A quality improvement collaborative increased preventive education and screening rates for women at high-risk for type 2 diabetes mellitus in primary care settings

Determinants for scalable adoption of autonomous AI in the detection of diabetic eye disease in diverse practice types: key best practices learned through collection of real-world data

Autonomous Artificial Intelligence (AI) has the potential to reduce disparities, improve quality of care, and reduce cost by improving access to specialty diagnoses at the point-of-care. Diabetes and related complications represent a significant source of health disparities. Vision loss is a complication of diabetes, and there is extensive evidence supporting annual eye exams for prevention. Prior to the use of autonomous AI, store-and-forward imaging approaches using remote reading centers (asynchronous telemedicine) attempted to increase diabetes related eye exams with limited success. In 2018, after rigorous clinical validation, the first fully autonomous AI system [LumineticsCore™ (formerly IDx-DR), Digital Diagnostics Inc., Coralville, IA, United States] received U.S. Food and Drug Administration (FDA) De Novo authorization. The system diagnoses diabetic retinopathy (including macular edema) without specialist physician overread at the point-of-care. In addition to regulatory clearance, reimbursement, and quality measure updates, successful adoption requires local optimization of the clinical workflow. The general challenges of frontline care clinical workflow have been well documented in the literature. Because healthcare AI is so new, there remains a gap in the literature about challenges and opportunities to embed diagnostic AI into the clinical workflow. The goal of this review is to identify common workflow themes leading to successful adoption, measured as attainment number of exams per month using the autonomous AI system against targets set for each health center. We characterized the workflow in four different US health centers over a 12-month period. Health centers were geographically dispersed across the Midwest, Southwest, Northeast, and West Coast and varied distinctly in terms of size, staffing, resources, financing and demographics of patient populations. After 1 year, the aggregated number of diabetes-related exams per month increased from 89 after the first month of initial deployment to 174 across all sites. Across the diverse practice types, three primary determinants underscored sustainable adoption: (1) Inclusion of Executive and Clinical Champions; (2) Underlining Health Center Resources; and (3) Clinical workflows that contemplate patient identification (pre-visit), LumineticsCore Exam Capture and Provider Consult (patient visit), and Timely Referral Triage (post-visit). In addition to regulatory clearance, reimbursement and quality measures, our review shows that addressing the core determinants for workflow optimization is an essential part of large-scale adoption of innovation. These best practices can be generalizable to other autonomous AI systems in front-line care settings, thereby increasing patient access, improving quality of care, and addressing health disparities.

Mothers' Perspectives on a Mother/Infant Dyad Postpartum Primary Care Program Following Gestational Diabetes Mellitus: A Qualitative Pilot Study

PURPOSE

The purpose of this study is to characterize mothers' experiences within a mother/infant dyad postpartum primary care program (Dyad) following gestational diabetes mellitus (GDM) to inform improvements in the delivery of care.

METHODS

A qualitative pilot study of women (n = 10) enrolled in a mother/infant Dyad program was conducted in a primary care practice at a large, urban academic medical center. Respondents were asked a series of open-ended questions about their experience with GDM, the Dyad program, and health behaviors. Interviews were audio-recorded, transcribed verbatim, and analyzed using ground theory with NVivo 12 Plus software.

RESULTS

Three key themes emerged: (1) Dyad program experience, (2) implementation of health behavior changes, and (3) acknowledgment of future GDM and type 2 diabetes mellitus (T2DM) health risks. Respondents found the Dyad program respondents felt that the program conveniently served mother and infant health care needs in a single appointment. Respondents also valued support from primary care providers when implementing health behavior changes. The Dyad program provided an opportunity for respondents to understand their current and future risk for developing GDM and T2DM.

CONCLUSIONS

Postpartum women enrolled in the Dyad program received highly personalized primary care services. The results of our study will help integrate patient-centered strategies into models for GDM care to maintain patient engagement in postpartum clinical services.

Mother-Infant Dyad program in primary care: evidence-based postpartum care following gestational diabetes

BACKGROUND

Gestational diabetes mellitus (GDM), a common complication of pregnancy, is associated with a 10-fold increased risk of type 2 diabetes mellitus (T2DM) compared to the general population. Evidence-based guidelines recommend that patients with GDM receive postpartum care for T2DM risk reduction including an oral glucose tolerance test (OGTT) 4-12 weeks after delivery, yet half of patients with GDM did not return for their postpartum visits by 12 weeks postpartum. Additionally, only 10% utilize primary care within 12 months of delivery and one-third of GDM patients receive timely postpartum OGTT.

OBJECTIVE

To determine if the Mother-Infant Dyad postpartum primary care program provides a framework to link well-child visits with postpartum primary care visits to increase postpartum clinical interactions promoting longitudinal care, such as postpartum visit attendance and T2DM screening.

STUDY DESIGN

All patients with a diagnosis of GDM that received care at a postpartum mother-infant dyad program at a Midwestern academic medical center internal medicine and pediatrics primary care clinic were enrolled. Clinic level data was obtained by baseline and 6-month post-enrollment surveys and chart review. A comparison population was identified from Medicaid claims data using propensity score matching to enable a comparison of program participants' outcomes to a population comprised of similar individuals diagnosed with GDM that received care at sites not participating in the Dyad program. Our primary outcome was completion of T2DM screening in the 4-12 week postpartum period. The secondary outcomes were postpartum visit attendance with a prenatal provider, and prediabetes diagnoses.

RESULTS

A total of 75 mother-infant dyads were seen by the clinic. Of the enrolled women, 43% were Non-Hispanic White and 30% were Non-Hispanic Black; mean age was 30.75 years. The matched comparison group (n = 62) had a mean age of 30.75 years, were 43% Non-Hispanic White and 30% Non-Hispanic Black. Women who participated in the program were more likely to receive T2DM screenings than women who did not participate (87 vs. 79%, p<.001) and complete postpartum visits (95 vs. 58%, respectively; p<.001). Additionally, a higher rate of new prediabetes diagnoses was observed (12 vs. 6%, p < .001).

CONCLUSION

The Mother-Infant Dyad postpartum primary care program improved T2DM screenings and postpartum visit attendance. In addition, a greater proportion of Dyad program participants experienced new prediabetes diagnoses that those in the comparison group. Our findings suggest that the dyad care model, in which women with GDM engage in postpartum primary care concurrent with well-child visits, can improve longitudinal postpartum care after a GDM diagnosis.