A Fair Individualized Polysocial Risk Score for Identifying Increased Social Risk in Type 2 Diabetes

Background

Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications. It is crucial to implement effective social risk management strategies at the point of care.

Objective

To develop an electronic health records (EHR)-based machine learning (ML) analytical pipeline to address unmet social needs associated with hospitalization risk in patients with T2D.

Methods

We identified real-world patients with T2D from the EHR data from University of Florida (UF) Health Integrated Data Repository (IDR), incorporating both contextual SDoH (e.g., neighborhood deprivation) and individual-level SDoH (e.g., housing instability). The 2015-2020 data were used for training and validation and 2021-2022 data for independent testing. We developed a machine learning analytic pipeline, namely individualized polysocial risk score (iPsRS), to identify high social risk associated with hospitalizations in T2D patients, along with explainable AI (XAI) and fairness optimization.

Results

The study cohort included 10,192 real-world patients with T2D, with a mean age of 59 years and 58% female. Of the cohort, 50% were non-Hispanic White, 39% were non-Hispanic Black, 6% were Hispanic, and 5% were other races/ethnicities. Our iPsRS, including both contextual and individual-level SDoH as input factors, achieved a C statistic of 0.72 in predicting 1-year hospitalization after fairness optimization across racial and ethnic groups. The iPsRS showed excellent utility for capturing individuals at high hospitalization risk because of SDoH, that is, the actual 1-year hospitalization rate in the top 5% of iPsRS was 28.1%, ~13 times as high as the bottom decile (2.2% for 1-year hospitalization rate).

Conclusion

Our ML pipeline iPsRS can fairly and accurately screen for patients who have increased social risk leading to hospitalization in real word patients with T2D.

Smart Meds: Using Pharmacists to Address Health Literacy Disparities Among Medically- and Socially-Vulnerable Populations

Patients in historically underserved communities are most vulnerable to uncontrolled chronic conditions and report a lack of health knowledge to manage them. This report aims to describe the development of SMART MEDS, a pharmacy-led program implemented to address health literacy disparities among medically and socially vulnerable patients.

Study protocol for a type III hybrid effectiveness-implementation trial to evaluate scaling interoperable clinical decision support for patient-centered chronic pain management in primary care

Background

The US continues to face public health crises related to both chronic pain and opioid overdoses. Thirty percent of Americans suffer from chronic noncancer pain at an estimated yearly cost of over $600 billion. Most patients with chronic pain turn to primary care clinicians who must choose from myriad treatment options based on relative risks and benefits, patient history, available resources, symptoms, and goals. Recently, with attention to opioid-related risks, prescribing has declined. However, clinical experts have countered with concerns that some patients for whom opioid-related benefits outweigh risks may be inappropriately discontinued from opioids. Unfortunately, primary care clinicians lack usable tools to help them partner with their patients in choosing pain treatment options that best balance risks and benefits in the context of patient history, resources, symptoms, and goals. Thus, primary care clinicians and patients would benefit from patient-centered clinical decision support (CDS) for this shared decision-making process.

Methods

The objective of this 3-year project is to study the adaptation and implementation of an existing interoperable CDS tool for pain treatment shared decision making, with tailored implementation support, in new clinical settings in the OneFlorida Clinical Research Consortium. Our central hypothesis is that tailored implementation support will increase CDS adoption and shared decision making. We further hypothesize that increases in shared decision making will lead to improved patient outcomes, specifically pain and physical function. The CDS implementation will be guided by the Exploration, Preparation, Implementation, Sustainment (EPIS) framework. The evaluation will be organized by the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework. We will adapt and tailor PainManager, an open source interoperable CDS tool, for implementation in primary care clinics affiliated with the OneFlorida Clinical Research Consortium. We will evaluate the effect of tailored implementation support on PainManager’s adoption for pain treatment shared decision making. This evaluation will establish the feasibility and obtain preliminary data in preparation for a multi-site pragmatic trial targeting the effectiveness of PainManager and tailored implementation support on shared decision making and patient-reported pain and physical function.

Discussion

This research will generate evidence on strategies for implementing interoperable CDS in new clinical settings across different types of electronic health records (EHRs). The study will also inform tailored implementation strategies to be further tested in a subsequent hybrid effectiveness-implementation trial. Together, these efforts will lead to important new technology and evidence that patients, clinicians, and health systems can use to improve care for millions of Americans who suffer from pain and other chronic conditions.

Trial registration

ClinicalTrials.gov, NCT05256394, Registered 25 February 2022.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13012-022-01217-4.

Incorporating Black women’s perspectives into long-acting reversible contraception implementation

Objective

To study urban, predominantly Black women’s expressed opinions and beliefs related to the use of contraceptives to better inform implementation strategies designed to increase the use of highly effective contraceptives among minoritized and low-income women.

Design

Focus group interviews with women, in conjunction with a community-based organization providing programs for underserved women with a mission of improved women and infant health.

Setting

Focus groups were conducted, and women were recruited from clinical sites in predominantly African American urban neighborhoods in a southeastern US city.

Patient(s)

Self-identified 18–35-year-old women recruited from clinical sites in the urban core of the city with an 80% African American population.

Intervention(s)

No interventions tested.

