Quantitative assessment of the impact of partially protective anti-schistosomiasis vaccines

Abstract

Background: Mass drug administration (MDA) of praziquantel has been the intervention of choice against schistosomiasis but with limited success in interrupting the transmission. The development of anti-Schistosoma vaccines is underway. Our objective is to quantify the population-level impact of anti-Schistosoma vaccines when administered alone and in combination with mass drug administration (MDA) and determine factors in vaccine design and public health implementation that optimize vaccination role in schistosomiasis control and elimination.

Methods and findings: We developed a deterministic compartmental model simulation of schistosomiasis transmission in a high-risk Kenyan community, including stratification by age, parasite burden, and vaccination status. The modeled schistosomiasis vaccines differed in terms of vaccine duration of protection (durability) and three biological efficacies. These are vaccine susceptibility effect (SE) of reducing person's susceptibility to Schistosoma acquisition, vaccine mortality effect (ME) of reducing established worm burden and vaccine fecundity effect (FE) of reducing egg release by mature worms. We quantified the population-level impact of vaccination over two decades under diverse vaccination schemes (childhood vs. mass campaigns), with different age-targeting scenarios, different risk settings, and with combined intervention with MDA. We also assessed the sensitivity of our predictions to uncertainties in model parameters. Over two decades, our base case vaccine with 80% SE, FE, and ME efficacies, 10 years' durability, provided by mass vaccination every 10 years, reduced host prevalence, mean intensity, incidence, and patent snail prevalence to 31%, 20 eggs/10-ml sample/person, 0.87 worm/person-year, and 0.74%, from endemic-state values of 71%, 152, 3.3, and 0.98%, respectively. Lower impact was found when coverage did not encompass all potential contaminators, and childhood-only vaccination schemes showed delayed and lower impact. In lower prevalence settings, the base case vaccine generated a proportionately smaller impact. A substantially larger vaccine program effect was generated when MDA + mass vaccination was provided every 5 years, which could be achieved by an MDA-only program only if drug was offered annually. Vaccine impact on schistosomiasis transmission was sensitive to a number of parameters including vaccine efficacies, human contact rates with water, human density, patent snails' rate of patency and lifespan, and force of infection to snails.

Conclusions: To be successful a vaccine-based control strategy will need a moderately to highly effective formulation combined with early vaccination of potential contaminators and aggressive coverage in repeated rounds of mass vaccination. Compared to MDA-only program, vaccination combined with MDA accelerates and prolongs the impact by reducing the acquisition of new worms and reducing egg release from residual worms.

Fig 1. Population-level impact of Base Case Vaccine (BCV) administered in the simulated Kenyan community.

The impact is shown on (A) human host prevalence, (B) patent snail prevalence, (C) the number of eggs/10-ml sample/person (mean intensity) and (D) the number of new worms acquired per person per year (incidence). The vaccine’s efficacies are SE = FE = ME = 80%, with a mean duration of protection (D) of ten years. Two schedules with universal coverage are shown: mass vaccination every 10 years for three rounds of vaccination (Mass BCV every 10 years) and vaccination of newborns (BCV in childhood). Pre-control endemic values were 71% prevalence, 1% snail patency, 152 eggs/10-ml sample/person mean intensity, and 3.3 worms/person/year incidence.

Fig 2. The effect of coverage level attained in mass vaccination rounds on the population-level impact of Base Case Vaccine (BCV).

The impact at different coverage levels is shown on (A) human host prevalence, (B) patent snail prevalence, (C) the number of eggs/10-ml sample/person (mean intensity) and (D) the number of new worms acquired per person per year (incidence). The vaccine’s efficacies are SE = FE = ME = 80%, with a mean duration of protection (D) of ten years. Rounds of mass vaccination campaigns are assumed every 10 years at coverage levels of 20%, 60%, 80% and universal coverage. The percentage vaccinated is assumed to be randomly assigned.

Fig 3. The effect of higher vaccination frequency using the Base Case Vaccine (BCV) on four outcomes.

The base case vaccine with a mean duration of protection of ten years (D = 10) is given according to different mass vaccination frequencies every ten, five and one years with universal coverage in each round. The panels indicate the impact of vaccination on (A) human host prevalence, (B) patent snail prevalence, (C) mean intensity of human infection (eggs/10-ml sample/person or e/s/p) and (D) incidence measured as the number of new worms acquired per person-year (w/p-y).

Fig 4. The effect of shorter duration of vaccine effect on four outcomes.

The vaccine is assumed to have different durations of effect, either 10, 5, or 2 years, with the mass vaccination administered at frequency intervals set equal to vaccine durability (adaptive vaccination frequency) with universal coverage in each round. The panels indicate the impact of vaccination on (A) human host prevalence, (B) patent snail prevalence, (C) mean intensity of human infection (eggs/10-ml sample/person or e/s/p) and (D) incidence measured as the number of new worms acquired per person-year (w/p-y).

Fig 5. The effect of sub-maximal coverage when vaccination is targeted to high-risk age groups.

Our predictions comparing a mass vaccination schedule with universal coverage (blue solid line, corresponding to predictions in Fig 1) versus targeted universal vaccination of persons of age 5–24 every 10 years (red dash-dotted line) or every 5 years (green dotted line). The panels indicate the impact of vaccination on (A) human host prevalence, (B) patent snail prevalence, (C) mean intensity of human infection (eggs/10-ml sample/person or e/s/p) and (D) incidence measured as the number of new worms acquired per person-year (w/p-y).

Fig 6. Predicted impact of mass vaccination with universal coverage in diverse schistosomiasis endemic settings at years 2, 12 and 22 following one, two, or three mass vaccination rounds, respectively.

By increasing the transmission parameters, different endemic settings with different contact rates—represented by the pre-vaccination host intensity in the abscissa—were generated. The absolute drop in host prevalence (panel A), absolute drop in patent snail prevalence (panel B), and the absolute drop in mean number of eggs/10-ml sample/person (panel C) are calculated at years 2, 12 and 22 by subtracting the value post-intervention from the value pre-intervention. Panel D shows the number of vaccinations needed in the first round to prevent the accrual of one new worm by persons in the community during one year after the first round of vaccination.

Fig 7. The impact of vaccination in terms of four outcomes in the short-term (year 2) and the long-term (year 22) at different assumptions of vaccine efficacies.

The vaccine durability and the frequency of mass vaccination are both assumed to be 10 years assuming universal coverage in each round of vaccination. The unit (e/s/p) stands for the number of eggs per 10ml sample per person and (w/p-y) stands for the number of new worms acquired per person-year.

Fig 8. The impact of combined intervention (PZQ + vaccine) on four outcomes.

The panels indicate the impact of different interventions on (A) human host prevalence, (B) patent snail prevalence, (C) mean intensity of human infection (eggs/10-ml sample/person or e/s/p) and (D) incidence measured as the number of new worms acquired per person-year (w/p-y). Vaccine durability in years is indicated in the legend by the value of D. For comparison we included a scenario of base case vaccine (BCV) without MDA (a vaccine with 80% efficacy and 10-year durability offered in mass campaigns every 10 years) shown as blue dashed line without markers. Universal coverage is assumed in each round of intervention. To compare the additional impact of vaccines relative to PZQ-only interventions, a corresponding figure without vaccine intervention (PZQ-only) is provided in S3 Fig.