRs). Researchers have implemented various approaches to standardize SDoH data collection, study the generated data, and apply the knowledge to improve care (see Fig. 1). SDoH data, collected from surveys [9], EHR modules [Reference Rogers, Parulekar, Malik and Torres10], and patient-reported outcomes [Reference Zulman, Maciejewski and Grubber11], can be aggregated into a unified repository for targeted research. However, data collection, integration, and utility remain inconsistent across systems. To be useful, data must be integrated and standardized using ontologies [Reference Dang, Li and Hu12], common representations [Reference Phuong, Zampino and Dobbins13], and value sets [14]. Integrated SDoH data can be studied with health outcomes and linked to programs [Reference Kessler, Bauer and Bishop15]. Leveraging SDoH data in EHRs can activate embedded tools like alerts and flags, such as guiding interventions like nutrition assistance based on hunger scores [Reference Gattu, Paik, Wang, Ray, Lichenstein and Black16], referring patients to community health workers for those in disadvantaged neighborhoods [Reference Johnson, Saavedra and Sun17], and creating high-risk patient panels for targeted care [Reference Navathe, Zhong and Lei18]. This integration facilitates personalized care management and health equity through patient-centric technologies [Reference Amarashingham, Xie, Karam, Nguyen and Kapoor19,Reference Parmar, Ryu, Pandya, Sedoc and Agarwal20], fostering a learning health system.

Figure 1. Data-to-knowledge-to-action workflow for translating social determinants of health (SDoH) into clinical care. EHR = electronic health record.

Challenges and barriers

Integrating SDoH data into EHRs is crucial for promoting health equity, but significant barriers exist [3,Reference Gottlieb, Tobey, Cantor, Hessler and Adler21]. Key challenges include incomplete and inconsistent data in structured fields [Reference Gottlieb, Tobey, Cantor, Hessler and Adler21,Reference Harle, Wu and Vest22], varying screening tools and data standards limiting interoperability [Reference Wetta, Severin and Gruhler23], and difficulties in consistently gathering and updating SDoH data due to clinical and administrative workflows [Reference Whitman, De Lew, Chappel, Aysola, Zuckerman and Sommers7].

Confidentiality rules and patient mistrust regarding information sharing also hinder SDoH data sharing [24]. Privacy-preserving tools like DeGAUSS [Reference Ryan, Brokamp and Blossom25] offer a promising approach by enabling secure and privacy-preserving sharing of SDoH data through geographical aggregation and statistical noise. However, the adoption of such tools may face challenges related to organizational policies, data governance, and stakeholder trust. Addressing these issues requires a multi-pronged approach involving policy change, system redesign, and community engagement [Reference Brokamp, Wolfe, Lingren, Harley and Ryan26].

Studies have shown that SDoH factors are commonly discussed in clinical encounters but rarely documented in structured fields, consistent with gaps in systematic SDoH data capture in EHRs [Reference Gold, Bunce and Cowburn27]. While natural language processing (NLP) approaches can help extract SDoH data from free-text notes, a more robust data collection and integration framework is needed. Connecting patients experiencing SDoH to relevant programs and services is critical, but determining patient eligibility and accessibility can be challenging. Clinical decision support systems and digital health technologies can assist healthcare professionals in making appropriate recommendations [Reference Hwang, Urbanowicz and Lynch28].

Our scoping review addresses the lack of a comprehensive understanding of SDoH-EHR integration by providing an integrated framework spanning data capture, analytics, and applications. We aim to identify best practices, gaps, and future directions by addressing key questions related to standardized tools, external data linkage, NLP methods, and the impact of harmonized SDoH data on health outcomes and interventions.

Method

Scoping literature review

We conducted a scoping review to explore the current landscape of SDoH data integration into EHRs. Scoping reviews are particularly useful for examining emerging evidence when the specific questions that can be addressed by a more precise systematic review are not yet clear [Reference Munn, Peters, Stern, Tufanaru, McArthur and Aromataris29Reference Peters, Godfrey, Khalil, McInerney, Parker and Soares31]. The five predetermined focus areas aligned with the SDoH research pipeline and key steps in SDoH-EHR integration, spanning from data capture to analytics and applications. These areas guided the analysis of included studies, and our approach is consistent with the methodological framework for scoping reviews.

Search strategy

The literature search was conducted in PubMed, a widely recognized database for biomedical literature, on 2023 May 8th. We utilized Medical Subject Headings (MeSH) terms to refine our search, focusing on articles indexed with terms “Electronic Health Records” and “Social Determinants of Health.” This combination was chosen to specifically target studies that discuss the intersection of EHRs with SDoH (Search strategy see Supplement Table 1 in Supplementary Material 1).

Screening and selection process

The screening process involved three phases. In phase one, papers were categorized into five non-mutually exclusive topics (depicted in Fig. 2):

  • SDoH Screening Tools and Assessments: Papers discussing various tools and methodologies for screening SDoH.

  • SDoH Data Collection and Documentation: Studies focusing on how SDoH data are collected and documented within EHR systems.

  • Use of NLP for SDoH: Research exploring the application of NLP techniques to identify and extract SDoH information from unstructured EHR data.

  • Associations between SDoH and Health Outcomes: Papers examining the relationship between SDoH and various health outcomes.

  • SDoH Interventions: Studies that evaluate the effectiveness of interventions aimed at addressing SDoH within healthcare settings.

In phase two, aligned with PRISMA guidelines [Reference Tricco, Lillie and Zarin32], the screening process involved an initial title/abstract review phase led by author C.L. (criteria see Supplement Table 2 in Supplementary Material 1) to categorize papers into one or more of the 5 topics. Targeted metadata extraction was performed by assigned reviewers as follows: Screening Assessments (R.Y.), SDoH Data Collection (C.L.), NLP Approaches (C.L.), and Interventions (X.M.). The SDoH and Outcomes papers were randomly assigned to the broader reviewer pool (C.L., R.Y., S.H., D.L.M., U.V., H.K.D.) for metadata extraction. Additional irrelevant studies were excluded in this second phase. The full-text metadata extraction phase allowed confirmation of accurate categorization and extraction, with discrepancies resolved through consensus meetings. Evidence synthesis leads included: C.L. for SDoH Screening tools and SDoH and health outcomes, D.L.M for SDoH Data collection, NLP for SDoH, X.M. for SDoH Interventions, overseen by senior authors M.J.M. and D.L.M.

Figure 2. Five social determinants of health categories describing the data workflow from data capture efforts to interventions. EHR = electronic health records; NLP = natural language processing.

In phase three, senior authors conducted evidence synthesis and conflict resolution, validating phase one and two results. The PRISMA flow diagram [Reference Tricco, Lillie and Zarin32] was used to depict the screening process.

The multi-stage process with independent categorization, full-text metadata extraction, and consensus meetings embedded quality checks aligning with scoping review best practices.

Results

In this section, we present the findings of SDoH in the EHR according to five domains of interest.

Data collection and synthesis

We identified a total of 685 articles through the PubMed query. After reviewing the titles and abstracts screening, 415 articles were included. Of these 415 articles, 324 articles included full text for qualitative synthesis. The reviewed articles were then classified according to SDoH in the EHR domains. The majority of articles focused on SDoH and health outcomes, SDoH data collection and documentation followed by NLP for SDoH, and SDoH screening tools and assessments. In the following sections, we reviewed the major themes and highlighted works for each of the five SDoH in the EHR domains (see Fig. 3, percentage see Supplement Table 3 in Supplementary Material 1).

Figure 3. PRISMA 2020 flow diagram. EHR = electronic health records; NLP = natural language processing.

SDoH screening tools

We included 29 papers (details see Supplement Material 2 – Meta Data) incorporating SDoH Screening tools into EHRs in our review. The majority of the studies utilized homegrown tools for screening SDoH, reflecting the need for tailored approaches and the limitations of existing standardized tools in certain contexts Some studies [Reference Gold, Bunce and Cowburn27,Reference Graif, Meurer and Fontana33Reference Barton, Parke and White35] developed their own questionnaires and screening sets, reflecting a trend toward customized tools tailored to specific healthcare settings or populations. Vendor-specific tools, like the two-item screening tool [Reference Gore, DiTursi, Rambuss, Pope-Collins and Train36] integrated into Epic SDoH Wheel, were less common but still present. The screened determinants varied, but common factors included housing, food insecurity, transportation, and mental health indicators like stress and depression.

Studies targeted a diverse range of populations. For example, children were the focus in some studies [Reference Graif, Meurer and Fontana33,Reference Vasan, Kenyon and Palakshappa37], while adults were the primary subjects in other studies [Reference Bechtel, Jones, Kue and Ford34,Reference Berkowitz, Bui and Shen38]. Various healthcare settings were represented, from primary care clinics [Reference Meyer, Lerner, Phillips and Zumwalt39,Reference Nohria, Xiao and Guardado40] to emergency departments [Reference Wallace, Luther, Guo, Wang, Sisler and Wong41], as well as school-based clinics [Reference Barton, Parke and White35]. This diversity indicates the widespread recognition of SDoH’s importance across different medical environments, underscoring its growing relevance throughout the healthcare spectrum.

Active screening methods, where healthcare providers proactively administered questionnaires or interviews, were predominant (n = 28) [Reference Gold, Bunce and Cowburn27,Reference Bechtel, Jones, Kue and Ford34]. Passive methods like the analysis of EHR data [Reference Hatef, Rouhizadeh and Tia42] were less common. However, the utilization of EHR data for passive screening indicates a potential to streamline the process in the future. While many studies focused on personal health determinants (n = 19), others also assessed structural determinants like housing quality and social networks [Reference Graif, Meurer and Fontana33,Reference Nohria, Xiao and Guardado40,Reference Chukmaitov, Dahman and Garland43]. A limited number of studies (n = 8) investigated both personal and structural determinants.

The heatmap (Fig. 4) shows EHRs as the dominant data source, with surveys, interviews, and ICD codes used for specific elements. Free text fields were underutilized, suggesting an opportunity for leveraging unstructured data. Housing was studied through the most diverse methods. The heatmap highlights the importance of EHRs and the need for diverse, integrated approaches.

Figure 4. Heatmap showing the frequency of association between the top 10 social determinants of health (SDoH) elements and the top five data collection methods.

Challenges and opportunities

The reviewed studies collectively highlight the challenges in standardizing SDoH screening across various contexts but also point toward the potential benefits of such screenings to patient care. The diversity in approaches reflects the complexity of addressing SDoH in clinical practice. However, it also demonstrates a concerted effort toward more comprehensive patient care. The prevalence of homegrown tools [Reference Graif, Meurer and Fontana33,Reference Barton, Parke and White35,Reference Nohria, Xiao and Guardado40,Reference Yazar, Kang, Ha, Dawson and Dawson44], indicates a trend toward customization, tailored to specific patient populations and healthcare settings. This is likely due to the unique needs and circumstances of different patient demographics. The variability in tools and approaches (e.g., the number of questions in studies [Reference Gold, Bunce and Cowburn27,Reference Okafor, Chiu and Feinn45], and the use of paper-based vs. EHR-based tools [Reference Bechtel, Jones, Kue and Ford34,Reference Meyer, Lerner, Phillips and Zumwalt39] highlight the challenges in standardizing SDoH screening. This variability could impact the comparability of data and the scalability of successful approaches. Despite the challenges, the focus on SDoH screening illustrates a shift toward more personalized patient care. Recognizing and addressing social and behavioral factors [Reference Barton, Parke and White35,Reference Herrera, Fiori, Archer-Dyer, Lounsbury and Wylie-Rrosett46] can lead to more effective healthcare interventions and better health outcomes.

SDoH data collection and documentation

In our review, we identified 76 articles (see Supplement Material 2 – Meta Data) describing SDoH data collection and documentation practices. These studies focused on engagement with populations and leveraged a variety of technologies to support collection and documentation processes.

The reviewed studies demonstrated that various technologies were employed to support the collection and documentation of SDoH data. Screening tools and questionnaires were also commonly used, often integrated directly into the EHR system. For example, Boston Medical Center’s THRIVE tool [Reference de la Vega, Losi and Sprague Martinez47] utilized a paper screening form that was entered into the EHR by medical assistants, while the University of California, San Diego [Reference Lee, Saseendrakumar and Nayak48] used a local EHR database (Epic) to collect SDoH data through ICD codes and discrete data fields. The OCHIN network of community health centers [Reference Gruß, Bunce, Davis, Dambrun, Cottrell and Gold49] developed an EHR-based screening questionnaire to assess various SDoH domains, and Wake Forest School of Medicine [Reference Palakshappa, Benefield and Furgurson50] employed a tablet-based digital health system to screen for food security, housing, and transportation needs.

In addition to EHRs and screening tools, some studies leveraged web-based platforms and applications for SDoH data collection. For instance, the COMPASS-CP study[Reference Duncan, Abbott and Rushing51] used a web-based application and iPad application to capture patient-reported outcomes related to physical, mental, and social well-being, as well as financial challenges and caregiver needs.

NLP techniques were also employed to extract SDoH information from unstructured EHR data. The OSF HealthCare System[Reference Stewart de Ramirez, Shallat, McClure, Foulger and Barenblat52] utilized the Pieces NLP system to identify SDoH factors from EHR notes, demonstrating the potential of NLP in automating the extraction of SDoH data from free-text clinical documentation.

Furthermore, studies used geocoding techniques to link patient addresses with external data sources, such as census tract socioeconomic data and community-level characteristics. The Envirome Web Service [Reference Kane, Wang and Gerkovich53], developed by Children’s Mercy Hospital, integrated census tract data with patient EHRs using real-time geocoding, enabling a more comprehensive understanding of patients’ social and environmental contexts.

Our review identified diverse methods for SDoH data collection and integration. Nine studies incorporated qualitative approaches, including interviews with patients and clinicians, community engagement initiatives, focus groups, and town hall meetings [Reference Potharaju, Fields and Cemballi54Reference Duberstein, Brunner and Panisch62]. These methods provided rich, contextual information about SDoH factors and their impacts on health outcomes.

Technology-assisted collection methods were also prevalent, with seven studies utilizing various tools for SDoH data gathering. These included paper-based entry, iPads/tablets, patient or clinician-facing web portals, and other web-based toolkits and forms [Reference Palakshappa, Benefield and Furgurson50,Reference Duncan, Abbott and Rushing51,Reference Gold, Bunce and Cottrell63Reference Arevian, Springgate and Jones67].

