Abstract: Understanding cause-specific mortality rates is crucial for monitoring population health and designing public health interventions. Worldwide, two-thirds of deaths do not have a cause assigned. Verbal autopsy (VA) is a well-established tool to collect information describing deaths outside of hospitals by conducting surveys to caregivers of a deceased person. It is routinely implemented in many low- and middle-income countries. Statistical algorithms to assign cause of death using VAs are typically vulnerable to the distribution shift between the data used to train the model and the target population. This presents a major challenge for analyzing VAs as labeled data are usually unavailable in the target population. This talk discusses a latent class model framework for VA data that jointly models VAs collected over heterogeneous domains, such as multiple study sites, different time periods, or distinct subpopulation. We introduce a parsimonious representation of the joint distribution of the collected symptoms and develop a computationally efficient algorithm for posterior inference and out-of-domain cause-of-death assignment. We demonstrate the performance of the model under various data shift scenarios.
Bio: Zehang "Richard" Li is an Assistant Professor of Statistics at University of California, Santa Cruz since July 2020. His research involves the development of statistical methods that address scientific questions in demography, epidemiology, and global health. He is particularly interested in latent variable models, space-time models, survey sampling, and applications in health data science.