VA-Calibration: Correcting for Algorithmic Misclassification in Estimating Cause Distributions

TL;DR

This paper introduces the 'vacalibration' R package, which uses a Bayesian framework to correct misclassification in verbal autopsy cause-of-death estimates, improving global health data accuracy.

Contribution

It presents a novel Bayesian calibration method and an R package that corrects for misclassification in cause-of-death estimates from verbal autopsy data, incorporating uncertainty quantification.

Findings

Improved accuracy of cause-specific mortality fractions after calibration.

Demonstrated effectiveness in real-world applications in Mozambique and other countries.

Supports multiple algorithms and ensemble calibration for flexible use.

Abstract

Accurate estimation of cause-specific mortality fractions (CSMFs), the percentage of deaths attributable to each cause in a population, is essential for global health monitoring. Challenge arises because computer-coded verbal autopsy (CCVA) algorithms, commonly used to estimate CSMFs, frequently misclassify the cause of death (COD). This misclassification is further complicated by structured patterns and substantial variation across countries. To address this, we introduce the R package 'vacalibration'. It implements a modular Bayesian framework to correct for the misclassification, thereby yielding more accurate CSMF estimates from verbal autopsy (VA) questionnaire data. The package utilizes uncertainty-quantified CCVA misclassification matrix estimates derived from data collected in the CHAMPS project and available on the 'CCVA-Misclassification-Matrices' GitHub repository. Currently, these matrices cover three CCVA algorithms (EAVA, InSilicoVA, and InterVA) and two age groups (neonates aged 0-27 days, and children aged 1-59 months) across countries (specific estimates for Bangladesh, Ethiopia, Kenya, Mali, Mozambique, Sierra Leone, and South Africa, and a combined estimate for all other countries), enabling global calibration. The 'vacalibration' package also supports ensemble calibration when multiple algorithms are available. Implemented using the 'RStan', the package offers rapid computation, uncertainty quantification, and seamless compatibility with openVA, a leading COD analysis software ecosystem. We demonstrate the package's flexibility with two real-world applications in COMSA-Mozambique and CA CODE. The package and its foundational methodology applies more broadly and can calibrate any discrete classifier or their ensemble.