Several studies (n = 6) made use of publicly available, external data resources to infer structural SDoH information for a given population. The most common external SDoH data sources linked to EHRs were US census and community survey data (at both patient/individual and area/neighborhood levels), administrative data/claims records, and disease registries. Commonly linked community surveys and systems include the Behavioral Risk Factor Surveillance System, the National Health and Nutrition Examination Survey, the National Health Interview Survey [Reference Melton, Manaktala, Sarkar and Chen68], the National Institutes of Health PROMIS® (Patient-Reported Outcomes Measurement Information System) [Reference Aghdaee, Gu, Sinha, Parkinson, Sharma and Cutler69], the National Survey of Children’s Health [70], the Center for Disease Control Youth Risk Behavior Surveillance System [Reference Ettinger, Landsittel and Abebe71], the Center for Medicare and Medicaid Services (CMS) Accountable Health Communities’ Health-Related Social Needs Screening Tool [Reference Trinacty, LaWall, Ashton, Taira, Seto and Sentell72], the National Center for Education Statistics, the Uniform Crime Reports, and the American Community Survey [Reference Cottrell, Hendricks and Dambrun73Reference Udalova, Carey and Chelminski76]. Longitudinal study data included the National Longitudinal Study of Adolescent to Adult Health (Add Health) [Reference Sacco, Chen, Wang and Aseltine77]. Other administrative data sources included the Healthcare Cost & Utilization Project (HCUP) Nationwide Readmissions Database [Reference Gottlieb, Tirozzi, Manchanda, Burns and Sandel78], claims data [Reference McCormack and Madlock-Brown79], and Medicaid data warehouse [Reference Hewner, Casucci and Sullivan80]. Few studies describe use of disease-specific registries e.g. cancer registries such as SEER-CMS, SEER-Medicare, and SEER-Medicaid [Reference Dusetzina PhD, Enewold Mph PhD, Gentile PhD, Ramsey Md PhD and Halpern81]. While these sources may not directly capture SDoH information, they can provide proxy measures related to healthcare utilization patterns, access to care, and socioeconomic status. However, the use of administrative and claims data for SDoH analysis has limitations, as they may lack the granularity and specificity of data collected directly from patients or through dedicated SDoH screening tools.

Eight studies describe methods for inferring structural SDoH using geocoding of patient addresses and linking to public census tract data [Reference Kane, Wang and Gerkovich53,Reference Van Brunt66,Reference Biro, Williamson and Leggett82,Reference Comer, Grannis, Dixon, Bodenhamer and Wiehe83] These studies employed various geocoding techniques to convert patient addresses into geographic coordinates, which could then be mapped to specific census tracts or other geographic units. For example, the Envirome Web Service, developed by Children’s Mercy Hospital, used real-time geocoding to link patient addresses with census tract data [Reference Kane, Wang and Gerkovich53]. This geocoding approach enabled the integration of information related to neighborhood and community-level characteristics (e.g., SES, crime incidence, and health facility locations) [Reference Gardner, Pedersen, Campbell and McClay74,Reference Hughes, Phillips, DeVoe and Bazemore85,Reference Bazemore, Cottrell and Gold86] and neighborhood factors (e.g., poverty level, education, employment status, etc.) [Reference de la Vega, Losi and Sprague Martinez47,Reference Lee, Saseendrakumar and Nayak48,Reference Kane, Wang and Gerkovich53,Reference Melton, Manaktala, Sarkar and Chen68,Reference Luijks, van Boven, olde Hartman, Uijen, van Weel and Schers87Reference Rousseau, Oliveira, Tierney and Khurshid89]. By linking patient locations to area-level SDoH data, these studies were able to provide a more comprehensive understanding of patients’ social and environmental contexts, even when individual-level SDoH data were not available in the EHR.

External data provided various socioeconomic factors (income, education, employment, poverty level, air quality), neighborhood variables (segregation, safety, and walkability), and health behaviors (diet, exercise, and smoking) [Reference de la Vega, Losi and Sprague Martinez47Reference Gruß, Bunce, Davis, Dambrun, Cottrell and Gold49,Reference Stewart de Ramirez, Shallat, McClure, Foulger and Barenblat52,Reference Potharaju, Fields and Cemballi54,Reference McCormack and Madlock-Brown79,Reference Wang, Pantell, Gottlieb and Adler-Milstein90Reference Freij, Dullabh, Lewis, Smith, Hovey and Dhopeshwarkar97]. These complemented and expanded the individual-level SDoH data (food/housing security, transportation, interpersonal violence, etc.) captured directly in EHRs [Reference Tenenbaum, Christian and Cornish98Reference Ofili, Schanberg and Hutchinson100]. A small subset of studies (n = 3) aimed to integrate EHR, genomic, and public health data to examine the intersection of lifestyle, genetics, and environmental influences [Reference Lee, Saseendrakumar and Nayak48,Reference Kyriazis, Autexier and Brondino101,Reference Khatib, Li, Glowacki and Siddiqi102].

Challenges and opportunities

Although these works highlight the potential for study of personal and structural SDoH, there is considerable effort for systematically collecting, linking, and analyzing SDoH data from external sources together with EHR data at the community, state, and national levels [Reference Smith, Gigot and Harburn103,Reference Cook, Espinoza and Weiskopf104]. The adoption of common data models to improve standardization and interoperability of collected SDoH data remains limited [Reference Lindemann, Chen, Wang, Skube and Melton105]. Moreover, there is a scarcity of research demonstrating how this integrated information could be leveraged to connect individuals with identified SDoH risk factors to appropriate social programs.

NLP in SDoH

In our review, we identified 36 articles (details see Supplement Material 2 – Meta Data). describing NLP methods for powering SDoH studies. Many SDoH elements are captured in clinical free-text notes, such as progress notes, discharge summaries, and social work assessments. These unstructured data often contain rich, contextual information about patients’ social circumstances that may not be fully captured in structured fields. For example, free text might include detailed descriptions of a patient’s living situation, family dynamics, or barriers to accessing care. In contrast, structured data elements typically consist of predefined fields or checkboxes in the EHR, such as standardized screening questionnaires or ICD-10 Z-codes for social factors [Reference Dorr, Quiñones, King, Wei, White and Bejan106Reference Dorr, Bejan, Pizzimenti, Singh, Storer and Quinones108]. The use of NLP techniques is crucial for extracting and analyzing SDoH information from these unstructured sources, as it allows researchers to access a wealth of data that might otherwise remain untapped. NLP can identify mentions of social factors, assess their relevance, and even determine the severity or impact of these factors on the patient’s health.

Several studies focused on lexicon development using methods such as lexical associations, word embeddings, term similarity, and query expansion. Lexicons and regular expressions have been demonstrated to extract SDoH and psychosocial risk factors [Reference Navathe, Zhong and Lei18,Reference Conway, Keyhani and Christensen109Reference Morrow, Zamora-Resendiz and Beckham112], learn distinct social risk factors by mapping them to standard vocabularies and code sets including ICD-9/10, ICD Z codes, Unified Medical Language System, and SNOMED-CT. Most articles (n = 15) describe rule-based approaches using regular expressions and/or hybrid machine learning methods leveraging platforms. Five articles highlighted well-known rule-based toolkits and platforms adapted with lexicons and regular expressions for SDoH extraction including Moonstone, Easy Clinical Information Extraction System, Medical Text Extraction, Reasoning and Mapping System, Queriable Patient Inference Dossier, and Clinical Event Recognizer [Reference Navathe, Zhong and Lei18,Reference Conway, Keyhani and Christensen109Reference Morrow, Zamora-Resendiz and Beckham112]. Other articles (n = 7) describe rule-based systems paired with traditional machine learning approaches i.e., an ensemble, particularly using NLP systems such as General Architecture for Text Engineering, Clinical Language Annotation, Modeling, and Processing Toolkit, Extract SDOH from EHRs, Yale clinical Text Analysis and Knowledge Extraction System, Relative Housing Stability in Electronic Documentation, and toolkits such as spaCy and medspaCy in conjunction with conditional random fields and support vector machines (SVM) [Reference Chilman, Song and Roberts113Reference Wang, Long and McGinnis116]. In contrast, several investigators have leveraged open-source NLP toolkits like spaCy and medspaCy without supervised learners to extract SDoH variables [Reference Hatef, Rouhizadeh and Nau117Reference Chapman, Jones and Kelley119]. Other studies (n = 19) have solely leveraged traditional supervised and unsupervised learning techniques, SVM, logistic regression (LR), Naïve Bayes, Adaboost, Random Forest, XGBoost, Bio-ClinicalBERT, Latent Dirichlet Allocation, and bidirectional long short-term memory [Reference Vaswani, Shazeer and Parmar125] to extract and standardize social and behavioral determinants of health (SBDoH), e.g., alcohol abuse, drug use, sexual orientation, homelessness, substance use, sexual history, HIV status, drug use, housing status, transportation needs, housing insecurity, food insecurity, financial insecurity, employment/income insecurity, insurance insecurity, and poor social support. In more recent years, nine studies have focused on the training and tuning of deep learning approaches, primarily transformer-based [Reference Yu, Yang, Guo, Bian and Wu126Reference Han, Zhang and Shi135] approaches i.e., Bidirectional Encoder Representations from Transformers (BERT), RoBERTa, BioClinical-BERT models for extracting SBDoHs including relationship status, social status, family history, employment status, race/ethnicity, gender, social history, sexual orientation, diet, alcohol, smoking housing insecurity, unemployment, social isolation, and illicit drug use—from clinical notes, PubMed, among other specialized texts, e.g., LitCOVID [Reference Yu, Yang, Guo, Bian and Wu126Reference Han, Zhang and Shi135]. The frequency of papers for SDoH extraction NLP algorithms within EHR systems, highlighting the combinations and intersections of utilized methodologies can be found in Fig. 5.

Figure 5. UpSet Plot of natural language processing for social determinants of health (SDoH) algorithms ∼electronic health record (EHR) integration. *Outlining the distribution of papers in which each approach/method individually and in combination was described in the study. *Supervised machine learning includes traditional machine learning methods (naive bayes, support vector machine, logistic regression, random forest, etc), excluding neural networks and pretrained approaches.

Challenges and opportunities

Although these works highlight the potential for extracting SDoH from texts, several challenges remain. Few studies focused on lexicon development, make use of standard terminologies for encoding SDoH data, and explore deep extraction and representation of SDoH attributes and relationships. Also, many studies focus on extraction and encoding SDoH data from a single site and fail to assess the portability of methods to new textual data sources beyond clinical notes and PubMed articles such as digital technologies and chatbots. The introduction of shared datasets like the Social History Annotated Corpus is an important step toward demonstrating generalizability of NLP-powered, SDoH extraction systems. Emerging generative models may also improve upon the state-of-the-art demonstrated by common shared task datasets.

SDoH and health outcomes

In our review, we identified 164 articles (details see Supplement Material 2 – Meta Data). describing SDoH and health outcomes. SDoH and health outcome studies examined a wide variety of health-related events and outcomes in relation to SDoH factors. A predominant focus was on infectious disease outcomes, with 16 studies examining drivers of COVID-19 hospitalization, mortality, treatment disparities, and differences in positivity rates across social groups [Reference Holbert, Andersen, Stone, Pipkin, Turcotte and Patton140Reference Sills, Hall and Cutler149]. Another major category included healthcare utilization metrics like preventable hospital readmissions (n = 11) [Reference Holbert, Andersen, Stone, Pipkin, Turcotte and Patton140Reference Sills, Hall and Cutler149], ED reliance ( n = 16) [Reference Luo, Tong and Crotty173], and telehealth adoption [Reference Schwartz, Kolak and Pollak174Reference Ares-Blanco, Polentinos-Castro, Rodríguez-Cabrera, Gullón, Franco and Del Cura-González184]. Beyond infectious outcomes and healthcare utilization, studies also assessed chronic disease control across conditions like diabetes (n = 11) [Reference Schwartz, Kolak and Pollak174Reference Ares-Blanco, Polentinos-Castro, Rodríguez-Cabrera, Gullón, Franco and Del Cura-González184], hypertension [Reference DuBay, Su and Morinelli187,Reference Ghazi, Oakes, MacLehose, Luepker, Osypuk and Drawz188], kidney disease [Reference Tomayko, Flood, Tandias and Hanrahan150,Reference Cereijo, Gullón and Del Cura179,Reference Lange, Kompaniyets and Freedman189Reference Boone-Heinonen, Tillotson and O’Malley193], and obesity (n = 7) [Reference Hong, Nguyen and Lee171,Reference Nemirovsky, Klose and Wynne194Reference Sathe, Accordino, DeStephano, Shah, Wright and Hershman203], along with risk factors like elevated blood pressure and cardiovascular events. Some studies focused on cancer (n = 11) screening, diagnoses, treatment disparities, and survival outcomes [Reference Tomayko, Flood, Tandias and Hanrahan150Reference Avalos, Nance and Zhu155], while others addressed mental health (n = 6) indicators [Reference Hayes-Larson, Ikesu and Fong204] ranging from dementia incidence [Reference Alemi, Avramovic, Renshaw, Kanchi and Schwartz205,Reference Blosnich, Montgomery and Dichter206] to suicide (n = 2) risk factors [Reference Liu, Hung and Liang207,Reference Freeman, Stanhope, Wichmann, Jamieson and Boulet208]. Additional outcomes evaluated included maternal morbidity (n = 2) [Reference Lê-Scherban, Ballester and Castro177,Reference Cottrell, O’Malley and Dambrun209] and pediatric health metrics, ranging from vaccine completion rates to epilepsy-related consequences.

The most common quality measures reported were standardized condition control thresholds like HbA1c levels for diabetes control [Reference Chakravarthy, Stallings and Velez Edwards195], blood pressure (n = 5) levels for hypertension control, and established cancer staging guidelines [Reference Alemi, Avramovic, Renshaw, Kanchi and Schwartz205]. Some studies used validated risk prediction models for outcomes like hospital readmissions (n = 5), suicide risk [Reference Kind and Buckingham210,Reference Ryan Powell, Sheehy and Kind211], or mortality (n = 6). Beyond clinical indicators, several studies incorporated validated SDoH indexes like the Area Deprivation Index [212], Social Deprivation Index [213], and CDC’s Social Vulnerability Index [Reference Faison, Moon and Buckman163,Reference Nieuwenhuijse, Struijs, Sutch, Numans and Vos183,Reference Ares-Blanco, Polentinos-Castro, Rodríguez-Cabrera, Gullón, Franco and Del Cura-González184,Reference Otero, Scott, Martin and Huesing196,Reference Sathe, Accordino, DeStephano, Shah, Wright and Hershman203,Reference Gordon, Banegas and Tucker-Seeley214Reference Kapoor, Lynch and Lacson221]. In terms of analysis approaches, common methods included multivariate regression models like LR (n = 13) [Reference Johnson, Zhu and Garrard142,Reference Adie, Kats and Tlimat200,Reference Ahmad, Kong and Turner216] and Cox proportional hazards models (n = 3) [Reference Thompson, Sharma and Smith219] to assess adjusted outcome associations with SDoH factors. Other advanced techniques included machine learning algorithms [Reference Cobert, Lantos and Janko222], geospatial analysis for clustering [Reference Schlauch, Read, Koning, Neveux and Grzymski154], and phenome-wide association studies [Reference Egede, Walker and Linde223,Reference Eakin, Singleterry, Wang, Brown, Saynina and Walker224].

