Modelling the public health impact of male circumcision for HIV prevention in high prevalence areas in Africa

Abstract

Background: Recent clinical trials in Africa, in combination with several observational epidemiological studies, have provided evidence that male circumcision can reduce HIV female-to-male transmission risk by 60% or more. However, the public health impact of large-scale male circumcision programs for HIV prevention is unclear.

Methods: Two mathematical models were examined to explore this issue: a random mixing model and a compartmental model that distinguishes risk groups associated with sex work. In the compartmental model, two scenarios were developed, one calculating HIV transmission and prevalence in a context similar to the country of Botswana, and one similar to Nyanza Province, in western Kenya.

Results: In both models, male circumcision programs resulted in large and sustained declines in HIV prevalence over time among both men and women. Men benefited somewhat more than women, but prevalence among women was also reduced substantially. With 80% male circumcision uptake, the reductions in prevalence ranged from 45% to 67% in the two "countries", and with 50% uptake, from 25% to 41%. It would take over a decade for the intervention to reach its full effect.

Conclusion: Large-scale uptake of male circumcision services in African countries with high HIV prevalence, and where male circumcision is not now routinely practised, could lead to substantial reductions in HIV transmission and prevalence over time among both men and women.

Figure 1

Structure of the compartmental model. Boxes represent compartments, i.e. the states males or females can be in. Arrows represent flows of individuals between compartments. High risk groups are male clients of sex workers, and female sex workers (csw). Disease progression is subdivided into 2 stages: early and late, including AIDS. Individuals (men) move to the circumcised boxes after circumcision. The flow diagram for women is similar except that there exists no circumcised compartment. Symbols refer to compartments and flows formally defined in the Additional file 1 (Compartments: M = male, F = female; first subscript: 1 = low risk group, 2 = high risk group; second subscript: 1 = uninfected, 2 = early HIV, 3 = late HIV, 4 =circumcised and uninfected. Flows: a = from low risk to high risk group, b = from high risk to low risk group, c = circumcision, i = infection, p = progression (to late stage HIV infection), q = death)

Figure 2

The relationship between R₀, male circumcision (MC), and sex-specific equilibrium HIV prevalence, under a random mixing assumption, assuming different levels of heterogeneity of sexual behaviour (rates of partner change). The distribution of male and female rates of partner change (x) are assumed to be N^m(x) ~Gamma(x, p^m, α^m) and N^f(x) ~Gamma(x, p^f, α^f) respectively. Bottom panel: homogeneous rates of partner change; middle panel: moderate heterogeneity in rates of partner change with parameters p^m = 1 & p^f = 0.5; top panel: high heterogeneity in rates of partner change with parameters p^m = 0.5 & p^f = 0.25. Continuous arrows indicate the approximate position of "Botswana" and the dotted arrow indicates the approximate position of "Nyanza".

Figure 3

The impact of male circumcision (MC) on HIV prevalence in the Botswana setting, according to our compartmental model, with high, 80%, MC uptake (bottom panel) and moderate, 50%, MC uptake (top panel). Predictions are for the period 2000–2100, when male circumcision is introduced in 2010. In addition the figure shows the results of 4 different sensitivity analyses: RR0.25: if protection afforded by circumcision would be as high 75% (RR 0.25); RR0.60: if it would be as low as 40% (RR 0.60); DISINHIB: if it would lead to disinhibition in the sense that condom use in high risk sex would be abandoned; MF 0.75: if male circumcision would reduce the risk of male-to-female transmission by 25%.

Figure 4

The impact of male circumcision (MC) on HIV prevalence in the Nyanza setting, according to our compartmental model, with high, 80%, MC uptake (bottom panel) and moderate, 50%, MC uptake (top panel). Predictions are for the period 2000–2100, when male circumcision is introduced in 2010. In addition the figure shows the results of 4 different sensitivity analyses:RR0.25: if protection afforded by circumcision would be as high 75% (RR 0.25); RR0.60: if it would be as low as 40% (RR 0.60); DISINHIB: if it would lead to disinhibition in the sense that condom use in high risk sex would be abandoned; MF 0.75: if male circumcision would reduce the risk of male-to-female transmission by 25%.