Text Analysis of Trends in Health Equity and Disparities From the Internal Revenue Service Tax Documentation Submitted by US Nonprofit Hospitals Between 2010 and 2019: Exploratory Study.

BACKGROUND: Many US hospitals are classified as nonprofits and receive tax-exempt status partially in exchange for providing benefits to the community. Proof of compliance is collected with the Schedule H form submitted as part of the annual Internal Revenue Service Form 990 (F990H), including a free-response text section that is known for being ambiguous and difficult to audit. This research is among the first to use natural language processing approaches to evaluate this text section with a focus on health equity and disparities. OBJECTIVE: This study aims to determine the extent to which the free-response text in F990H reveals how nonprofit hospitals address health equity and disparities, including alignment with public priorities. METHODS: We used free-response text submitted by hospital reporting entities in Part V and VI of the Internal Revenue Service Form 990 Schedule H between 2010 and 2019. We identified 29 main themes connected to health equity and disparities, and 152 related key phrases. We tallied occurrences of these phrases through term frequency analysis, calculated the Moran I statistic to assess geographic variation in 2018, analyzed Google Trends use for the same terms during the same period, and used semantic search with Sentence-BERT in Python to understand contextual use. RESULTS: We found increased use from 2010 to 2019 across all the 29 phrase themes related to health equity and disparities. More than 90% of hospital reporting entities used terms in 2018 and 2019 related to affordability (2018: 2117/2131, 99.34%; 2019: 1620/1627, 99.57%), government organizations (2018: 2053/2131, 96.33%; 2019: 1577/1627, 96.93%), mental health (2018: 1937/2131, 90.9%; 2019: 1517/1627, 93.24%), and data collection (2018: 1947/2131, 91.37%; 2019: 1502/1627, 92.32%). The themes with the largest relative increase were LGBTQ (lesbian, gay, bisexual, transgender, and queer; 1676%; 2010: 12/2328, 0.51%; 2019: 149/1627, 9.16%) and social determinants of health (958%; 2010: 68/2328, 2.92%; 2019: 503/1627, 30.92%). Terms related to homelessness varied geographically from 2010 to 2018, and terms related to equity, health IT, immigration, LGBTQ, oral health, rural, social determinants of health, and substance use showed statistically significant (P<.05) geographic variation in 2018. The largest percentage point increase was for terms related to substance use (2010: 403/2328, 17.31%; 2019: 1149/1627, 70.62%). However, use in themes such as LGBTQ, disability, oral health, and race and ethnicity ranked lower than public interest in these topics, and some increased mentions of themes were to explicitly say that no action was taken. CONCLUSIONS: Hospital reporting entities demonstrate an increasing awareness of health equity and disparities in community benefit tax documentation, but these do not necessarily correspond with general population interests or additional action. We propose further investigation of alignment with community health needs assessments and make suggestions for improvements to F990H reporting requirements.

Barriers, Facilitators, and Potential Solutions to Advancing Interoperable Clinical Decision Support: Multi-Stakeholder Consensus Recommendations for the Opioid Use Case.

With the advent of interoperability standards such as FHIR, SMART, CDS Hooks, and CQL, interoperable clinical decision support (CDS) holds great promise for improving healthcare. In 2018, the Agency for Healthcare Research and Quality (AHRQ)-sponsored Patient-Centered CDS Learning Network (PCCDS LN) chartered a Technical Framework Working Group (TechFWG) to identify barriers, facilitators, and potential solutions for interoperable CDS, with a specific focus on addressing the opioid epidemic. Through an open, multi-stakeholder process that engaged 54 representatives from healthcare, industry, and academia, the TechFWG identified barriers in 6 categories: regulatory environment, data integration, scalability, business case, effective and useful CDS, and care planning and coordination. Facilitators and key recommendations were also identified for overcoming these barriers. The key insights were also extrapolated to CDS-facilitated care improvement outside of the specific opioid use case. If applied broadly, the recommendations should help advance the availability and impact of interoperable CDS delivered at scale.

A qualitative framework-based evaluation of radiology clinical decision support initiatives: eliciting key factors to physician adoption in implementation.

OBJECTIVES: To illustrate key contextual factors that may have effects on clinical decision support (CDS) adoption and, ultimately, success. MATERIALS AND METHODS: We conducted a qualitative evaluation of 2 similar radiology CDS innovations for near-term endpoints affecting adoption and present the findings using an evaluation framework. We identified key contextual factors between these 2 innovations and determined important adoption differences between them. RESULTS: Degree of electronic health record integration, approach to education and training, key drivers of adoption, and tailoring of the CDS to the clinical context were handled differently between the 2 innovations, contributing to variation in their relative degrees of adoption and use. Attention to these factors had impacts on both near and later-term measures of success (eg, patient outcomes). DISCUSSION: CDS adoption is a well-studied early-term measure of CDS success that directly impacts outcomes. Adoption requires attention throughout the design phases of an intervention especially to key factors directly affecting it, including how implementation across multiple sites and systems complicates adoption, which prior experience with CDS matters, and that practice guidelines invariably require tailoring to the clinical context. CONCLUSION: With better planning for the capture of early-term measures of successful CDS implementation, especially adoption, critical adjustments may be made to ensure that the CDS is effectively implemented to be successful.

The Imperative for Patient-Centered Clinical Decision Support.

This commentary introduces the Patient-Centered Clinical Decision Support (PCCDS) Learning Network, which is collaborating with AcademyHealth to publish "Better Decisions Together" as part of eGEMs. Patient-centered clinical decision support (CDS) is an important vehicle to address broad issues in the U.S. health care system regarding quality and safety while also achieving better outcomes and better patient and provider satisfaction. Defined as CDS that supports individual patients and their care givers and/or care teams in health-related decisions and actions, PCCDS is an important step forward in advancing endeavors to move patient-centered care forward. The PCCDS Learning Network has developed a framework, referred to as the Analytic Framework for Action (AFA), to organize thinking and activities around PCCDS. A wide array of activities the PCCDS Learning Network is engaging in to inform and connect stakeholders is discussed.