SDoH interventions

A total of 19 papers (details see Supplement Material 2 – Meta Data) collected supplementary SDoH data to support population health intervention initiatives targeting hospitals/clinics (n = 10) or communities (including primary care, n = 9) at the meso (institution) level. Two articles discussed policy potential and proposed policy reform at the macro (system) level [Reference Sokan, Stryckman and Liang225]. The majority of the selected research (n = 16) focused on implementing a social and healthcare-supportive program to address the social needs of the target population. Interventions were implemented in various settings for hospital-based initiatives, including posthospital discharge [Reference Tung, Abramsohn and Boyd226], the emergency department [Reference McCrae, Robinson, Spain, Byers and Axelrod227Reference Embick, Maeng and Juskiewicz231], and clinics specializing in different medical disciplines [Reference Sandel, Hansen and Kahn232Reference Berkowitz, Hulberg and Placzek235]. On the other hand, community-based initiatives concentrated mainly on integrating interventions into primary care services [Reference Henize, Beck, Klein, Adams and Kahn236,Reference Gyamfi, Cooper and Barber237].

The social and healthcare supportive programs included a range of initiatives designed toward improving community health. These initiatives encompassed the introduction of new healthcare programs [Reference Liu, Cruz, Gamcsik and Harris229,Reference Henize, Beck, Klein, Adams and Kahn236,Reference Emmert-Aronson, Grill, Trivedi, Markle and Chen238], health education and coaching [Reference Sandel, Hansen and Kahn232], the strengthening of medical-legal partnerships [Reference Krist, O’Loughlin and Woolf233,Reference Berkowitz, Hulberg and Placzek235,Reference Taber, Williams and Huang239], the enhancement of integrated care planning [Reference Tung, Abramsohn and Boyd226,Reference Battaglia, Freund and Haas240,Reference Loo, Anderson and Lin241] and the improvement of patient navigation [Reference McCrae, Robinson, Spain, Byers and Axelrod227,Reference Henize, Beck, Klein, Adams and Kahn236,Reference Emmert-Aronson, Grill, Trivedi, Markle and Chen238]. Only a few papers (n = 3) have examined the potential of incorporating the family or social support element into their intervention design [Reference Sokan, Stryckman and Liang225]. Meanwhile, four studies investigated the potential for enhancing resource allocation through surveying outcomes. The improvement objectives encompassed the allocation of staff and equipment [Reference Messmer, Brochier, Joseph, Tripodis and Garg228], the enhancement of patient navigation [Reference Mathias, Mahali and Agarwal230,Reference Zuckerman, Mourani and Smith242], and the transformation of health service practices [Reference Gyamfi, Cooper and Barber237].

Our review identified a range of target populations receiving SDoH interventions. Several interventions focused on specific demographic groups, including racial/ethnic minorities (e.g., Blacks for hypertension control) [Reference McCrae, Robinson, Spain, Byers and Axelrod227,Reference Messmer, Brochier, Joseph, Tripodis and Garg228], specific age groups (both pediatric and adult populations) [Reference Embick, Maeng and Juskiewicz231], and women’s health [Reference Sokan, Stryckman and Liang225]. Health condition-specific interventions were also common, targeting chronic diseases such as heart failure [Reference Gyamfi, Cooper and Barber237], COPD [Reference Krist, O’Loughlin and Woolf233], diabetes [Reference Mathias, Mahali and Agarwal230], and hypertension [Reference Embick, Maeng and Juskiewicz231,Reference Berkowitz, Hulberg and Placzek235], as well as mental health conditions [Reference Taber, Williams and Huang239] and specific diseases like lupus [Reference Hsu, Hertel and Johnson234,Reference Taber, Williams and Huang239,Reference Loo, Anderson and Lin241,Reference Zuckerman, Mourani and Smith242]. Many studies focused on vulnerable or underserved populations.

Health outcomes, such as improvements in health metrics, reductions in disease incidence, changes in vital signs, and quality of life, are commonly used as measures to determine the feasibility of initiating an intervention (n = 10). Several studies have also assessed social SDoH in relation to patient satisfaction and acceptability [Reference Alcaraz, Wiedt, Daniels, Yabroff, Guerra and Wender243Reference Dagenais, Russo, Madsen, Webster and Becnel245]. Since most programs were new efforts, it was not possible to determine the effectiveness of the intervention in the short term, nor could the potential generalizability be assessed.

Discussion

This scoping review set out to map SDoH-EHR integration literature across five key domains: structured data capture tools, external data linkage approaches, NLP-based extraction techniques, and applications for outcomes analysis, and health care interventions. Our results synthesized major themes and collective gaps within each sphere. Regarding our first aim, predominant tailored screening instruments enable assessment but standardization barriers persist. For the second objective, enriching patient profiles via claims and census linkage shows promise but systematic consolidation is lacking. On research question three, rule-based systems boast precision while neural networks improve unstructured element recognition – yet reproducibility hurdles remain. Finally, concerning predicting outcomes and targeting programs, consistent risk evidence conflicts with implementation uncertainty. Across the five domains, our review highlights the progress made in SDoH data integration, while also identifying critical gaps and challenges. We provide a comprehensive assessment of the current state of SDoH research, from data collection and analysis to the development and evaluation of interventions. Our findings underscore the need for standardized approaches, improved data interoperability, and more rigorous evaluation of SDoH interventions.

By synthesizing insights from diverse research areas, we offer a roadmap for advancing SDoH-EHR integration. This cross-domain perspective reveals the interdependencies between different aspects of SDoH research and practice, emphasizing the importance of a holistic, “full-stack” approach. Our review lays the foundation for future work in this field, guiding researchers and practitioners in their efforts to leverage SDoH data for promoting health equity and improving patient outcomes.

Key findings by theme

SDoH screening tools

The studies revealed variety of screening tools to assess patients’ SDoH across diverse healthcare settings. The most prevalent SDoH domains screened included housing instability, food insecurity, transportation and utility service needs, interpersonal safety, financial strain, social isolation, health literacy, and education level. Notably, the majority utilized homegrown instruments rather than standardized tools, with PRAPARE, National Academy of Medicine recommendations, and CMS Accountable Health Communities screening tool being the most commonly referenced standardized options.

These tools were tested across various settings, from primary care clinics to emergency departments and inpatient units. While most relied on active screening during visits, some explored passive methods like paper questionnaires or electronic tablets. The instruments primarily focused on individual-level SDoH, with a minority attempting to capture community or structural factors.

This widespread implementation reflects a growing recognition of upstream factors in shaping health outcomes. By systematically documenting social and environmental impacts on health, providers and researchers aim to address root causes of health disparities, aligning with population health management and preventive medicine principles.

Researchers found SDoH screening feasible and effective in identifying unmet social needs across diverse populations and implementation strategies. However, further research is warranted to develop optimal referral systems and interventions for identified needs, evaluate the impact of SDoH screening on patient outcomes, or develop evidence-based interventions that effectively address identified social needs. This will help to fully realize the potential of this upstream approach in improving overall health outcomes and reducing health disparities.

SDoH data collection and documentation

Our review reveals a rich landscape of SDoH data collection and integration efforts, as summarized in Table 2. The integration of external data sources with EHRs has significantly enhanced the capture of SDoH, providing critical information on socioeconomic position, neighborhood characteristics, and health behaviors [246]. This integration enables more holistic patient profiling, supporting risk stratification, outcomes studies, and health equity initiatives.

Table 2. Social Determinants of Health (SDoH)-driven translational research: deriving and translating actionable knowledge into clinical care. NLP = natural language processing.

The SDoH data collection efforts span a wide range of domains, from housing and food insecurity to education and employment status. The diversity of data sources – including census data, community surveys, and administrative claims – reflects the multifaceted nature of social determinants. However, this diversity also underscores the challenges in standardizing data collection and integration practices.

Several initiatives have been developed to address these challenges through the creation of common data elements (CDEs) and standardized models [247], including the Gravity Project [Reference Hamilton, Strader and Pratt248], the PhenX Toolkit [Reference Tesfaye, Cronin and Lopez-Class249], All of Us [250], and USCDI [250], and the extensions to the OMOP Common Data Model [Reference Gruß, Bunce, Davis, Dambrun, Cottrell and Gold49,Reference Fox251,Reference Yan, Chen and Wang252]. These efforts aim to enable consistent data collection, facilitating better understanding of SDoH contributions to health inequities and improving data sharing. However, a gap persists between available standardized elements and their implementation in practice, contributing to heterogeneity in SDoH data collection and documentation. Limited adoption of CDEs can be attributed to technical challenges in integrating new data structures into existing EHR systems, resource constraints, staff training needs, and the diverse nature of SDoH factors across populations and healthcare contexts.

Technical approaches for integrating external SDoH data with EHRs have employed geocoding of addresses, aggregation of community measures, and linkage based on unique identifiers. While progress has been made, further research must promote systematic collection, analysis, and application of integrated data sources. Key steps include implementing reliable linkage mechanisms for disparate datasets and embedding multidimensional patient social profiles within clinical decision tools and workflows [Reference Sawatzky, Kwon and Barclay253Reference McKneally, Dickens, Meslin and Singer255].

Only through purposeful integration and translation efforts can external SDoH data fully support identification of at-risk populations, patient-centered risk assessments, and targeted community-clinical interventions.

NLP in SDoH

A range of NLP approaches have been leveraged to identify critical social determinants from unstructured clinical notes. These methods can be broadly categorized into: 1. Rule-based systems using expert-curated lexicons and regular expressions; 2. Supervised machine learning models (e.g., convolutional neural networks, recurrent neural networks); 3. Advanced contextual embedding models (e.g., BERT).

Both generic NLP software libraries and custom systems tailored to social and behavioral health domains have been implemented. While reported accuracy metrics vary by model type and target social determinants, precision and recall generally exceed 80% for key factors like housing insecurity and occupations. Simpler models often demonstrate high precision, while recent neural networks improve sensitivity in capturing key entities from free-text fields.

Importantly, these NLP approaches recognize more patient social factors than structured EHR data alone, enabling richer risk assessments and interventions. However, challenges remain in standardization and integration into clinical workflows.

In the future, we can focus on developing better-standardized corpora for reusable NLP systems in social domains, integrating validated SDoH screening workflows into routine practice, improving ontologies and shareable custom systems, enhancing linkages to longitudinal outcomes, and conducting rigorous assessments of multi-sector SDoH interventions and their specific mechanisms of impact.

These efforts will facilitate more comprehensive and effective identification and addressing of SDoH across diverse populations.

SDoH and health outcomes

This review provides insights into current approaches and gaps in research on SDoH and health outcomes. Most studies were retrospective analyses examining links between social determinants and health issues, including neighborhood disadvantage, food and housing insecurity, healthcare access barriers, healthcare utilization, chronic illness control, and infectious diseases. A smaller number of studies assessed mental health, cancer, and mortality. This distribution of research focus highlights areas where more investigation is needed to provide a comprehensive understanding of SDoH impacts across all health domains.

COVID-19 has significantly impacted SDoH research, stimulating greater attention to health disparities. Studies consistently found higher COVID-19 risks and deaths among minorities, low-income groups, and those with prior conditions. Researchers leveraged diverse data sources, including medical records, census indices, and surveys, to quantify the disproportionate pandemic burden on disadvantaged groups. Some studies displayed sophisticated applications of predictive analytics and machine learning to model disease dynamics. This crisis has expanded SDoH data infrastructure and methodology while underscoring long-term disparities. Assessing pandemic response and recovery across social levels is critical, as disruptions may exacerbate existing health inequities among vulnerable groups.

Methodologically, regression modeling was commonly used to characterize adjusted outcome associations. However, more advanced analytics and predictive modeling were less prevalent. This gap presents an opportunity for more sophisticated computational research to uncover precise interactions between SDoH and health outcomes.

Moving forward, key areas for development include standardizing processes for SDoH data collection and integration into medical records, shifting from predominantly observational analyses to more interventional studies, and translating research findings into community initiatives for at-risk groups. Developing analytic guidelines to navigate the complexities of real-world SDoH data and creating standardized frameworks for SDoH data analysis in healthcare are also crucial.

These advancements are essential for health outcomes research, providing a foundation for more effective, evidence-based interventions and policies that consider the broad influences of social factors on health. By addressing these challenges, we can better leverage SDoH data to inform healthcare decisions and strategies, ultimately working toward reducing health disparities and improving population health.

SDoH interventions

Interventions addressing health care-related issues occur at micro (patient care), meso (healthcare institutions), and macro (healthcare policy) levels [Reference Midboe, Gray, Cheng, Okwara and Gale256,Reference Pfaff, Krohn and Crawley257]. Our review found that SDoH recognition primarily facilitates interventions at the meso level, including primary care and specialist referrals, patient navigation services, integrated care management, group education sessions, and resource allocation. Fewer studies reported macro-level policy changes or micro-level interventions emphasizing family/peer support and social connections for individual patients.

While many interventions showed some benefit, their generalizability was often limited due to narrow focus within single health systems (citation needed). This limitation is particularly relevant in the US, where health delivery systems are often fragmented into regional networks (citation needed). Implementing interventions for vulnerable populations presents unique challenges, as demographics vary across communities depending on cultural and geographical factors [Reference Small, Ong and Lewis258,Reference Silvola, Restelli, Bonfanti and Croce259].

Healthcare professionals must recognize that identifying SDoH within a community is only the initial stage. Establishing connections between individuals facing both health and social issues can be challenging due to various barriers. Building trust with vulnerable individuals is an ongoing process requiring sustained social and material support from healthcare professionals and community social workers. Creating effective regional support networks necessitates lasting partnerships with organizations possessing resources to address SDoH-related challenges, such as housing and transportation [24].

To enhance intervention effectiveness, mature plans with SDoH collection tools embedded in EHR systems should be adopted and tailored to the target population’s needs. Careful selection of platforms for survey distribution and data storage is crucial to prevent duplication of effort, ensure data integrity, and promote program sustainability. It’s imperative to collect intervention-informing data directly from the affected population. Incorporating patient feedback is essential for achieving optimal results. Pilot surveys can be used to pretest data collection instruments, allowing for refinement based on patient input. This collaborative approach helps create a more supportive environment for vulnerable individuals and mitigates unforeseen obstacles [Reference Brown, Ma and Miranda261].

Along with these methods, many interventions have been tried to help with known social problems and imbalances. Some of these are community health programs, help finding resources, patient navigation services, unified care management models, and educational meetings with peer support. Vulnerable groups have been given extra resources like more medical staff or tools in some studies. System-level policy changes have also been implemented to promote health equity [260].

