Adverse event profile of a mature voluntary medical male circumcision programme performing PrePex and surgical procedures in Zimbabwe

Introduction: The frequency of adverse events (AEs) is a widely used indicator of voluntary medical male circumcision (VMMC) programme quality. Though over 11.7 million male circumcisions (MCs) have been performed, little published data exists on the profile of AEs from mature, large-scale programmes. No published data exists on routine implementation of PrePex, a device-based MC method. Methods: The ZAZIC Consortium began implementing VMMC in Zimbabwe in 2013, supporting services at 36 facilities. Aggregate data on VMMC outputs are collected monthly from each facility. Detailed forms are completed describing the profile of each moderate and severe AE. Bivariate and multivariable analyses were conducted using log-binomial regression models. Results: From October 2014 through September 2015, 44,868 clients were circumcised with 156 clients experiencing a moderate or severe AE. 96.2% of clients had a follow-up visit within 14 days of their procedure. AEs were uncommon, with 0.3% (116/41,416) of surgical and 1.2% (40/3,452) of PrePex clients experiencing a moderate or severe AE. After adjusting for VMMC site, we found that PrePex was associated with a 3.29-fold (95% CI: 1.78-6.06) increased risk of experiencing an AE compared to surgical procedures. Device displacements, when the PrePex device is intentionally or accidentally dislodged during the 7-day placement period, accounted for 70% of PrePex AEs. The majority of device displacements were intentional self-removals. Overall, infection was the most common AE among VMMC clients. Compared to clients aged 20 and above, clients aged 10-14 were 3.07-fold (95% CI: 1.36-6.91) more likely to experience an infection and clients aged 15-19 were 1.80-fold (95% CI: 0.82-3.92) more likely to experience an infection, adjusted for site. Conclusions: This exploratory analysis found that clients receiving PrePex were more likely to experience an AE than surgical circumcision clients. This is largely attributable to the occurrence of device displacements, which require prompt access to corrective surgical MC procedures as part of their clinical management. Most device displacements were self-removals which are preventable if client behaviour could be modified through counselling interventions. We also found that infection after MC is more common among younger clients, who may benefit from additional counselling or increased parental involvement.