Background Adherence clubs, where groups of 25-30 patients who are virally suppressed on antiretroviral therapy (ART) meet for counseling and medication pickup, represent an innovative model to retain patients in care and facilitate task-shifting. This intervention replaces traditional clinical care encounters with a 1-hour group session every 2-3 months, and can be organized at a clinic or a community venue. We performed a pragmatic randomized controlled trial to compare loss from club-based care between community- and clinic-based adherence clubs. Methods and findings Patients on ART with undetectable viral load at Witkoppen Health and Welfare Centre in Johannesburg, South Africa, were randomized 1:1 to a clinic- or community-based adherence club. Clubs were held every other month. All participants received annual viral load monitoring and medical exam at the clinic. Participants were referred back to clinic-based standard care if they missed a club visit and did not pick up ART medications within 5 days, had 2 consecutive late ART medication pickups, developed a disqualifying (excluding) comorbidity, or had viral rebound. From February 12, 2014, to May 31, 2015, we randomized 775 eligible adults into 12 pairs of clubs376 (49%) into clinic-based clubs and 399 (51%) into community-based clubs. Characteristics were similar by arm: 65% female, median age 38 years, and median CD4 count 506 cells/mm(3). Overall, 47% (95% CI 44%-51%) experienced the primary outcome of loss from club-based care. Among community-based club participants, the cumulative proportion lost from club-based care was 52% (95% CI 47%-57%), compared to 43% (95% CI 38%-48%, p = 0.002) among clinic-based club participants. The risk of loss to club-based care was higher among participants assigned to community-based clubs than among those assigned to clinic-based clubs (adjusted hazard ratio 1.38, 95% CI 1.02-1.87, p = 0.032), after accounting for sex, age, nationality, time on ART, baseline CD4 count, and employment status. Among those who were lost from club-based care (n = 367), the most common reason was missing a club visit and the associated ART medication pickup entirely (54%, 95% CI 49%-59%), and was similar by arm (p = 0.086). Development of an excluding comorbidity occurred in 3% overall of those lost from club-based care, and was not different by arm (p = 0.816); no deaths occurred in either arm during club-based care. Viral rebound occurred in 13% of those lost from community club-based care and 21% of those lost from clinic-based care (p = 0.051). In post hoc secondary analysis, among those referred to standard care, 72% (95% CI 68%-77%) reengaged in clinic-based care within 90 days of their club-based care discontinuation date. The main limitations of the trial are the lack of a comparison group receiving routine clinic-based standard care and the potential limited generalizability due to the single-clinic setting. Conclusions These findings demonstrate that overall loss from an adherence club intervention was high in this setting and that, importantly, it was worse in community-based adherence clubs compared to those based at the clinic. We urge caution in assuming that the effectiveness of clinic-based interventions will carry over to community settings, without a better understanding of patient-level factors associated with successful retention in care.