Future research should focus on rigorous evaluation of health outcomes improvement to ensure the long-term success and widespread applicability of SDoH interventions [Reference Brown, Ma and Miranda261,Reference Gottfredson, Cook and Gardner262].

Cross-cutting insights

Despite progress in SDoH research and implementation, several challenges persist across domains. These challenges highlight the need for an integrated approach to advance the field.

Standardization remains a critical issue in SDoH integration. The current variability in screening tools, data collection methods, and documentation practices [Reference Holmes, Beinlich and Boland263] hinders comparability and generalizability of findings. There’s an urgent need for standardized corpora, data elements, and workflows across all aspects of SDoH integration to facilitate more robust and comparable research.

Data integration presents another significant challenge. Presently, expertise and data often reside in silos, with screening, linkage, extraction, analysis, and intervention programs operating independently [Reference Heacock, Lopez and Amolegbe264]. Breaking down these silos to create a comprehensive platform spanning from data collection to application is crucial for optimizing SDoH efforts. As research continues, embracing interoperable design principles and controlled evaluation around representative datasets, model transparency, and equitable outcomes remains vital [265].

Technological advancements offer both opportunities and challenges. While NLP and machine learning show promise in SDoH identification and analysis, their application remains limited. Few studies have employed advanced predictive modeling techniques, highlighting an area for growth. The recent exponential development in large language models (LLMs) presents new opportunities for SDoH entity recognition across contexts [Reference Guevara, Chen and Thomas266,Reference Clusmann, Kolbinger and Muti267].

Longitudinal studies are crucial for understanding the long-term impact of SDoH interventions. Enhanced linkages to longitudinal outcomes are needed to fully grasp the effects of interventions over time. This requires rethinking workflows to integrate contextual data into real-world utilities [Reference Gruß, Bunce, Davis, Dambrun, Cottrell and Gold49].

As the field evolves, embracing interoperable design principles, controlled evaluation around representative datasets, and a focus on equitable outcomes will be vital. The integration of advanced technologies like LLMs must be balanced with ethical considerations and rigorous validation to ensure their reliable and equitable application in SDoH contexts.

By addressing these cross-cutting issues, the field can move toward more comprehensive, effective, and equitable integration of SDoH in healthcare, ultimately improving population health outcomes and reducing health disparities.

Limitations

This scoping review faces certain limitations in comprehensively capturing the state of SDoH data integration into EHRs. Relying solely on PubMed for literature searches and limiting the results to English papers may introduce selection bias, omitting potentially relevant research indexed in other databases. Supplementing with sources like SCOPUS or Web of Science may have revealed additional insights and applications. Additionally, our search strategy relies on the MeSH terms “SDoH” and “EHR” in our search strategy. While using standardized subject headings helps retrieve relevant articles indexed in MEDLINE and PubMed, it may have limited the scope of our search. Future research could expand the search strategy to include specific SDoH factors and compare the results with our current findings. This approach may provide a more comprehensive understanding of the literature on SDoH and EHR integration, particularly for studies conducted before the widespread use of the term ‘SDoH’.

Due to resource constraints, the metadata extraction from the final set of included studies was completed by a single reviewer. Having dual independent extraction with consensus meetings is ideal to ensure accuracy and completeness of scoping review data abstractions. The feasibility and impact of implementing a second reader should be evaluated in future updates to strengthen robustness.

Our review methodology, which relies on published literature, may not fully capture the landscape of SDoH screening tools used in clinical practice. Many healthcare institutions have implemented SDoH screening within their EHR systems without publishing these efforts in academic literature. This gap between published research and actual clinical practice means our review may underestimate the prevalence and variety of SDoH screening tools in use. Our findings primarily reflect tools that have been reported in academic literature, which may disproportionately represent novel or custom-developed instruments rather than more commonly used, commercially available tools.

Finally, heterogeneity across settings, populations, tools, and outcomes creates complexity in evaluating SDoH-EHR integration maturity. Varying implementation stages and study designs introduce difficulty in benchmarking best practices. The scoping methodology prioritized inclusiveness over appraising integration quality, leaving gaps in assessing real-world effectiveness. Capturing nuanced, multidimensional integration processes by diverse healthcare systems persists as a challenge, though framework refinement helps structure insights.

Future research could benefit from alternative methodologies to capture a more comprehensive picture of SDoH screening practices and data integration. This might include surveys of healthcare institutions, analysis of EHR vendor data, or case studies of health systems’ unpublished screening practices. Such approaches could help bridge the gap between published literature and real-world implementation of SDoH screening tools and data integration practices.

Conclusion

Overall, while collecting patient social contexts shows immense potential to rectify health disparities, realizing these possibilities requires ongoing informatics innovation alongside economic investments and policy reforms targeting root societal drivers. This review contributes an evidence base for such continued progress in wisely applying multidimensional SDoH data to promote health equity.

The integration of SDoH data into healthcare practice holds transformative potential for addressing health disparities. Realizing this potential demands continued innovation, strategic investment, and policy evolution, guided by the evidence and insights garnered from comprehensive SDoH research.

Supplementary material

The supplementary material for this article can be found at https://doi.org/10.1017/cts.2024.571

Author contributions

M.J.B. C.L., and D.L.M: Conceptualized the study design and methodology. C.L., D.L.M., X.M., S.H., and M.J.B.: Led data synthesis and analysis as well as initial manuscript drafting. C.L., R.Y., S.H., D.L.M., U.V., H.K.D., and P.F.: Contributed to metadata extraction from selected articles. C.L., Z.A., and H.K.D.: Developed visualizations and tables to summarize key data. C.L., S.V., Y.S., E.S., P.F., and U.V. edited and refined the revised manuscript. All authors contributed intellectually to the interpretation of findings, critically revised the manuscript, gave final approval of the version to be published, and agreed to be accountable for the work.

Funding statement

We thank PaTH is a Network Partner in PCORnet® which has been developed with funding from the Patient-Centered Outcomes Research Institute® (PCORI®). PaTH’s participation in PCORnet is funded through PCORI Award RI-PITT-01-PS1 (MJB). We also thank the Clinical and Translational Science Institute at the University of Pittsburgh is supported by the National Institutes of Health (NIH) Clinical and Translational Science Award (CTSA) program, grant UL1 TR001857 (MJB). We also thank the National Institutes of Health for supporting this research: R01-HL162354 (DM), K24-HL167127-01A1 (DM), and P50MH127511 (DM).

Competing interests

There are no conflicts of interest to declare.