Main Outcome Measure(s)

Black women’s opinions and concerns about contraception.

Results

Key insights from the focus group results for healthcare providers include the following: the importance of framing discussions with patients within the context of the patients’ goals; need to acknowledge and respect the support systems that women rely on for child birthing and childcare; recognition of the clinician’s role as a trusted and respected source of information; and need to understand and be prepared to address much of the inaccurate and misleading information that can interfere with the patients’ optimal choices for contraception.

Conclusions

A critical component for applying the implementation science theory to increase the use of evidence-based practices, such as implementation of highly effective contraceptives, requires understanding women’s perspectives of the factors influencing their decisions to use highly effective contraceptives. This study provides important insights into the following: the potential barriers inherent in minoritized women’s concerns about contraceptives and how these insights can inform implementation strategies such as patient-centered counseling and education to overcome those barriers.

Implementation Research as Applied Science: Bridging the Research to Practice Gap

Implementation research is intended to address challenges posed by the slow adoption of evidence-based science by the medical and health promotion practice community. A case study approach is used to illustrate and discuss the use of Quality improvement and Evaluation as an applied approach to implementation science in contrast of more classic purposes of research. Quality improvement was the implementation model used to facilitate organizational change needed to adopt the use of texting to report sexually transmitted infection test results in over a fifth of Florida's larger county health departments. Both quantitative and qualitative methods were used to evaluate implementation. All seven participating county health departments were successful in enrolling clients in texting with extensive variation (24% to 72%) in texting enrollment at the end of the 10-month study. Statistically significant outcomes for those enrolled in texting were recorded through Florida's online sexually transmitted infection reporting system in the form of increased number of people receiving early (1-4 days) treatment and reductions in delayed (≥8 days) or no treatment. This study illustrates an applied approach to implementation research which may be critical to adapt emerging evidence and technologies to the multiple and complex characteristics of the diverse populations served by health promotion institutions.

Seeing the quality improvement forest through the quality improvement trees: A meta-synthesis of case studies in Florida and Georgia

Objectives

To identify important characteristics of quality improvement applications for population health and healthcare settings and to explore the use of quality improvement as a model for implementing and disseminating evidence-based or best practices.

Methods

A meta-synthesis was used to examine published quality improvement case studies. A total of 10 published studies that were conducted in Florida and Georgia were examined and synthesized using meta-synthesis (a qualitative research methodology) for meaningful insights and lessons learned using defined meta-synthesis inclusion criteria. The primary focus of the analysis and synthesis were the reported processes and findings that included responses to structured questioning in addition to emergent results from direct observation and semi-structured open-ended interviewing.

Results

The key insights for the use of quality improvement in public health and healthcare settings included (1) the essential importance of data monitoring, analysis, and data-based decision making; (2) the need to focus on internal mutable factors within organizations; (3) the critical role of quality improvement team group dynamics; (4) the value of using a quality improvement collaborative or multi-clinic quality council/committee for sharing and comparing performance on key metrics; and (5) the need to identify a quality improvement approach and methods for clarification as a structured quality improvement intervention.

Conclusion

In addition to the advantages of using quality improvement to enhance or improve healthcare and public health services, there is also potential for quality improvement to serve as a model for enhancing the adoption of evidence-based practices within the context of dissemination and implementation research.

Utilization management and information technology: adapting to the new era

Overuse of clinical laboratory services has been written about for many years (1), but remedies that easily could be implemented and effective over the long term have been in short supply. This issue has been acute for CLS, Inc., which is wholly owned by a managed care organization (HIP Health Plan of New York). Because CLS is assessing the possibility of acquiring a new laboratory information system, we reviewed past reports on approaches to utilization management (UM) and considered how developments in information technology (IT) may affect the latter. We feel there is a distinct possibility for implementation of UM in real time, and we propose this as a new paradigm whose realization has implications for choice of IT and for how clinical laboratories operate in the future.

The role of reflexive (algorithmic) testing in laboratory medicine: adapting to the new era

Centralized Laboratory Services, Inc. (CLS) is a large, freestanding laboratory that is an affiliate of the Health Insurance Plan of New York, a managed care organization with more than 1 million members in New York and New Jersey. The laboratory work for this membership is consolidated at CLS, which thus serves an ambulatory patient population. The Medical Director at CLS is charged with optimizing laboratory utilization by clinicians who are part of the system.

Selection factors in the choice of immunoassay technology: implementing technology in the new era

Centralized Laboratory Services, Inc. is a large, freestanding laboratory that underwent a major equipment reconfiguration for the performance of endocrine/tumor marker/anemia assays (N = 15) in August 1995. Before the transition these assays were done on six instruments, none of which were computer interfaced. All assays were subsequently consolidated on four ACS-180+ instruments (Chiron Diagnostics, Norwood, MA), which were interfaced to our laboratory information system (Cerner Corp, Kansas City, MO). Our experience suggests that significant increases in productivity and reductions in cost are possible through instrument upgrades. Both laboratory-specific and analytical system-specific factors were found to be important in the optimal selection of immunoassay technology. As laboratorians necessarily adjust to changing economic and organizational circumstances and are compelled to "do more with less," technology assessment will become an increasingly important function for senior laboratory management.