Hierarchical Latent Class Models for Mortality Surveillance Using Partially Verified Verbal Autopsies

Monitoring data on causes of death is an important part of understanding the burden of diseases and the effects of public health interventions. Verbal autopsy (VA) is a well-established method for gathering information about deaths outside of hospitals by conducting an interview to family members or caregivers of a deceased person, and is usually the only tool for cause-of-death surveillance in low-resource settings. A critical limitation with the current practice of VA analysis is that all algorithms require either highly informative domain knowledge about symptom-cause relationships or large labeled datasets for model training. Therefore, they cannot be quickly adopted during public health emergencies when new diseases emerge with rapidly evolving epidemiological patterns. In this paper, we consider the task of estimating the fraction of deaths due to an emerging disease using continuously collected VAs where causes of death are only partially verified. We develop a novel Bayesian framework using a hierarchical latent class model to account for the informative verification process. Our model flexibly captures the joint distribution of symptoms and how they change over time in different sub-populations. We also propose structured priors to further improve the precision of prevalence estimation for small sub-populations. Our model is motivated by mortality surveillance of COVID-19 related deaths in low-resource settings. We apply our method to a dataset that includes suspected COVID-19 related deaths in Brazil in 2021. We show that standard modeling approaches can be severely biased under selective verification and our model leads to more robust and accurate quantification of disease prevalence.