References

Braveman, P.Introduction: What Influences Health? And What Influences the Influences?’, The Social Determinants of Health and Health Disparities. Online edn. New YorkOxford Academic; 2023. doi: 10.1093/oso/9780190624118.003.0001.CrossRefGoogle Scholar
Marmot, M. Social determinants of health inequalities. Lancet. 2005;365(9464):10991104.CrossRefGoogle ScholarPubMed
WHO Commission on Social Determinants of Health, World Health Organization. Closing the Gap in a Generation: Health Equity Through Action on the Social Determinants of Health : Commission on Social Determinants of Health Final Report. World Health Organization; 2008. https://www.who.int/publications/i/item/WHO-IER-CSDH-08.1.Google Scholar
Social determinants of health. (https://health.gov/healthypeople/priority-areas/social-determinants-health) Accessed January 26, 2024.Google Scholar
Barragan, [d-Ca-44] ND. Improving Social Determinants of Health Act of 2021, 2021 (https://www.congress.gov/bill/117th-congress/house-bill/379/text) Accessed January 26, 2024.Google Scholar
Daniel, H, Bornstein, SS, Kane, GC, et al. Addressing social determinants to improve patient care and promote health equity: an American college of physicians position paper. Ann Intern Med, 2018;168(8):577578.CrossRefGoogle Scholar
Whitman, A, De Lew, N, Chappel, A, Aysola, V, Zuckerman, R, Sommers, BD. Addressing social determinants of health: Examples of successful evidence-based strategies and current federal efforts. (https://www.aspe.hhs.gov/sites/default/files/documents/e2b650cd64cf84aae8ff0fae7474af82/SDOH-Evidence-Review.pdf) Accessed January 26, 2024.Google Scholar
Hood, CM, Gennuso, KP, Swain, GR, Catlin, BB. County health rankings: relationships between determinant factors and health outcomes. Am J Prevent Med. 2016;50(2):129135.CrossRefGoogle ScholarPubMed
PRAPARE (https://prapare.org/) Accessed January 31, 2024.Google Scholar
Rogers, CK, Parulekar, M, Malik, F, Torres, CA. A local perspective into electronic health record design, integration, and implementation of screening and referral for social determinants of health. Perspect Health Inf Manag. 2022;19(Spring):1g.Google ScholarPubMed
Zulman, DM, Maciejewski, ML, Grubber, JM, et al. Patient-reported social and behavioral determinants of health and estimated risk of hospitalization in high-risk veterans affairs patients. JAMA Netw Open, 2020;3(10):e2021457.CrossRefGoogle ScholarPubMed
Dang, Y, Li, F, Hu, X, et al. Systematic design and data-driven evaluation of social determinants of health ontology (SDoHO). J Am Med Inform Assoc, 2023;30(9):14651473.CrossRefGoogle ScholarPubMed
Phuong, J, Zampino, E, Dobbins, N, et al. Extracting patient-level social determinants of health into the OMOP common data model. AMIA Annu Symp Proc. 2021:;2021, 989998.Google ScholarPubMed
HL7.FHIR.US.SDOH-CLINICALCARE\\gravity value sets - FHIR v4.0.1, 2024 (https://build.fhir.org/ig/HL7/fhir-sdoh-clinicalcare/gravity_terminology.html Google Scholar
Kessler, RC, Bauer, MS, Bishop, TM, et al. Evaluation of a model to target high-risk psychiatric inpatients for an intensive postdischarge suicide prevention intervention. JAMA Psychiatry, 2023;80(3):230240.CrossRefGoogle Scholar
Gattu, RK, Paik, G, Wang, Y, Ray, P, Lichenstein, R & Black, MM. The hunger vital sign identifies household food insecurity among children in emergency departments and primary care. Children. 2019;6(10):100107.CrossRefGoogle Scholar
Johnson, D, Saavedra, P, Sun, E, et al. Community health workers and medicaid managed care in New Mexico. J Community Health, 2012;37(3):563571.CrossRefGoogle ScholarPubMed
Navathe, AS, Zhong, F, Lei, VJ, et al. Hospital readmission and social risk factors identified from physician notes. Health Serv Res. 2018;53(2):11101136.CrossRefGoogle ScholarPubMed
Amarashingham, R, Xie, B, Karam, A, Nguyen, N, Kapoor, B. Using community partnerships to integrate health and social services for high-need, high-cost patients. Issue Brief. 2018:;2018:111.Google ScholarPubMed
Parmar, P, Ryu, J, Pandya, S, Sedoc, J, Agarwal, S. Health-focused conversational agents in person-centered care: a review of apps. NPJ Digit Med. 2022;5(1):21.CrossRefGoogle Scholar
Gottlieb, L, Tobey, R, Cantor, J, Hessler, D, Adler, NE. Integrating social and medical data to improve population health: opportunities and barriers. Health Aff. 2016;35(11):21162123.CrossRefGoogle Scholar
Harle, CA, Wu, W, Vest, JR. Accuracy of electronic health record food insecurity, housing instability, and financial strain screening in adult primary care. JAMA, 2023;329(5):423424.CrossRefGoogle ScholarPubMed
Wetta, RE, Severin, RD, Gruhler, H. An evidence-based strategy to achieve equivalency and interoperability for social-behavioral determinants of health assessment, storage, exchange, and use. Health Informat J, 2020;26(2):14771488.CrossRefGoogle ScholarPubMed
Domestic Policy Council, Office of Science and Technology Policy. The U.S. Playbook to Address Social Determinants of Health, 2023.Google Scholar
Ryan, PH, Brokamp, C, Blossom, J, et al. A distributed geospatial approach to describe community characteristics for multisite studies. J Clin Transl Sci. 2021;5(1):e86.CrossRefGoogle ScholarPubMed
Brokamp, C, Wolfe, C, Lingren, T, Harley, J, Ryan, P. Decentralized and reproducible geocoding and characterization of community and environmental exposures for multisite studies. J Am Med Inform Assoc. 2018;25(3):309314.CrossRefGoogle ScholarPubMed
Gold, R, Bunce, A, Cowburn, S, et al. Adoption of social determinants of health EHR tools by community health centers. Ann Fam Med. 2018;16(5):399407.CrossRefGoogle ScholarPubMed
Hwang, S, Urbanowicz, R, Lynch, S, et al. Toward predicting 30-day readmission among oncology patients: Identifying timely and actionable risk factors. JCO Clin Cancer Inform. 2023; 7:e2200097.Google Scholar
Munn, Z, Peters, MDJ, Stern, C, Tufanaru, C, McArthur, A, Aromataris, E. Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med Res Methodol. 2018;18(1):143.CrossRefGoogle ScholarPubMed
Arksey, H, O’Malley, L. Scoping studies: towards a methodological framework. Int J Soc Res Methodol. 2005;8(1):1932.CrossRefGoogle Scholar
Peters, MDJ, Godfrey, CM, Khalil, H, McInerney, P, Parker, D, Soares, CB. Guidance for conducting systematic scoping reviews. Int J Evid Based Healthc. 2015;13(3):141146.CrossRefGoogle ScholarPubMed
Tricco, AC, Lillie, E, Zarin, W, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med. 2018;169(7):467473.CrossRefGoogle ScholarPubMed
Graif, C, Meurer, J, Fontana, M. An ecological model to frame the delivery of pediatric preventive care. Pediatrics. 2021;148(Suppl 1):s13s20.CrossRefGoogle ScholarPubMed
Bechtel, N, Jones, A, Kue, J & Ford, JL. Evaluation of the core 5 social determinants of health screening tool. Public Health Nurs. 2022;39(2):438445.CrossRefGoogle Scholar
Barton, LR, Parke, KA, White, CL. Screening for the social and behavioral determinants of health at a school-based clinic. J Pediatr Health Care. 2019;33(5):537544.CrossRefGoogle Scholar
Gore, E, DiTursi, J, Rambuss, R, Pope-Collins, E, Train, MK. Implementing a process for screening hospitalized adults for food insecurity at a tertiary care center. J Healthc Qual. 2022;44(5):305312.CrossRefGoogle ScholarPubMed
Vasan, A, Kenyon, CC, Palakshappa, D. Differences in pediatric residents’ social needs screening practices across health care settings. Hosp Pediatr. 2020;10(5):443446.CrossRefGoogle ScholarPubMed
Berkowitz, RL, Bui, L, Shen, Z, et al. Evaluation of a social determinants of health screening questionnaire and workflow pilot within an adult ambulatory clinic. BMC Fam Pract. 2021;22(1):256.CrossRefGoogle ScholarPubMed
Meyer, D, Lerner, E, Phillips, A, Zumwalt, K. Universal screening of social determinants of health at a large US Academic Medical Center, 2018. Am J Public Health. 2020;110(S2):S219S221.CrossRefGoogle Scholar
Nohria, R, Xiao, N, Guardado, R, et al. Implementing health related social needs screening in an outpatient clinic. J Prim Care Community Health, 2022;, 13:21501319221118810.CrossRefGoogle Scholar
Wallace, AS, Luther, B, Guo, JW, Wang, CY, Sisler, S, Wong, B. Implementing a social determinants screening and referral infrastructure during routine emergency department visits, Utah, 2017-2018. Prev Chronic Dis. 2020;17:E45.CrossRefGoogle ScholarPubMed
Hatef, E, Rouhizadeh, M, Tia, I, et al. Assessing the availability of data on social and behavioral determinants in structured and unstructured electronic health records: a retrospective analysis of a multilevel health care system. JMIR Med Inform. 2019;7(3):e13802.CrossRefGoogle ScholarPubMed
Chukmaitov, A, Dahman, B, Garland, SL, et al. Addressing social risk factors in the inpatient setting: initial findings from a screening and referral pilot at an urban safety-net academic medical center in Virginia, USA. Prev Med Rep. 2022;29:101935.CrossRefGoogle ScholarPubMed
Yazar, V, Kang, SU, Ha, S, Dawson, VL & Dawson, TM. Integrative genome-wide analysis of dopaminergic neuron-specific PARIS expression in Drosophila dissects recognition of multiple PPAR-γ associated gene regulation. Sci Rep. 2021;11(1):21500.CrossRefGoogle ScholarPubMed
Okafor, M, Chiu, S & Feinn, R. Quantitative and qualitative results from implementation of a two-item food insecurity screening tool in healthcare settings in Connecticut. Prev Med Rep. 2020;20:10, 1191.Google ScholarPubMed
Herrera, T, Fiori, KP, Archer-Dyer, H, Lounsbury, DW & Wylie-Rrosett, J. Social determinants of health screening by preclinical medical students during the COVID-19 pandemic: service-based learning case study. JMIR Med Educ. 2022;8(1):e32818.CrossRefGoogle ScholarPubMed
de la Vega, PBuitron, Losi, S, Sprague Martinez, L, et al. Implementing an EHR-based screening and referral system to address social determinants of health in primary care. Med Care. 2019;57:S133S139.CrossRefGoogle Scholar
Lee, TC, Saseendrakumar, BR, Nayak, M, et al. Social determinants of health data availability for patients with eye conditions. Ophthalmol Sci. 2022;2(2):100151. doi: 10.1016/j.xops.2022.100151.CrossRefGoogle ScholarPubMed
Gruß, I, Bunce, A, Davis, J, Dambrun, K, Cottrell, E, Gold, R. Initiating and implementing social determinants of health data collection in community health centers. Popul Health Manag. 2021;24(1):5258.CrossRefGoogle ScholarPubMed
Palakshappa, D, Benefield, AJ, Furgurson, KF, et al. Feasibility of mobile technology to identify and address patients unmet social needs in a primary care clinic. Popul Health Manag. 2021;24(3):385392.Google Scholar
Duncan, PW, Abbott, RM, Rushing, S, et al. COMPASS-CP: an electronic application to capture patient-reported outcomes to develop actionable stroke and transient ischemic attack care plans. Circ Cardiovasc Qual Outcomes. 2018;11(8):e004444.CrossRefGoogle ScholarPubMed
Stewart de Ramirez, S, Shallat, J, McClure, K, Foulger, R, Barenblat, L. Screening for social determinants of health: active and passive information retrieval methods. Popul Health Manag. 2022;25(6):781788.CrossRefGoogle ScholarPubMed
Kane, NJ, Wang, X, Gerkovich, MM, et al. The envirome web service: patient context at the point of care. J Biomed Inform. 2021;119:103817.CrossRefGoogle ScholarPubMed
Potharaju, KA, Fields, JD, Cemballi, AG, et al. Assessing alignment of patient and clinician perspectives on community health resources for chronic disease management. Healthcare (Basel), 2022, 10(10).Google ScholarPubMed
Vale, MD. Perkins DW.Discuss and remember: clinician strategies for integrating social determinants of health in patient records and care. Soc Sci Med. 2022;315:115548.CrossRefGoogle ScholarPubMed
Senteio, C, Adler-Milstein, J, Richardson, C, Veinot, T. Psychosocial information use for clinical decisions in diabetes care. J Am Med Inform Assoc. 2019;26(8-9):813824.CrossRefGoogle ScholarPubMed
Hirsch, A, Durden, TE, Silva, J. Linking electronic health records and in-depth interviews to inform efforts to integrate social determinants of health into health care delivery: protocol for a qualitative research study. JMIR Res Protoc. 2022;11(3):e36201.CrossRefGoogle ScholarPubMed
Lasser, EC, Kim, JM, Hatef, E, Kharrazi, H, Marsteller, JA & DeCamp, LR. Social and behavioral variables in the electronic health record: a path forward to increase data quality and utility. Acad Med. 2021;96(7):10501056.CrossRefGoogle ScholarPubMed
Vatani, H, Sharma, H, Azhar, K, Kochendorfer, KM, Valenta, AL, Dunn Lopez, K. Required data elements for interprofessional rounds through the lens of multiple professions. J Interprof Care . 2024;38(3):453459. doi: 10.1080/13561820.2020.1832447.CrossRefGoogle ScholarPubMed
Nguyen, OK, Chan, CV, Makam, A, Stieglitz, H, Amarasingham, R. Envisioning a social-health information exchange as a platform to support a patient-centered medical neighborhood: a feasibility study. J Gen Intern Med. 2015;30(1):6067.CrossRefGoogle ScholarPubMed
Lindau, ST, Makelarski, J, Abramsohn, E, et al. CommunityRx: a population health improvement innovation that connects clinics to communities. Health Aff. 2016;35(11):20202029.CrossRefGoogle ScholarPubMed
Duberstein, ZT, Brunner, J, Panisch, LS, et al. The biopsychosocial model and perinatal health care: determinants of perinatal care in a community sample. Front Psychiatry. 2021;12:746803.CrossRefGoogle Scholar
Gold, R, Bunce, A, Cottrell, E, et al. Study protocol: a pragmatic, stepped-wedge trial of tailored support for implementing social determinants of health documentation/action in community health centers, with realist evaluation. Implement Sci. 2019;14(1):9.CrossRefGoogle ScholarPubMed
Sposito, RS & Selleck, C. Expanding data reporting capacity of free and charitable clinics: a quality improvement project. J Dr Nurs Pract. 2020;13(1):6470.Google ScholarPubMed
Sitapati, AM, Berkovich, B, Arellano, AM, et al. A case study of the 1115 waiver using population health informatics to address disparities. JAMIA Open, 2020;3(2):178184.CrossRefGoogle ScholarPubMed
Van Brunt, D. Community health records: Establishing a systematic approach to improving social and physical determinants of health. Am J Public Health. 2017;107(3):407412.CrossRefGoogle ScholarPubMed
Arevian, AC, Springgate, B, Jones, F, et al. The Community and Patient Partnered Research Network (CPPRN): application of patient-centered outcomes research to promote behavioral health equity. Ethn Dis. 2018;28(Suppl 2):295302.CrossRefGoogle Scholar
Melton, GB, Manaktala, S, Sarkar, IN & Chen, ES. Social and behavioral history information in public health datasets. AMIA Annu Symp Proc. 2012;2012: 625634.Google ScholarPubMed
Aghdaee, M, Gu, Y, Sinha, K, Parkinson, B, Sharma, R & Cutler, H. Mapping the patient-reported outcomes measurement information system (PROMIS-29) to EQ-5D-5L. Pharmacoeconomics. 2023;41(2):187198.CrossRefGoogle ScholarPubMed
National Survey of Children’s Health - Data Resource Center for Child and Adolescent Health. (https://www.childhealthdata.org/learn-about-the-nsch/NSCH). Accessed February 1, 2024.Google Scholar
Ettinger, AK, Landsittel, D, Abebe, KZ, et al. THRIVE conceptual framework and study protocol: a community-partnered longitudinal multi-cohort study to promote child and youth thriving, health equity, and community strength. Front Pediatr. 2021;9:797526.CrossRefGoogle ScholarPubMed
Trinacty, CM, LaWall, E, Ashton, M, Taira, D, Seto, TB, Sentell, T. Adding social determinants in the electronic health record in clinical care in Hawai’i: supporting community-clinical linkages in patient care. Hawaii J Med Public Health. 2019;78(6 Suppl 1):4651.Google ScholarPubMed
Cottrell, EK, Hendricks, M, Dambrun, K, et al. Comparison of community-level and patient-level social risk data in a network of community health centers. JAMA Netw Open. 2020;3(10):e20.16852.CrossRefGoogle Scholar
Gardner, BJ, Pedersen, JG, Campbell, ME, McClay, JC. Incorporating a location-based socioeconomic index into a de-identified i2b2 clinical data warehouse. J Am Med Inform Assoc. 2019;26(4):286293.CrossRefGoogle Scholar
Korzeniewski, SJ, Bezold, C, Carbone, JT, et al. The Population Health OutcomEs aNd Information EXchange (PHOENIX) program - a transformative approach to reduce the burden of chronic disease. Online J Public Health Inform. 2020;12(1):e3.CrossRefGoogle Scholar
Udalova, V, Carey, TS, Chelminski, PR, et al. Linking electronic health records to the American community survey: Feasibility and process. Am J Public Health. 2022;112(6):923930.CrossRefGoogle Scholar
Sacco, SJ, Chen, K, Wang, F & Aseltine, R. Target-based fusion using social determinants of health to enhance suicide prediction with electronic health records. PLoS One. 2023;18(4):e0. 283595.CrossRefGoogle ScholarPubMed
Gottlieb, LM, Tirozzi, KJ, Manchanda, R, Burns, AR, Sandel, MT. Moving electronic medical records upstream: incorporating social determinants of health. Am J Prev Med. 2015;48(2):215218.CrossRefGoogle ScholarPubMed
McCormack, LA & Madlock-Brown, C. Social determinant of health documentation trends and their association with emergency department admissions. AMIA Annu Symp Proc. 2020:823832.Google ScholarPubMed
Hewner, S, Casucci, S, Sullivan, S, et al. Integrating social determinants of health into primary care clinical and informational workflow during care transitions. eGEMS (Wash DC). 2017;5(2):2.Google ScholarPubMed
Dusetzina PhD, SB, Enewold Mph PhD, L, Gentile PhD, D, Ramsey Md PhD, SD, Halpern, MT. New data resources, linkages, and infrastructure for cancer health economics research: main topics from a panel discussion. J Natl Cancer Inst Monogr. 2022;2022(59):6873.CrossRefGoogle Scholar
Biro, S, Williamson, T, Leggett, JA, et al. Utility of linking primary care electronic medical records with Canadian census data to study the determinants of chronic disease: an example based on socioeconomic status and obesity. BMC Med Inform Decis Mak. 2016;16(1):32.CrossRefGoogle Scholar
Comer, KF, Grannis, S, Dixon, BE, Bodenhamer, DJ, Wiehe, SE. Incorporating geospatial capacity within clinical data systems to address social determinants of health. Public Health Rep. 2011;126(Suppl 3):5461.CrossRefGoogle ScholarPubMed
Bambekova, PG, Liaw, W, Phillips, RL & Bazemore, A. Integrating community and clinical data to assess patient risks with a population health assessment engine (PHATE). J Am Board Fam Med. 2020;33(3):463467.CrossRefGoogle ScholarPubMed
Hughes, LS, Phillips, RL, DeVoe, JE & Bazemore, AW. Community vital signs: taking the pulse of the community while caring for patients. J Am Board Fam Med. 2016;29(3):419422.CrossRefGoogle ScholarPubMed
Bazemore, AW, Cottrell, EK, Gold, R, et al. Community vital signs”: incorporating geocoded social determinants into electronic records to promote patient and population health. J Am Med Inform Assoc. 2016;23(2):407412.CrossRefGoogle ScholarPubMed
Luijks, H, van Boven, K, olde Hartman, T, Uijen, A, van Weel, C, Schers, H. Purposeful incorporation of patient narratives in the medical record in the Netherlands. J Am Board Fam Med. 2021;34(4):709723.CrossRefGoogle Scholar
Jain, A, van Hoek, AJ, Walker, JL, Mathur, R, Smeeth, L & Thomas, SL. Identifying social factors amongst older individuals in linked electronic health records: an assessment in a population based study. PLoS One. 2017;12(11):e0. 189038.CrossRefGoogle ScholarPubMed
Rousseau, JF, Oliveira, E, Tierney, WM, Khurshid, A. Methods for development and application of data standards in an ontology-driven information model for measuring, managing, and computing social determinants of health for individuals, households, and communities evaluated through an example of asthma. J Biomed Inform. 2022;136:104241.CrossRefGoogle Scholar
Wang, M, Pantell, MS, Gottlieb, LM, Adler-Milstein, J. Documentation and review of social determinants of health data in the EHR: measures and associated insights. J Am Med Inform Assoc. 2021;28(12):26082616.CrossRefGoogle ScholarPubMed
Tan-McGrory, A, Bennett-AbuAyyash, C, Gee, S, et al. A patient and family data domain collection framework for identifying disparities in pediatrics: results from the pediatric health equity collaborative. BMC Pediatr. 2018;18(1):18.CrossRefGoogle Scholar
