Incorporating oral PrEP into standard prevention services for South African women: a nested interrupted time-series study

Abstract

Background: As oral pre-exposure prophylaxis (PrEP) becomes the standard of prevention globally, its potential effect on HIV incidence in clinical trials of new prevention interventions is unknown, particularly for trials among women. In a trial measuring HIV incidence in African women, oral PrEP was incorporated into the standard of prevention in the trial's last year. We assessed the effect of on-site access to PrEP on HIV incidence in this natural experiment.

Methods: We did a nested interrupted time-series study using data from the ECHO trial. At 12 sites in four countries (Eswatini, Kenya, South Africa, and Zambia), women (aged 16-35 years) were randomly assigned to receive one of three contraceptives between Dec 14, 2015, and Sept 12, 2017, and followed up quarterly for up to 18 months to determine the effect of contraceptive method on HIV acquisition. Women were eligible if they wanted long-acting contraception, were medically qualified to receive study contraceptives, and had not used any of the study contraceptives in the past 6 months. The present analyses are limited to nine South African sites where on-site access to oral PrEP was implemented between March 13 and June 12, 2018. Using an interrupted time-series design, we compared HIV incidence before versus after PrEP access, limited to quarterly study visits at which on-site PrEP access was available to at least some participants and, in a sensitivity analysis, to the 180 days before and after access. The outcome was incident HIV infection, detected using two rapid HIV tests done in parallel for each participant at every scheduled follow-up visit. This study is registered on ClinicalTrials.gov, NCT02550067.

Findings: 2124 women were followed up after on-site PrEP access began, of whom 543 (26%) reported PrEP use. A total of 12 HIV seroconversions were observed in 556 person-years (incidence 2·16%) after on-site PrEP access, compared with 133 HIV seroconversions in 2860 person-years (4·65%) before PrEP access (adjusted incidence rate ratio [IRR] 0·45, 95% CI 0·25-0·82, p=0·0085). Similar results were also observed when limiting the analysis to 180 days before versus after PrEP access. A total of 46 HIV seroconversions were observed in 919 person-years within 180 days before PrEP access, compared with 11 seroconversions in 481 person-years in the 180 days following PrEP access (incidence 5·00 vs 2·29 per 100 person-years; IRR 0·43, 95% CI 0·22-0·88, p=0·012).

Interpretation: On-site access to PrEP as part of standard of prevention in a clinical trial among women in South Africa was associated with halving HIV incidence, when approximately a quarter of women started PrEP. Providing access to on-site PrEP could decrease incidence in HIV prevention trials. These data are also among the first to show in any setting that access to PrEP is associated with decreased HIV acquisition among South African women.

Funding: Bill & Melinda Gates Foundation, United States Agency for International Development, President's Emergency Plan for AIDS Relief, the Swedish International Development Cooperation Agency, South African Medical Research Council, and United Nations Population Fund.

Figure 1

Study visits included in the analysis, compared with total study visits Number of visits with each type of PrEP access are shown for two different time scales. (A) Study visits (months since participant enrolment). (B) Calendar time (month since first participant enrolled). Distribution of visits with PrEP access through the national standard of care (orange) or on-site implementation (blue) are shown. The upper plots show all study visits and the lower plots show study visits that are included in the analysis. For the study visit time scale, study visits were included if both types of access occurred; for the calendar time scale, intervals within 180 days entirely before and after on-site PrEP access are included (intervals including the transition to PrEP access are excluded). PrEP=pre-exposure prophylaxis.

Figure 2

IRR comparing HIV incidence before and after fake dates of on-site PrEP access Change in HIV incidence for a fake access date is compared using two different time scales, as for the analysis of true date of on-site access. (A) Study visit showing a comparison within the same study visits for women with and without access to PrEP. (B) Calendar time showing a comparison close to the same calendar time for women with and without access. IRR=incidence rate ratio. PrEP=pre-exposure prophylaxis.