Abstract
Verbal autopsy (VA) deals with post-mortem surveys about deaths, mostly in low and middle income countries, where the majority of deaths occur at home rather than a hospital, for retrospective assignment of causes of death (COD) and subsequently evidence-based health system strengthening. Automated algorithms for VA COD assignment have been developed and their performance has been assessed against physician and clinical diagnoses. Since the performance of automated classification methods remains low, we aimed to enhance the Naïve Bayes Classifier (NBC) algorithm to produce better ranked COD classifications on 26,766 deaths from four globally diverse VA datasets compared to some of the leading VA classification methods, namely Tariff, InterVA-4, InSilicoVA and NBC. We used a different strategy, by training multiple NBC algorithms using the one-against-all approach (OAA-NBC). To compare performance, we computed the cumulative cause-specific mortality fraction (CSMF) accuracies for population-level agreement from rank one to five COD classifications. To assess individual-level COD assignments, cumulative partially-chance corrected concordance (PCCC) and sensitivity was measured for up to five ranked classifications. Overall results show that OAA-NBC consistently assigns CODs that are the most alike physician and clinical COD assignments compared to some of the leading algorithms based on the cumulative CSMF accuracy, PCCC and sensitivity scores. The results demonstrate that our approach improves the performance of classification (sensitivity) by between 6% and 8% compared with other VA algorithms. Population-level agreements for OAA-NBC and NBC were found to be similar or higher than the other algorithms used in the experiments. Although OAA-NBC still requires improvement for individual-level COD assignment, the one-against-all approach improved its ability to assign CODs that more closely resemble physician or clinical COD classifications compared to some of the other leading VA classifiers.
Highlights
Verbal autopsy (VA) is increasingly being used in developing countries where most deaths occur at home rather than in hospitals, and causes of death (COD) information remains unknown[1]
Datasets In order to test the performance of the algorithms, we used four main datasets, containing information on a total of 26,766 deaths: three physician COD diagnosed VA datasets, namely the Indian Million Death Study (MDS)[22], South African Agincourt Demographic Surveillance Sites (HDSS) dataset[23], and Bangladeshi Matlab Health and Demographic Surveillance Sites (HDSS) dataset[24], and one health facility diagnosed COD dataset, namely the Population Health Metrics Research Consortium (PHMRC) VA data collected from six sites in four countries (India, Mexico, the Philippines and Tanzania)[25,26]
These results show that one-against-all approach with NBC (OAANBC) consistently yields closer agreement with the physician review or clinical diagnoses at the individual-level than the other algorithms on most of the VA datasets
Summary
Verbal autopsy (VA) is increasingly being used in developing countries where most deaths occur at home rather than in hospitals, and causes of death (COD) information remains unknown[1]. This gap in information prevents evidence-based healthcare programming and policy reform needed to reduce the global burden of diseases[2]. The justification for the development of this method could be fleshed out a little more, perhaps explaining (for those unfamiliar with how VA data feed into policy) why it is important for these methods to be more accurate To this end, the authors may want to consider citing the 2014 systematic review by Leitao et al comparing PCVA with CCVA in LMIC and mentioning - even briefly - the large project underway to incorporate VA into CRVS systems (https://crvsgateway.info/A-stepwise-process~503 ). We would suggest using ‘assignment’ consistently throughout, to differentiate from ‘diagnoses’ made by clinicians during life
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