Phuong, J, Hong, S, Palchuk, MB, et al. Advancing interoperability of patient-level social determinants of health data to support COVID-19 research. AMIA Jt Summits Transl Sci Proc. 2022, 2022:, 396405.Google ScholarPubMed
Kepper, MM, Walsh‐Bailey, C, Prusaczyk, B, Zhao, M, Herrick, C, Foraker, R. The adoption of social determinants of health documentation in clinical settings. Health Serv Res. 2023;58(1):6777.CrossRefGoogle ScholarPubMed
Yang, X, Yelton, B, Chen, S, et al. Examining social determinants of health during a pandemic: clinical application of Z codes before and during COVID-19. Front Public Health. 2022;10:888459.CrossRefGoogle ScholarPubMed
Richman, EL, Lombardi, BM, de Saxe Zerden, L Forte, AB. What do EHRs tell us about how we deploy health professionals to address the social determinants of health. Soc Work Public Health, 2022;37(3):287296.CrossRefGoogle Scholar
Albert, SM, McCracken, P, Bui, T, et al. Do patients want clinicians to ask about social needs and include this information in their medical record? BMC Health Serv Res. 2022;22(1):1275.CrossRefGoogle Scholar
Freij, M, Dullabh, P, Lewis, S, Smith, SR, Hovey, L & Dhopeshwarkar, R. Incorporating social determinants of health in electronic health records: qualitative study of current practices among top vendors. JMIR Med Inform. 2019;7(2):e13849.CrossRefGoogle ScholarPubMed
Tenenbaum, JD, Christian, V, Cornish, MA, et al. The MURDOCK Study: a long-term initiative for disease reclassification through advanced biomarker discovery and integration with electronic health records. Am J Transl Res. 2012;4(3):291301.Google Scholar
Shi, Q, Herbert, C, Ward, DV. COVID-19 variant surveillance and social determinants in central Massachusetts: development study. JMIR Form Res. 2022;6(6):e37858.CrossRefGoogle ScholarPubMed
Ofili, EO, Schanberg, LE, Hutchinson, B, et al. The Association of Black Cardiologists (ABC) Cardiovascular Implementation Study (CVIS): a research registry integrating social determinants to support care for underserved patients. Int J Environ Res Public Health. 2019;16(9).CrossRefGoogle Scholar
Kyriazis, D, Autexier, S, Brondino, I, et al. CrowdHEALTH: Holistic health records and big data analytics for health policy making and personalized health. Stud Hhealth Ttechnol Iinform. 2017, 238:1923.Google ScholarPubMed
Khatib, R, Li, Y, Glowacki, N, Siddiqi, A. Addressing social needs in the clinical setting: description of needs identified in a quality improvement pilot across 3 community hospital service areas. Popul Health Manag. 2022;25(5):632638.CrossRefGoogle Scholar
Smith, MA, Gigot, M, Harburn, A, et al. Insights into measuring health disparities using electronic health records from a statewide network of health systems: a case study. J Clin Transl Sci. 2023;7(1):e54.CrossRefGoogle ScholarPubMed
Cook, L, Espinoza, J, Weiskopf, NG, et al. Issues with variability in electronic health record data about race and ethnicity: descriptive analysis of the national COVID cohort collaborative data enclave. JMIR Med Inform. 2022;10(9):e39235.CrossRefGoogle ScholarPubMed
Lindemann, EA, Chen, ES, Wang, Y, Skube, SJ & Melton, GB. Representation of social history factors across age groups: a topic analysis of free-text social documentation. AMIA Annu Symp Proc. 2018;2017:11691178.Google ScholarPubMed
Dorr, DA, Quiñones, AR, King, T, Wei, MY, White, K & Bejan, CA. Prediction of future health care utilization through note-extracted psychosocial factors. Med Care. 2022;60(8):570578.CrossRefGoogle ScholarPubMed
Bejan, CA, Angiolillo, J, Conway, D, et al. Mining 100 million notes to find homelessness and adverse childhood experiences: 2 case studies of rare and severe social determinants of health in electronic health records. J Am Med Inf Assoc. 2018;25(1):6171.CrossRefGoogle ScholarPubMed
Dorr, D, Bejan, CA, Pizzimenti, C, Singh, S, Storer, M & Quinones, A. Identifying patients with significant problems related to social determinants of health with natural language processing. Stud Health Technol Inform. 2019;264:14561457.Google ScholarPubMed
Conway, M, Keyhani, S, Christensen, L, et al. Moonstone: a novel natural language processing system for inferring social risk from clinical narratives. J Biomed Semantics. 2019;10(1):6.CrossRefGoogle ScholarPubMed
Bucher, BT, Shi, J, Pettit, RJ, Ferraro, J, Chapman, WW. Determination of marital status of patients from structured and unstructured electronic healthcare data. AMIA Annu Symp Proc. 2019:267274.Google ScholarPubMed
Oreskovic, NM, Maniates, J, Weilburg, J, Choy, G. Optimizing the use of electronic health records to identify high-risk psychosocial determinants of health. JMIR Med Inform. 2017;5(3):e25.CrossRefGoogle ScholarPubMed
Morrow, D, Zamora-Resendiz, R, Beckham, JC, et al. A case for developing domain-specific vocabularies for extracting suicide factors from healthcare notes. J Psychiatr Res. 2022, 151:328338.CrossRefGoogle ScholarPubMed
Chilman, N, Song, X, Roberts, A, et al. Text mining occupations from the mental health electronic health record: a natural language processing approach using records from the Clinical Record Interactive Search (CRIS) platform in south London. UKBMJ Open. 2021;11(3):e04. 2274.Google ScholarPubMed
Rawat, BPS, Keating, H, Goodwin, R, Druhl, E. An investigation of the representation of social determinants of health in the UMLS. AMIA Annu Symp Proc. 2023;2022:912921.Google ScholarPubMed
Shah-Mohammadi, F, Cui, W, Bachi, K, Hurd, Y & Finkelstein, J. Comparative analysis of patient distress in opioid treatment programs using natural language processing. Biomed Eng Syst Technol Int Jt Conf BIOSTEC Revis Sel Pap. 2022;2022:319326.Google ScholarPubMed
Wang, EA, Long, JB, McGinnis, KA, et al. Measuring exposure to incarceration using the electronic health record. Med Care. 2019;57(Suppl 6 2):S157S163.CrossRefGoogle ScholarPubMed
Hatef, E, Rouhizadeh, M, Nau, C, et al. Development and assessment of a natural language processing model to identify residential instability in electronic health records’ unstructured data: a comparison of 3 integrated healthcare delivery systems. JAMIA Open. 2022;5(1):ooac006.CrossRefGoogle Scholar
Hatef, E, Singh Deol, G, Rouhizadeh, M, et al. Measuring the value of a practical text mining approach to identify patients with housing issues in the free-text notes in electronic health record: findings of a retrospective cohort study. Front Public Health. 2021;9:697501.CrossRefGoogle ScholarPubMed
Chapman, AB, Jones, A, Kelley, AT, et al. ReHouSED: a novel measurement of Veteran housing stability using natural language processing. J Biomed Inform. 2021;122:103903.CrossRefGoogle ScholarPubMed
Feller, DJ, Bear Don’t Walk IV, OJ, Zucker, J, Yin, MT, Gordon, P, & Elhadad, N. Detecting social and behavioral determinants of health with structured and free-text clinical data. Appl Clin Inform. 2020;11(1):172181.Google ScholarPubMed
Ahsan, H, Ohnuki, E, Mitra, A & Yu, H. MIMIC-SBDH: a dataset for social and behavioral determinants of health. Proc Mach Learn Res. 2021;149:391413.Google Scholar
Feller, DJ, Zucker, J, Yin, MT, Gordon, P, Elhadad, N. Using clinical notes and natural language processing for automated HIV risk assessment. J Acquir Immune Defic Syndr. 2018;77(2):160166.CrossRefGoogle ScholarPubMed
Rouillard, CJ, Nasser, MA, Hu, H & Roblin, DW. Evaluation of a natural language processing approach to identify social determinants of health in electronic health records in a diverse community cohort. Med Care. 2022;60(3):248255.CrossRefGoogle Scholar
Teng, A, Wilcox, A. Simplified data science approach to extract social and behavioural determinants: a retrospective chart review. BMJ Open. 2022;12(1):e048397.CrossRefGoogle Scholar
Vaswani, A, Shazeer, NM, Parmar, N, et al. Attention is all you need. Adv Neural Inf Process Syst2017;30:59986008.Google Scholar
Yu, Z, Yang, X, Guo, Y, Bian, J, Wu, Y. Assessing the documentation of social determinants of health for lung cancer patients in clinical narratives. Front Public Health. 2022;10:778463.CrossRefGoogle ScholarPubMed
Yu, Z, Yang, X, Dang, C, et al. A study of social and behavioral determinants of health in lung cancer patients using transformers-based natural language processing Models. AMIA Annu Symp Proc. 2021;2021, 12251233.Google ScholarPubMed
Bashir, SR, Raza, S, Kocaman, V & Qamar, U. Clinical application of detecting COVID-19 risks: a natural language processing approach. Viruses. 2022;14(12):10.3390/v1412. 2761.CrossRefGoogle Scholar
Mitra, A, Pradhan, R, Melamed, RD, et al. Associations between natural language processing-enriched social determinants of health and suicide death among US veterans. JAMA Netw Open. 2023;6(3):e233079.CrossRefGoogle ScholarPubMed
Richie, R, Ruiz, VM, Han, S, Shi, L, Tsui, FR. Extracting social determinants of health events with transformer-based multitask, multilabel named entity recognition. J Am Med Inform Assoc. 2023;30(8):13791388.CrossRefGoogle ScholarPubMed
Zhao, X & Rios, A. A marker-based neural network system for extracting social determinants of health. J Am Med Inform Assoc. 2023;30(8):13981407.CrossRefGoogle ScholarPubMed
Newman-Griffis, D, Fosler-Lussier, E. Automated coding of under-studied medical concept domains: linking physical activity reports to the international classification of functioning, disability, and health. Front Digit Health. 2021;3:20828. doi: 10.3389/fdgth.2021.620828.CrossRefGoogle Scholar
Mitra, A, Ahsan, H, Li, W, et al. Risk factors associated with nonfatal opioid overdose leading to intensive care unit admission: a cross-sectional study. JMIR Med Inform. 2021;9(11):2851.CrossRefGoogle ScholarPubMed
Lybarger, K, Dobbins, NJ, Long, R, et al. Leveraging natural language processing to augment structured social determinants of health data in the electronic health record. J Am Med Inform Assoc. 2023;30(8):13891397.CrossRefGoogle ScholarPubMed
Han, S, Zhang, RF, Shi, L, et al. Classifying social determinants of health from unstructured electronic health records using deep learning-based natural language processing. J Biomed Inform. 2022;127:103984.CrossRefGoogle ScholarPubMed
Wong, L, Yu, F, Bhattacharyya, S, Greer, ML. Covid-19 positivity differences among patients of a rural, southern US state hospital system based on population density, rural-urban classification, and area deprivation index. Stud Health Technol Inform. 2022, 294:701702.Google ScholarPubMed
Giovanatti, A, Elassar, H, Karabon, P, Wunderlich-Barillas, T, Halalau, A. Social determinants of health correlating with mechanical ventilation of COVID-19 patients: a multi-center observational study. Int J Gen Med. 2021;14:85218526.CrossRefGoogle ScholarPubMed
David, P, Fracci, S, Wojtowicz, J, et al. Ethnicity, social determinants of health, and pediatric primary care during the COVID-19 pandemic. J Prim Care Community Health. 2022; 13:21501319221112250.CrossRefGoogle ScholarPubMed
Harding, JL, Patel, SA, Davis, T, et al. Understanding racial disparities in COVID-19-related complications: protocol for a mixed methods study. JMIR Res Protoc. 2022;11(10):e38914.CrossRefGoogle ScholarPubMed
Holbert, SE, Andersen, K, Stone, D, Pipkin, K, Turcotte, J, Patton, C. Social determinants of health influence early outcomes following lumbar spine surgery. Ochsner J. 2022;22(4):299306.CrossRefGoogle ScholarPubMed
Ye, Y, Beachy, MW,Luo, J, et al. Geospatial, clinical, and social determinants of hospital readmissions. Am J Med Qual, 2019;34(6):607614.CrossRefGoogle ScholarPubMed
Johnson, AE, Zhu, J, Garrard, W, et al. Area deprivation index and cardiac readmissions: evaluating risk-prediction in an electronic health record. J Am Heart Assoc, 2021;10(13):e0. 20466.CrossRefGoogle Scholar
Hall, AG, Davlyatov, GK, Orewa, GN, Mehta, TS, Feldman, SS. Multiple electronic health record-based measures of social determinants of health to predict return to the emergency department following discharge. Popul Health Manag. 2022;25(6):771780.CrossRefGoogle Scholar
Jamei, M, Nisnevich, A, Wetchler, E, Sudat, S & Liu, E. Predicting all-cause risk of 30-day hospital readmission using artificial neural networks. PLoS One. 2017;12(7):e01e08, 1173.CrossRefGoogle ScholarPubMed
Zhang, Y, Zhang, Y, Sholle, E, et al. Assessing the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission or death. PLoS One, 2020;15(6):e0. 235064.Google ScholarPubMed
Nijhawan, AE, Metsch, LR, Zhang, S, et al. Clinical and sociobehavioral prediction model of 30-day hospital readmissions among people with HIV and substance use disorder: beyond electronic health record data. J Acquir Immune Defic Syndr. 2019;80(3):330341.CrossRefGoogle ScholarPubMed
Ehwerhemuepha, L, Pugh, K, Grant, A, et al. A statistical-learning model for unplanned 7-day readmission in pediatrics. Hosp Pediatr. 2020;10(1):4351.CrossRefGoogle ScholarPubMed
Graham, LA, Hawn, MT, Dasinger, EA, et al. Psychosocial determinants of readmission after surgery. Med Care, 2021;59(10):864871.CrossRefGoogle ScholarPubMed
Sills, MR, Hall, M, Cutler, GJ, et al. Adding social determinant data changes children’s hospitals’ readmissions performance. J Pediatr, 2017, 186:150157.e1.CrossRefGoogle Scholar
Tomayko, EJ, Flood, TL, Tandias, A, Hanrahan, LP. Linking electronic health records with community-level data to understand childhood obesity risk. Pediatr Obes. 2015;10(6):436441.CrossRefGoogle ScholarPubMed
Prather, AA, Gottlieb, LM, Giuse, NB, et al. National academy of medicine social and behavioral measures: associations with self-reported health. Am J Prev Med. 2017;53(4):449456.CrossRefGoogle ScholarPubMed
Winckler, B, Nguyen, M, Khare, M, et al. Geographic variation in acute pediatric mental health utilization. Acad Pediatr. 2023;23(2):448456.CrossRefGoogle ScholarPubMed
Tai-Seale, M, Cheung, MW, Kwak, J, et al. Unmet needs for food, medicine, and mental health services among vulnerable older adults during the COVID-19 pandemic. Health Serv Res. 2023;58(Suppl 1):6977.CrossRefGoogle ScholarPubMed
Schlauch, KA, Read, RW, Koning, SM, Neveux, I, Grzymski, JJ. Using phenome-wide association studies and the SF-12 quality of life metric to identify profound consequences of adverse childhood experiences on adult mental and physical health in a Northern Nevadan population. Front Psychiatry. 2022;13:984366.CrossRefGoogle Scholar
Avalos, LA, Nance, N, Zhu, Y, et al. Contributions of COVID-19 pandemic-related stressors to racial and ethnic disparities in mental health during pregnancy. Front Psychiatry. 2022;13:837659.CrossRefGoogle ScholarPubMed
Ben-Assuli, O, Vest, JR. Return visits to the emergency department: an analysis using group based curve models. Health Infor J. 2022;28(2):146045822211054.Google Scholar
Davis, CI, Montgomery, AE, Dichter, ME, Taylor, LD, Blosnich, JR. Social determinants and emergency department utilization: findings from the Veterans Health Administration. Am J Emerg Med. 2020;38(9):19041909.CrossRefGoogle ScholarPubMed
Mosen, DM, Banegas, MP, Benuzillo, JG, Hu, WR, Brooks, NB, Ertz-Berger, BL. Association between social and economic needs with future healthcare utilization. Am J Prev Med. 2020;58(3):457460.CrossRefGoogle ScholarPubMed
Lawson, NR, Klein, MD, Ollberding, NJ, Wurster Ovalle, V, Beck, AF. The impact of infant well-child care compliance and social risks on emergency department utilization. Clin Pediatr. 2017;56(10):920927.CrossRefGoogle ScholarPubMed
Headen, IE, Dubbin, L, Canchola, AJ, Kersten, E & Yen, IH. Health care utilization among women of reproductive age living in public housing: associations across six public housing sites in San Francisco. Prev Med Rep. 2022;27:101797.CrossRefGoogle ScholarPubMed
Vest, JR, Ben-Assuli, O. Prediction of emergency department revisits using area-level social determinants of health measures and health information exchange information. Int J Med Inform. 2019;129:205210.CrossRefGoogle ScholarPubMed
Bhavsar, NA, Gao, A, Phelan, M, Pagidipati, NJ & Goldstein, BA. Value of neighborhood socioeconomic status in predicting risk of outcomes in studies that use electronic health record data. JAMA Netw Open. 2018;1(5):e182716.CrossRefGoogle ScholarPubMed
Faison, K, Moon, A, Buckman, C, et al. Change of address as a measure of housing insecurity predicting rural emergency department revisits after asthma exacerbation. J Asthma, 2021;58(12):16161622.CrossRefGoogle ScholarPubMed
Grinspan, ZM, Patel, AD, Hafeez, B, Abramson, EL & Kern, LM. Predicting frequent emergency department use among children with epilepsy: a retrospective cohort study using electronic health data from 2 centers. Epilepsia. 2018;59(1):155169.CrossRefGoogle ScholarPubMed
Weigert, RM, McMichael, BS, VanderVelden, HA, et al. Parental childhood adversity and pediatric emergency department utilization: a pilot study. Pediatr Emerg Care, 2022;38(12):665671.CrossRefGoogle ScholarPubMed
Power-Hays, A, Patterson, A & Sobota, A. Household material hardships impact emergency department reliance in pediatric patients with sickle cell disease. Pediatr Blood Cancer. 2020;67(10):e28587.CrossRefGoogle ScholarPubMed
Heinert, SW, McCoy, J, Strickland, PO, Riggs, R & Eisenstein, R. More accessible COVID-19 treatment through monoclonal antibody infusion in the emergency department. West J Emerg Med. 2022;23(5):618622.CrossRefGoogle ScholarPubMed
Mayfield, CA, de Hernandez, BU, Geraci, M, Eberth, JM, Dulin, M & Merchant, AT. Residential segregation and emergency department utilization among an underserved urban emergency department sample in North Carolina. N C Med J. 2022;83(1):4857.Google Scholar
O’Malley, JA, Klett, BM, Klein, MD, Inman, N, Beck, AF. Revealing the prevalence and consequences of food insecurity in children with epilepsy. J Community Health. 2017;42(6):12131219.CrossRefGoogle ScholarPubMed
Goyal, P, Schenck, E, Wu, Y, et al. Influence of social deprivation index on in-hospital outcomes of COVID-19. Sci Rep. 2023;13(1):1746.CrossRefGoogle Scholar
Hong, AS, Nguyen, DQ, Lee, SC, et al. Prior frequent emergency department use as a predictor of emergency department visits after a new cancer diagnosis. JCO Oncol Pract. 2021;17(11):e1738e. 1752.CrossRefGoogle ScholarPubMed
Conroy, K, Samnaliev, M, Cheek, S, Chien, AT. Pediatric primary care-based social needs services and health care utilization. Acad Pediatr. 2021;21(8):13311337.CrossRefGoogle ScholarPubMed
Luo, J, Tong, L, Crotty, BH, et al. Telemedicine adoption during the COVID-19 pandemic: gaps and inequalities. Appl Clin Inform. 2021;12(4):836844.Google ScholarPubMed
Schwartz, BS, Kolak, M, Pollak, JS, et al. Associations of four indexes of social determinants of health and two community typologies with new onset type 2 diabetes across a diverse geography in Pennsylvania. PLOS ONE. 2022;17(9):e0. 274758.CrossRefGoogle ScholarPubMed
Scarton, L, Nelson, T, Yao, Y, et al. Medication adherence and cardiometabolic control indicators among American Indian adults receiving tribal health services: protocol for a longitudinal electronic health records study. JMIR Res Protoc. 2022;11(10):e39193.CrossRefGoogle Scholar
Li, Y, Hu, H, Zheng, Y, et al. Impact of contextual-level social determinants of health on newer antidiabetic drug adoption in patients with type 2 diabetes. Int J Environ Res Public Health. 2023;20(5).Google ScholarPubMed
Lê-Scherban, F, Ballester, L, Castro, JC, et al. Identifying neighborhood characteristics associated with diabetes and hypertension control in an urban African-American population using geo-linked electronic health records. Prev Med Rep. 2019;15:100953.CrossRefGoogle Scholar
Kivimäki, M, Vahtera, J, Tabák, AG, et al. Neighbourhood socioeconomic disadvantage, risk factors, and diabetes from childhood to middle age in the Young Finns Study: a cohort study. Lancet Public Health. 2018;3(8):e365e373.CrossRefGoogle Scholar
Cereijo, L, Gullón, P, Del Cura, I, et al. Exercise facilities and the prevalence of obesity and type 2 diabetes in the city of Madrid. Diabetologia, 2022;65(1):150158.CrossRefGoogle Scholar
Brown, AGM, Kressin, N, Terrin, N, et al. The influence of health insurance stability on racial/Ethnic differences in diabetes control and management. Ethn Dis, 2021;31(1):149158.CrossRefGoogle ScholarPubMed
