Bayesian factor models for probabilistic cause of death assessment with verbal autopsies

TL;DR

This paper introduces a Bayesian factor model for analyzing verbal autopsy data to estimate cause-specific death distributions, improving understanding of mortality causes in regions lacking vital registration.

Contribution

It develops a novel Bayesian multivariate probit model with latent factors to better estimate causes of death from verbal autopsy data, incorporating associations among questionnaire items.

Findings

Model accurately estimates cause-specific death distributions.

Identifies key questionnaire items linked to causes of death.

Framework simplifies future verbal autopsy data collection.

Abstract

The distribution of deaths by cause provides crucial information for public health planning, response, and evaluation. About 60% of deaths globally are not registered or given a cause, limiting our ability to understand disease epidemiology. Verbal autopsy (VA) surveys are increasingly used in such settings to collect information on the signs, symptoms, and medical history of people who have recently died. This article develops a novel Bayesian method for estimation of population distributions of deaths by cause using verbal autopsy data. The proposed approach is based on a multivariate probit model where associations among items in questionnaires are flexibly induced by latent factors. Using the Population Health Metrics Research Consortium labeled data that include both VA and medically certified causes of death, we assess performance of the proposed method. Further, we estimate important questionnaire items that are highly associated with causes of death. This framework provides insights that will simplify future data collection.