Ability of epidemiological studies to monitor HPV post-vaccination dynamics: a simulation study

Abstract

Genital human papillomavirus (HPV) infections are caused by a broad diversity of genotypes. As available vaccines target a subgroup of these genotypes, monitoring transmission dynamics of nonvaccine genotypes is essential. After reviewing the epidemiological literature on study designs aiming to monitor those dynamics, we evaluated their abilities to detect HPV-prevalence changes following vaccine introduction. We developed an agent-based model to simulate HPV transmission in a heterosexual population under various scenarios of vaccine coverage and genotypic interaction, and reproduced two study designs: post-vs.-prevaccine and vaccinated-vs.-unvaccinated comparisons. We calculated the total sample size required to detect statistically significant prevalence differences at the 5% significance level and 80% power. Although a decrease in vaccine-genotype prevalence was detectable as early as 1 year after vaccine introduction, simulations indicated that the indirect impact on nonvaccine-genotype prevalence (a decrease under synergistic interaction or an increase under competitive interaction) would only be measurable after >10 years whatever the vaccine coverage. Sample sizes required for nonvaccine genotypes were >5 times greater than for vaccine genotypes and tended to be smaller in the post-vs.-prevaccine than in the vaccinated-vs.-unvaccinated design. These results highlight that previously published epidemiological studies were not powerful enough to efficiently detect changes in nonvaccine-genotype prevalence.

Keywords: Agent-based modelling; genotype interactions; human papillomavirus; observational study simulations; vaccination.

Fig. 1.

Schematic view of components of the agent-based model and simulation results of vaccine (V)- and nonvaccine (NV)-genotype prevalences over time (median values over 100 iterations) assuming 60% vaccine coverage and selected V–NV-genotype interaction strengths (γ): (A) all women (all ages); (B) vaccinated and (C) unvaccinated women of ages targeted by vaccination. Results from A were used for post-vs.-prevaccine comparisons, while results from B and C combined were used for vaccinated-vs.-unvaccinated comparisons. The dashed vertical line at 15 years indicates when all age cohorts have been offered the vaccine. For V genotypes, the 3 curves according to interaction strength overlapped.

Fig. 2.

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram.

Fig. 3.

Prevalence differences reported in observational studies for V (a and b) and NV (c and d) high-risk genotypes by study design: post-vs.-prevaccine (a and c) and vaccinated-vs.-unvaccinated (b and d), according to vaccine coverage (colour gradient from yellow, low coverage to purple, high coverage) and sample size (dot size from small, low sample size to large, large sample size). Vertical intervals correspond to reported 95% confidence intervals while horizontal lines correspond to the time span covered.

Fig. 4.

Prevalence differences for V genotypes (a and b) and corresponding sample sizes (c and d) over time according to epidemiological study design (a and c: post-vs.-prevaccine (post-vs.-pre), b and d: vaccinated vs. unvaccinated (vac-vs.-unvac) comparisons) and vaccine coverage under the neutral interaction scenario (γ = 1). The dashed vertical line at 15 years indicates when all age cohorts have been offered the vaccine. Results shown are medians and 90% empirical intervals over 100 simulations.

Fig. 5.

Absolute prevalence-difference values for NV genotypes (a) and corresponding sample sizes (b) over time according to strength of competitive, neutral and synergistic interactions (γ), epidemiological study design (post-vs.-pre or vaccinated-vs.-unvaccinated) and vaccine coverage. Dashed vertical lines at 15 years indicate when all age cohorts have been offered the vaccine. Median values and 90% empirical intervals over 100 simulations are shown. For synergistic values, prevalence differences are negative; they are presented here as absolute values for ease of comparability.

Fig. 6.

Prevalence differences for (a) V- and (b) NV-genotypes over time under strong synergistic interaction (γ = 1.5), according to the individual's number of partners during the past year, epidemiological study design (post-vs.-pre or vaccinated-vs.-unvaccinated) and vaccine coverage. Dashed vertical lines at 15 years indicate when all age cohorts have been offered the vaccine. Median values and 90% empirical intervals over 100 simulations are reported; V- or NV-genotype prevalence before vaccine introduction in each sexual activity group is specified on each graph.