Matsumoto, CL, Tobe, S, Schreiber, YS, et al. Diabetes prevalence and demographics in 25 First Nations communities in northwest Ontario (2014-2017). Can J Rural Med. 2020;25(4):139144.Google ScholarPubMed
Cereijo, L, Gullón, P, Del Cura, I, et al. Exercise facility availability and incidence of type 2 diabetes and complications in Spain: a population-based retrospective cohort 2015-2018. Health Place. 2023;81:103027.CrossRefGoogle Scholar
Nieuwenhuijse, EA, Struijs, JN, Sutch, SP, Numans, ME & Vos, RC. Achieving diabetes treatment targets in people with registered mental illness is similar or improved compared with those without: analyses of linked observational datasets. Diabet Med. 2022;39(6):e.–14835.CrossRefGoogle ScholarPubMed
Ares-Blanco, S, Polentinos-Castro, E, Rodríguez-Cabrera, F, Gullón, P, Franco, M, Del Cura-González, I. Inequalities in glycemic and multifactorial cardiovascular control of type 2 diabetes: The Heart Healthy Hoods study. Front Med. 2022;9:966368.CrossRefGoogle ScholarPubMed
Ye, C, Fu, T, Hao, S, et al. Prediction of incident hypertension within the next year: prospective study using statewide electronic health records and machine learning. J Med Internet Res. 2018;20(1):e22.CrossRefGoogle ScholarPubMed
Sonnenblick, R, Reilly, A, Roye, K, et al. Social determinants of health and hypertension control in adults with Medicaid. J Prim Care Community Health, 2022;, 13:21501319221142424.CrossRefGoogle ScholarPubMed
DuBay, DA, Su, Z, Morinelli, TA, et al. Development and future deployment of a 5 years allograft survival model for kidney transplantation. Nephrology. 2019;24(8):855862.CrossRefGoogle ScholarPubMed
Ghazi, L, Oakes, JM, MacLehose, RF, Luepker, RV, Osypuk, TL, Drawz, PE. Neighborhood socioeconomic status and identification of patients with CKD using electronic health records. Am J Kidney Dis. 2021;78(1):5765.e1.CrossRefGoogle ScholarPubMed
Lange, SJ, Kompaniyets, L, Freedman, DS, et al. Longitudinal trends in body mass index before and during the COVID-19 pandemic among persons aged 2-19 years - United States, 2018-2020. MMWR Morb Mortal Wkly Rep. 2021;70(37):12781283.CrossRefGoogle ScholarPubMed
Roth, C, Foraker, RE, Payne, PRO, Embi, PJ. Community-level determinants of obesity: harnessing the power of electronic health records for retrospective data analysis. BMC Med Inform Decis Mak. 2014;14(1):36.CrossRefGoogle ScholarPubMed
Tung, EL, Wroblewski, KE, Boyd, K, Makelarski, JA, Peek, ME, Lindau, ST. Police-Recorded Crime and Disparities in Obesity and Blood Pressure Status in Chicago. J Am Heart Assoc. 2018;7(7):e008030. doi: 10.1161/JAHA.117.008030.CrossRefGoogle ScholarPubMed
Schlauch, KA, Read, RW, Neveux, I, Lipp, B, Slonim, A & Grzymski, JJ. The impact of ACEs on BMI: an investigation of the genotype-environment effects of BMI. Front Genet. 2022;13:816660.CrossRefGoogle ScholarPubMed
Boone-Heinonen, J, Tillotson, CJ, O’Malley, JP, et al. Characterizing a, big data, cohort of over 200,000 low-income U.S. infants and children for obesity research: the ADVANCE early life cohort. Matern Child Health J. 2017;21(3):421431.CrossRefGoogle ScholarPubMed
Nemirovsky, DR, Klose, C, Wynne, M, et al. Role of race and insurance status in prostate cancer diagnosis-to-treatment interval. Clin Genitourin Cancer. 2023;21(3):e198e203.CrossRefGoogle ScholarPubMed
Chakravarthy, R, Stallings, SC, Velez Edwards, DR, et al. Determinants of stage at diagnosis of HPV-related cancer including area deprivation and clinical factors. J Public Health. 2022;44(1):1827.CrossRefGoogle ScholarPubMed
Otero, P, Scott, P, Martin, SZ, Huesing, E. Data to identify social determinants of health affecting disparities in cancer survival. Stud Health Technol Inform. 2022;290:967971.Google Scholar
Byhoff, E, Guardado, R, Xiao, N, Nokes, K, Garg, A, Tripodis, Y. Association of unmet social needs with chronic illness: a cross-sectional study. Popul Health Manag. 2022;25(2):157163.CrossRefGoogle ScholarPubMed
Kurani, SS, McCoy, RG, Lampman, MA, et al. Association of neighborhood measures of social determinants of health with breast, cervical, and colorectal cancer screening rates in the US midwest. JAMA Netw Open. 2020;3(3):e200618.CrossRefGoogle ScholarPubMed
Halbert, CH, Jefferson, M, Allen, CG, et al. Racial differences in patient portal activation and research enrollment among patients with prostate cancer. JCO Clin Cancer Inform. 2021, 5:768774.CrossRefGoogle ScholarPubMed
Adie, Y, Kats, DJ, Tlimat, A, et al. Neighborhood disadvantage and lung cancer incidence in ever-smokers at a safety net health-care system: a retrospective study. Chest, 2020;157(4):10211029.CrossRefGoogle Scholar
Edwards, CV, Sheikh, AR, Dennis, MJ, et al. The impact of substance use on health care utilization, treatment, and outcomes in patients with non-small cell lung cancer. J Thorac Dis. 2022;14(10):38653875.CrossRefGoogle ScholarPubMed
Choi, HY, Graetz, I, Shaban-Nejad, A, et al. Social disparities of pain and pain intensity among women diagnosed with early stage breast cancer. Front Oncol. 2022;12:759272.CrossRefGoogle ScholarPubMed
Sathe, C, Accordino, MK, DeStephano, D, Shah, M, Wright, JD, Hershman, DL. Social determinants of health and CDK4/6 inhibitor use and outcomes among patients with metastatic breast cancer. Breast Cancer Res Treat. 2023;200(1):8592.CrossRefGoogle Scholar
Hayes-Larson, E, Ikesu, R, Fong, J, et al. Association of education with dementia incidence stratified by ethnicity and nativity in a cohort of older Asian American individuals. JAMA Netw Open. 2023;6(3):e231661.CrossRefGoogle Scholar
Alemi, F, Avramovic, S, Renshaw, KD, Kanchi, R, Schwartz, M. Relative accuracy of social and medical determinants of suicide in electronic health records. Health Serv Res. 2020;55(Suppl 2):833840.CrossRefGoogle ScholarPubMed
Blosnich, JR, Montgomery, AE, Dichter, ME, et al. Social determinants and military veterans’ suicide ideation and attempt: a cross-sectional analysis of electronic health record data. J Gen Intern Med. 2020;35(6):17591767.CrossRefGoogle ScholarPubMed
Liu, J, Hung, P, Liang, C, et al. Multilevel determinants of racial/ethnic disparities in severe maternal morbidity and mortality in the context of the COVID-19 pandemic in the USA: protocol for a concurrent triangulation, mixed-methods study. BMJ Open. 2022;12(6):e062294.CrossRefGoogle ScholarPubMed
Freeman, C, Stanhope, KK, Wichmann, H, Jamieson, DJ, Boulet, SL. Neighborhood deprivation and severe maternal morbidity in a medicaid-insured population in Georgia. J Matern Fetal Neonatal Med. 2022;35(25):1011010115.CrossRefGoogle Scholar
Cottrell, EK, O’Malley, JP, Dambrun, K, et al. The impact of social and clinical complexity on diabetes control measures. J Am Board Fam Med. 2020;33(4):600610.CrossRefGoogle ScholarPubMed
Kind, AJH, Buckingham, WMaking Neighborhood Disadvantage Metrics Accessible: The Neighborhood AtlasN Engl J Med. 2018;378:24562458. doi: 10.1056/NEJMp1802313.CrossRefGoogle ScholarPubMed
Ryan Powell, W, Sheehy, AM & Kind, AJH. The area deprivation index is the most scientifically validated social exposome tool available for policies advancing health equity. Health Affairs Forefront. 2023. doi: 10.1377/forefront.20230714.676093. https://www.healthaffairs.org/content/forefront/area-deprivation-index-most-scientifically-validated-social-exposome-tool-available Google Scholar
Social Deprivation Index (SDI). (2021). (https://www.graham-center.org/maps-data-tools/social-deprivation-index.html) Accessed January 29, 2024.Google Scholar
CDC/ATSDR Social Vulnerability Index. (2024). (https://www.atsdr.cdc.gov/placeandhealth/svi/index.html) Accessed January 29, 2024.Google Scholar
Gordon, NP, Banegas, MP & Tucker-Seeley, RD. Racial-ethnic differences in prevalence of social determinants of health and social risks among middle-aged and older adults in a Northern California health plan. PLoS One. 2020;15(11):e.0240822.CrossRefGoogle Scholar
Jordan, CAL, Alizadeh, F, Ramirez, LS, Kimbro, R, Lopez, KN. Obesity in pediatric congenital heart disease: the role of age, complexity, and sociodemographics. Pediatr Cardiol. 2023;44(6):12511261.CrossRefGoogle ScholarPubMed
Ahmad, TR, Kong, AW, Turner, ML, et al. Socioeconomic correlates of keratoconus severity and progression. Cornea, 2023;42(1):6065.CrossRefGoogle Scholar
Mansfield, LN, Chung, RJ, Silva, SG, Merwin, EI & Gonzalez-Guarda, RM. Social determinants of human papillomavirus vaccine series completion among U.S. adolescents: a mixed-methods study. SSM Popul Health. 2022;18:101082.Google ScholarPubMed
Islam, JY, Madhira, V, Sun, J, et al. Racial disparities in COVID-19 test positivity among people living with HIV in the United States. Int J STD AIDS, 2022;33(5):462466.Google ScholarPubMed
Thompson, HM, Sharma, B, Smith, DL, et al. Machine learning techniques to explore clinical presentations of COVID-19 severity and to test the association with unhealthy opioid use: retrospective cross-sectional cohort study. JMIR Public Health Surveill. 2022;8(12):e38158.CrossRefGoogle ScholarPubMed
Chavez, LJ, Tyson, DP, Davenport, MA, Kelleher, KJ & Chisolm, DJ. Social needs as a risk factor for positive postpartum depression screens in pediatric primary care. Acad Pediatr. 2023;23(7):14111416.CrossRefGoogle ScholarPubMed
Kapoor, N, Lynch, EA, Lacson, R, et al. Predictors of completion of clinically necessary radiologist-recommended follow-up imaging: assessment using an automated closed-loop communication and tracking tool. Am J Roentgenol. 2023;220(3):429440.CrossRefGoogle ScholarPubMed
Cobert, J, Lantos, PM, Janko, MM, et al. Geospatial variations and neighborhood deprivation in drug-related admissions and overdoses. J Urban Health, 2020;97(6):814822.CrossRefGoogle ScholarPubMed
Egede, LE, Walker, RJ, Linde, S, et al. Nonmedical interventions for type 2 diabetes: evidence, actionable strategies, and policy opportunities. Health Aff. 2022;41(7):963970.CrossRefGoogle ScholarPubMed
Eakin, M, Singleterry, V, Wang, E, Brown, I, Saynina, O, Walker, R. Effects of California’s new patient homelessness screening and discharge care law in an emergency department. Cureus. 2023;15(2):e35534.Google Scholar
Sokan, O, Stryckman, B, Liang, Y, et al. Impact of a mobile integrated healthcare and community paramedicine program on improving medication adherence in patients with heart failure and chronic obstructive pulmonary disease after hospital discharge: a pilot study. Explor Res Clin Soc Pharm. 2022;8:100201.Google ScholarPubMed
Tung, EL, Abramsohn, EM, Boyd, K, et al. Impact of a low-intensity resource referral intervention on patients’ knowledge, beliefs, and use of community resources: results from the communityRx trial. J Gen Intern Med, 2020;35(3):815823.CrossRefGoogle ScholarPubMed
McCrae, JS, Robinson, JAL, Spain, AK, Byers, K, Axelrod, JL. The Mitigating Toxic Stress study design: approaches to developmental evaluation of pediatric health care innovations addressing social determinants of health and toxic stress. BMC Health Serv Res. 2021;21(1):71.CrossRefGoogle Scholar
Messmer, E, Brochier, A, Joseph, M, Tripodis, Y & Garg, A. Impact of an on-site versus remote patient navigator on pediatricians’ referrals and families’ receipt of resources for unmet social needs. J Prim Care Community Health. 2020;11:2150132720924252.CrossRefGoogle Scholar
Liu, I, Cruz, A, Gamcsik, S, Harris, SC. Reducing barriers to COVID-19 vaccine uptake through a culturally sensitive pharmacy-led patient medication education group in a behavioral health population. J Am Pharm Assoc. 2023;63(3):915919. doi: 10.1016/j.japh.2023.01.012.CrossRefGoogle Scholar
Mathias, P, Mahali, LP & Agarwal, S. Targeting technology in underserved adults with type 1 diabetes: effect of diabetes practice transformations on improving equity in CGM prescribing behaviors. Diabetes Care. 2022;45(10):22312237.CrossRefGoogle ScholarPubMed
Embick, ER, Maeng, DD, Juskiewicz, I, et al. Demonstrated health care cost savings for women: findings from a community health worker intervention designed to address depression and unmet social needs. Arch Womens Ment Health, 2021;24(1):8592.CrossRefGoogle ScholarPubMed
Sandel, M, Hansen, M, Kahn, R, et al. Medical-legal partnerships: transforming primary care by addressing the legal needs of vulnerable populations. Health Aff. 2010;29(9):16971705.CrossRefGoogle ScholarPubMed
Krist, AH, O’Loughlin, K, Woolf, SH, et al. Enhanced care planning and clinical-community linkages versus usual care to address basic needs of patients with multiple chronic conditions: a clinician-level randomized controlled trial. Trials. 2020;21(1):517.CrossRefGoogle ScholarPubMed
Hsu, C, Hertel, E, Johnson, E, et al. Evaluation of the learning to integrate neighborhoods and clinical care project: findings from implementing a new lay role into primary care teams to address social determinants of health. Perm J. 2018;22(4S), 101. doi: 10.7812/tpp/18-101,CrossRefGoogle ScholarPubMed
Berkowitz, SA, Hulberg, AC, Placzek, H, et al. Mechanisms associated with clinical improvement in interventions that address health-related social needs: a mixed-methods analysis. Popul Health Manag. 2019;22(5):399405.CrossRefGoogle Scholar
Henize, AW, Beck, AF, Klein, MD, Adams, M, Kahn, RS. A road map to address the social determinants of health through community collaboration. Pediatrics. 2015;136(4):e9931001.CrossRefGoogle ScholarPubMed
Gyamfi, J, Cooper, C, Barber, A, et al. Needs assessment and planning for a clinic-community-based implementation program for hypertension control among blacks in New York City: a protocol paper. Implement Sci Commun. 2022;3(1):96.CrossRefGoogle Scholar
Emmert-Aronson, B, Grill, KB, Trivedi, Z, Markle, EA, Chen, S. Group medical visits 2.0: the open source wellness behavioral pharmacy model. J Altern Complement Med. 2019;25(10):10261034.CrossRefGoogle ScholarPubMed
Taber, KA, Williams, JN, Huang, W, et al. Use of an integrated care management program to uncover and address social determinants of health for individuals with lupus. ACR Open Rheumatol. 2021;3(5):305311.CrossRefGoogle ScholarPubMed
Battaglia, TA, Freund, KM, Haas, JS, et al. Translating research into practice: protocol for a community-engaged, stepped wedge randomized trial to reduce disparities in breast cancer treatment through a regional patient navigation collaborative. Contemp Clin Trials. 2020;93:106007.CrossRefGoogle ScholarPubMed
Loo, S, Anderson, E, Lin, JG, et al. Evaluating a social risk screening and referral program in an urban safety-net hospital emergency department. J Am Coll Emerg Physicians Open, 2023;4(1):e12883.CrossRefGoogle Scholar
Zuckerman, AD, Mourani, J, Smith, A, et al. ASHP survey of health-system specialty pharmacy practice: clinical services. Am J Health Syst Pharm. 2022;80(13):827841. doi: 10.1093/ajhp/zxad064.CrossRefGoogle Scholar
Alcaraz, KI, Wiedt, TL, Daniels, EC, Yabroff, KR, Guerra, CE, Wender, RC. Understanding and addressing social determinants to advance cancer health equity in the united States: a blueprint for practice, research, and policy. CA Cancer J Clin. 2020;70(1):3146.CrossRefGoogle ScholarPubMed
DOMESTIC POLICY COUNCIL OFFICE OF SCIENCE AND TECHNOLOGY POLICY. The U.S. Playbook to address social determinants of health: THE WHITE HOUSE; 2023. (https://www.whitehouse.gov/wp-content/uploads/2023/11/SDOH-Playbook-3.pdf) Accessed January 7, 2024.Google Scholar
Dagenais, S, Russo, L, Madsen, A, Webster, J & Becnel, L. Use of real-world evidence to drive drug development strategy and inform clinical trial design. Clin Pharmacol Ther. 2022;111(1):7789.CrossRefGoogle ScholarPubMed
Common Data Elements and social determinants of health. (https://datascience.nih.gov/fhir-initiatives/common-data-elements-and-social-determinants-of-health) Accessed June 28, 2024.Google Scholar
Gravity Project. Gravity Project (2022). (https://thegravityproject.net/) Accessed June 28, 2024.Google Scholar
Hamilton, CM, Strader, LC, Pratt, JG, et alThe PhenX Toolkit: get the most from your measures. Am J Epidemiol2011;174(3):253260.CrossRefGoogle ScholarPubMed
Tesfaye, S, Cronin, RM, Lopez-Class, Met alMeasuring social determinants of health in the All of Us Research ProgramSci Rep2024;14: Article 8815. doi: 10.1038/s41598-024-57410-6.CrossRefGoogle ScholarPubMed
United States core data for interoperability (USCDI). (https://www.healthit.gov/isp/united-states-core-data-interoperability-uscdi) Accessed June 28, 2024.Google Scholar
Fox, A. Scaling SDOH initiatives with analytics and coordinated workflows. Healthcare IT News. 2023. (https://www.healthcareitnews.com/news/scaling-sdoh-initiatives-analytics-and-coordinated-workflows) Accessed January 29, 2024.Google Scholar
Yan, AF, Chen, Z, Wang, Y, et al. Effectiveness of social needs screening and interventions in clinical settings on utilization, cost, and clinical outcomes: a systematic review. Health Equity. 2022;6(1):454475.CrossRefGoogle ScholarPubMed
Sawatzky, R, Kwon, JY, Barclay, R, et al. Implications of response shift for micro-, meso-, and macro-level healthcare decision-making using results of patient-reported outcome measures. Qual life Res. 2021;30(12):33433357.CrossRefGoogle ScholarPubMed
Barasa, EW, Molyneux, S, English, M, Cleary, S. Setting healthcare priorities in hospitals: a review of empirical studies. Health Policy Plan. 2015;30(3):386396.CrossRefGoogle ScholarPubMed
McKneally, MF, Dickens, BM, Meslin, EM & Singer, PA. Bioethics for clinicians: 13. Resource allocation. CMAJ. 1997;157(2):163167.Google ScholarPubMed
Midboe, AM, Gray, C, Cheng, H, Okwara, L, Gale, RC. Implementation of health-focused interventions in vulnerable populations: protocol for a scoping review. BMJ Open. 2020;10(7):e036937.CrossRefGoogle ScholarPubMed
Pfaff, K, Krohn, H, Crawley, J, et al. The little things are big: evaluation of a compassionate community approach for promoting the health of vulnerable persons. BMC Public Health. 2021;21(1):2253.CrossRefGoogle ScholarPubMed
Small, N, Ong, BN, Lewis, A, et al. Co-designing new tools for collecting, analysing and presenting patient experience data in NHS services: working in partnership with patients and carers. Res Involv Engagem. 2021;7(1):85.CrossRefGoogle ScholarPubMed
Silvola, S, Restelli, U, Bonfanti, M, Croce, D. Co-design as enabling factor for patient-centred healthcare: a bibliometric literature review. Clinicoecon Outcomes Res. 2023;15:333347.CrossRefGoogle ScholarPubMed
National Academies of Sciences, Engineering, and Medicine, Health and Medicine Division, Board on Population Health and Public Health Practice, et al. The Need to Promote Health Equity. Washington, D.C., DC: National Academies Press; 2017.Google Scholar
Brown, AF, Ma, GX, Miranda, J, et al. Structural interventions to reduce and eliminate health disparities. Am J Public Health. 2019;109(S1):S72S78.CrossRefGoogle Scholar
Gottfredson, DC, Cook, TD, Gardner, FEM, et al. Standards of evidence for efficacy, effectiveness, and scale-up research in prevention science: next generation. Preven Sci. 2015;16(7):893926.CrossRefGoogle Scholar
Holmes, JH, Beinlich, J, Boland, MR, et al. Why is the electronic health record so challenging for research and clinical care? Methods Inf Med. 2021;60(1-02):3248.Google ScholarPubMed
Heacock, ML, Lopez, AR, Amolegbe, SM, et al. Enhancing data integration, interoperability, and reuse to address complex and emerging environmental health problems. Environ Sci Technol. 2022;56(12):75447552.CrossRefGoogle ScholarPubMed
Health and Human Services Department. Health data, technology, and interoperability: Certification program updates, algorithm transparency, and information sharing. Federal Register, 2023, 88:2374623917, https://www.federalregister.gov/d/2023-07229.Google Scholar
Guevara, M, Chen, S, Thomas, S, et al. Large language models to identify social determinants of health in electronic health records. NPJ Digit Med. 2024;7(1):6.CrossRefGoogle ScholarPubMed
Clusmann, J, Kolbinger, FR, Muti, HS, et al. The future landscape of large language models in medicine. Commun Med. 2023;3(1):141.CrossRefGoogle ScholarPubMed
Figure 0

