A0601
Title: Domain adaptive cause-of-death assignment using verbal autopsies under distribution shift
Authors: Zehang Li - University of California, Santa Cruz (United States) [presenting]
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 the 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. The purpose is to discuss 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 subpopulations. A parsimonious representation of the joint distribution of the collected symptoms is introduced, and a computationally efficient algorithm is developed to generate posterior inference and out-of-domain cause-of-death assignment. The importance of accounting for data shift is also discussed in other related decision-making problems in VA studies.
