Large age shifts in HIV-1 incidence patterns in KwaZulu-Natal, South Africa

Abstract

Recent declines in adult HIV-1 incidence have followed the large-scale expansion of antiretroviral therapy and primary HIV prevention across high-burden communities of sub-Saharan Africa. Mathematical modeling suggests that HIV risk will decline disproportionately in younger adult age-groups as interventions scale, concentrating new HIV infections in those >age 25 over time. Yet, no empirical data exist to support these projections. We conducted a population-based cohort study over a 16-y period (2004 to 2019), spanning the early scale-up of antiretroviral therapy and voluntary medical male circumcision, to estimate changes in the age distribution of HIV incidence in a hyperepidemic region of KwaZulu-Natal, South Africa, where adult HIV incidence has recently declined. Median age of HIV seroconversion increased by 5.5 y in men and 3.0 y in women, and the age of peak HIV incidence increased by 5.0 y in men and 2.0 y in women. Incidence declined disproportionately among young men (64% in men 15 to 19, 68% in men 20 to 24, and 46% in men 25 to 29) and young women (44% in women 15 to 19, 24% in women 20 to 24) comparing periods pre- versus post-universal test and treat. Incidence was stable (<20% change) in women aged 30 to 39 and men aged 30 to 34. Age shifts in incidence occurred after 2012 and were observed earlier in men than in women. These results provide direct epidemiological evidence of the changing demographics of HIV risk in sub-Saharan Africa in the era of large-scale treatment and prevention. More attention is needed to address lagging incidence decline among older individuals.

Keywords: HIV incidence; HIV prevention; age distribution; antiretroviral therapy.

Fig. 1.

Crude number of HIV seroconversions, py, and incidence rates observed by continuous age and year stratified on sex and averaged across 300 datasets with seroconversion randomly imputed between the last negative and first positive. The numbers are rounded to the zero-decimal place for py and seroconversions. Incidence rates over 100 per 100 py were observed in age-year bins where at least one seroconversion occurred in less than 1 py.

Fig. 2.

Year-specific cross-sections of incidence age distributions and 95% CIs from years 2004, 2012, and 2019. The largest difference in age distribution occurred in the latter half of the study period, between 2012 and 2019.

Fig. 3.

Smoothed age- and year-specific relative risks comparing age-specific incidence by year to age-specific incidence in 2004 (reference year).

Fig. 4.

Annual sex-specific trends in (A) median age at seroconversion, (B) age of peak incidence, (C) peak age-specific HIV incidence (per 100 py), and (D) proportion of the incidence age distribution under age 25. (B–D) Derived from modeled age-specific HIV incidence; A is calculated as the median age at seroconversion across n = 300 imputed datasets.

Fig. 5.

(Top) Fitted age distribution of HIV incidence for pre-UTT (2004 to 2015) and post-UTT (2016 to 2019). (Bottom) Categorical, age-specific IRRs comparing incidence post-UTT (2016 to 2019) to incidence pre-UTT (2004 to 2015).