Table 1. World Health Organization (WHO)–Social Determinants of Health (SDoH) data components. EHR = electronic health record.

Figure 1

Figure 1. Data-to-knowledge-to-action workflow for translating social determinants of health (SDoH) into clinical care. EHR = electronic health record.

Figure 2

Figure 2. Five social determinants of health categories describing the data workflow from data capture efforts to interventions. EHR = electronic health records; NLP = natural language processing.

Figure 3

Figure 3. PRISMA 2020 flow diagram. EHR = electronic health records; NLP = natural language processing.

Figure 4

Figure 4. Heatmap showing the frequency of association between the top 10 social determinants of health (SDoH) elements and the top five data collection methods.

Figure 5

Figure 5. UpSet Plot of natural language processing for social determinants of health (SDoH) algorithms ∼electronic health record (EHR) integration. *Outlining the distribution of papers in which each approach/method individually and in combination was described in the study. *Supervised machine learning includes traditional machine learning methods (naive bayes, support vector machine, logistic regression, random forest, etc), excluding neural networks and pretrained approaches.

Figure 6

Table 2. Social Determinants of Health (SDoH)-driven translational research: deriving and translating actionable knowledge into clinical care. NLP = natural language processing.

Supplementary material: File

Li et al. supplementary material 1

Li et al. supplementary material
Download Li et al. supplementary material 1(File)
File 1 MB
Supplementary material: File

Li et al. supplementary material 2

Li et al. supplementary material
Download Li et al. supplementary material 2(File)
File 629.6 KB