Latent Class Analysis: Insights about design and analysis of schistosomiasis diagnostic studies

Various global health initiatives are currently advocating the elimination of schistosomiasis within next decade. Schistosomiasis is a highly debilitating tropical infectious disease with severe burden morbidity and thus operational research accurately evaluating diagnostics that quantify epidemic status for guiding effective strategies essential. Latent class models (LCMs) have been generally considered in epidemiology particular recent diagnostic studies as flexible tool because assessing true infection (via gold standard) not possible. However, biostatistics literature, classical LCM already criticised real-life problems under violation conditional independence (CI) assumption when applied to small number (i.e. most often 3-5 tests). Solutions relaxing CI accounting zero-inflation, well collecting partial standard information, proposed, offering potential more robust model estimates. In current article, we examined such approaches context via analysis two real datasets extensive simulation studies. Our main conclusions highlighted poor fit low prevalence settings necessity information order improve accuracy reduce bias sensitivity specificity