Community Health Workers as Trust Builders and Healers: A Cohort Study in Primary Care

Abstract

Purpose: Improving patients' self-care for chronic disease is often elusive in the context of social deprivation. We evaluated whether a practice-integrated community health worker (CHW) intervention could encourage effective long-term self-management of type 2 diabetes mellitus (T2DM).

Methods: This cohort study, in a safety-net primary care practice, enrolled patients with uncontrolled T2DM and psychosocial risk factors. Patients were identified through a practice diabetes registry or by clinicians' referrals. The CHWs engaged patients in trust building and sensemaking to understand their social context, identify goals, navigate health care, and connect to community resources. Primary outcome was progress through 3 prospectively defined stages of self-care: outreach (meeting face-to-face); stabilization (collaborating to address patients' life circumstances); and self-care generativity (achieving self-care competencies). Secondary outcomes were change in hemoglobin A_1c (HbA_1c) and need for urgent care, emergency department, or hospital visits.

Results: Of 986 participating patients, 27% remained in outreach, 41% progressed to stabilization, and 33% achieved self-care generativity. Repeated measures ANOVA demonstrates an overall decline in HbA_1c, without group differences, through the 4th HbA_1c measurement (mean follow-up 703 days). Beginning at the 5th HbA_1c measurement (mean 859 days), the self-care generativity group achieved greater declines in HbA_1c, which widened through the 10th measurement (mean 1,365 days) to an average of 8.5% compared with an average of 8.8% in the outreach group and 9.0% in the stabilization group (P = .003). Rates of emergency department and hospital visits were lower in the self-care generativity group.

Conclusions: Practice-linked CHWs can sustainably engage vulnerable patients, helping them advance self-management goals in the context of formidable social disadvantage.

Keywords: community health worker; primary care; self-management; trust; type 2 diabetes.

Figure 1.

Glycoslyated hemoglobin trajectories by care periods. HbA = hemoglobin A Note: Marginal means for HbA are estimated for sequential measurement episodes during follow-up. Covariates appearing in the model were evaluated at age 55.7 and insurance 0.59. Difference between outreach and stabilization groups significant at P <.001 and between outreach and self-care generatively groups significant at P <.002.

Figure 2.

Predicted average count of health care visits, unadjusted and adjusted. ^a Values were adjusted for age, sex, health insurance status, and prior-year utilization.

Figure 2.

Predicted average count of health care visits, unadjusted and adjusted. ^a Values were adjusted for age, sex, health insurance status, and prior-year utilization.