The importance of failure

Abstract

Trachoma programs use annual antibiotic mass drug administration (MDA) in evaluation units (EUs) that generally encompass 100,000-250,000 people. After one, three, or five MDA rounds, programs undertake impact surveys. Where impact survey prevalence of trachomatous inflammation-follicular (TF) in 1- to 9-year-olds is ≥ 5%, ≥ 1 additional MDA rounds are recommended before resurvey. Impact survey costs, and the proportion of impact surveys returning TF prevalence ≥ 5% (the failure rate or, less pejoratively, the MDA continuation rate), therefore influence the cost of eliminating trachoma. We modeled, for illustrative EU sizes, the financial cost of undertaking MDA with and without conducting impact surveys. As an example, we retrospectively assessed how conducting impact surveys affected costs in the United Republic of Tanzania for 2017-2018. For EUs containing 100,000 people, the median (interquartile range) cost of continuing MDA without doing impact surveys is USD 28,957 (17,581-36,197) per EU per year, whereas continuing MDA solely where indicated by impact survey results costs USD 17,564 (12,158-21,694). If the mean EU population is 100,000, then continuing MDA without impact surveys becomes advantageous in financial cost terms only when the continuation rate exceeds 71%. For the United Republic of Tanzania in 2017-2018, doing impact surveys saved enough money to provide MDA for > 1,000,000 people. Although trachoma impact surveys have a nontrivial cost, they generally save money, providing EUs have > 50,000 inhabitants, the continuation rate is not excessive, and they generate reliable data. If all EUs pass their impact surveys, then we have waited too long to do them.