Publications

Reports

Peer-Reviewed Articles

Mortality and Cause of Death Report (2019)

This report presents the COMSA data for calendar year 2019, including population size, number of births and deaths, cause of death assigned by verbal autopsy, and social autopsy findings. Download COMSA 2019 Mortality Report (English)

Formative Research Report (2018)

This report presents findings from formative research conducted prior to the surveillance system’s implementation, in order to inform the design of the surveillance system. It is available only in Portuguese. Download formative report.

Regularized Bayesian transfer learning for population-level etiological distributions

Datta et al. Biostatistics (2020)

Summary excerpt: Computer-coded verbal autopsy (CCVA) algorithms predict cause of death from high- dimensional family questionnaire data (verbal autopsy) of a deceased individual, which are then aggregated to generate national and regional estimates of cause-specific mortality fractions. These estimates may be inaccurate if CCVA is trained on non-local training data different from the local population of interest. 

Link to full article.

Generalized Bayesian Quantification Learning

Fiksel et al. (Under review)

Abstract excerpt: Quantification learning is the task of prevalence estimation for a test population using predictions from a classifier trained on a differen population. Commonly used quantification methods either assume perfect sensitivity and specificity of the classifier, or use the training data to both train the classifier and also estimate its missclassification rates… We proposed a generalized Bayesian quantification learning (GBQL) approach that uses the entire compositional predictions from probabilistic classifiers and allows for uncertainty in true class labeled test data. Download preprint article.

Computer coded verbal autopsy (CCVA) algorithms are commonly used to generate burden of disease estimates using data from verbal autopsy surveys in low and middle income countries with poor vital registration data on causes of death.

Johns Hopkins Bloomberg School

of Public Health (JHSPH)

615 N. Wolfe Street, Baltimore, MD 21205

United States

Instituto Nacional de Saúde (INS)

Vila De Marracuene, Estrada Nacional N°1,

Parcela N°3943,

Província De Maputo – Moçambique


Instituto Nacional de Estatística (INE)

Av. 24 De Julho 1989 Caixa Postal 493,

Cidade De Maputo – Moçambique