Progress toward the United Nations 2030 Sustainable Development Goals requires improved information on mortality and causes of death. However, causes of many of the fifty million annual deaths in low- and middle-income countries remain unknown, as most of the deaths occur at home without medical attention. In 2001 India began the Million Death Study in 1.3 million nationally representative households. Nonmedical staff conduct verbal autopsies, which are structured interviews including a half-page narrative in local language of the family's story of the symptoms and events leading to death. Two physicians independently assess each death to arrive at an underlying cause of death. The study has thus far yielded information that substantially altered previous estimates of cause-specific mortality and risk factors in India. Similar robust studies are feasible at low cost in other low- and middle-income countries, particularly if they adopt electronic data management and ensure high quality of fieldwork and physician coding. Nationwide mortality studies enable the quantification of avoidable premature mortality and key risk factors for disease, and provide a practicable method to monitor progress toward the Sustainable Development Goals.

BackgroundVerbal autopsies (VA) are increasingly used in low- and middle-income countries where most causes of death (COD) occur at home without medical attention, and home deaths differ substantially from hospital deaths. Hence, there is no plausible “standard” against which VAs for home deaths may be validated. Previous studies have shown contradictory performance of automated methods compared to physician-based classification of CODs. We sought to compare the performance of the classic naive Bayes classifier (NBC) versus existing automated classifiers, using physician-based classification as the reference.MethodsWe compared the performance of NBC, an open-source Tariff Method (OTM), and InterVA-4 on three datasets covering about 21,000 child and adult deaths: the ongoing Million Death Study in India, and health and demographic surveillance sites in Agincourt, South Africa and Matlab, Bangladesh. We applied several training and testing splits of the data to quantify the sensitivity and specificity compared to physician coding for individual CODs and to test the cause-specific mortality fractions at the population level.ResultsThe NBC achieved comparable sensitivity (median 0.51, range 0.48-0.58) to OTM (median 0.50, range 0.41-0.51), with InterVA-4 having lower sensitivity (median 0.43, range 0.36-0.47) in all three datasets, across all CODs. Consistency of CODs was comparable for NBC and InterVA-4 but lower for OTM. NBC and OTM achieved better performance when using a local rather than a non-local training dataset. At the population level, NBC scored the highest cause-specific mortality fraction accuracy across the datasets (median 0.88, range 0.87-0.93), followed by InterVA-4 (median 0.66, range 0.62-0.73) and OTM (median 0.57, range 0.42-0.58).ConclusionsNBC outperforms current similar COD classifiers at the population level. Nevertheless, no current automated classifier adequately replicates physician classification for individual CODs. There is a need for further research on automated classifiers using local training and test data in diverse settings prior to recommending any replacement of physician-based classification of verbal autopsies.Electronic supplementary materialThe online version of this article (doi:10.1186/s12916-015-0521-2) contains supplementary material, which is available to authorized users.