Miasnikof, P, Giannakeas, V, Gomes, M, Aleksandrowicz, L, Shestopaloff, AY, Alam, D, Tollman, S, Samarikhalaj, A and Jha, P. 2015. Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths. [Online]. Figshare. Available from: https://doi.org/10.6084/m9.figshare.c.3629489_D1.v1
Miasnikof, P, Giannakeas, V, Gomes, M, Aleksandrowicz, L, Shestopaloff, AY, Alam, D, Tollman, S, Samarikhalaj, A and Jha, P. Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths [Internet]. Figshare; 2015. Available from: https://doi.org/10.6084/m9.figshare.c.3629489_D1.v1
Miasnikof, P, Giannakeas, V, Gomes, M, Aleksandrowicz, L, Shestopaloff, AY, Alam, D, Tollman, S, Samarikhalaj, A and Jha, P (2015). Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths. [Data Collection]. Figshare. https://doi.org/10.6084/m9.figshare.c.3629489_D1.v1
Description
BACKGROUND: Verbal 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. METHODS: We 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. RESULTS: The 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). CONCLUSIONS: NBC 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.
Data capture method | Compilation/Synthesis |
---|---|
Date (Date published in a 3rd party system) | 25 November 2015 |
Language(s) of written materials | English |
Data Creators | Miasnikof, P, Giannakeas, V, Gomes, M, Aleksandrowicz, L, Shestopaloff, AY, Alam, D, Tollman, S, Samarikhalaj, A and Jha, P |
---|---|
LSHTM Faculty/Department | Faculty of Epidemiology and Population Health > Dept of Population Health (2012- ) |
Participating Institutions | St. Michael’s Hospital, University of Toronto, University of the Witwatersrand, Ryerson University, London School of Hygiene & Tropical Medicine |
Date Deposited | 10 Mar 2016 16:11 |
---|---|
Last Modified | 09 Feb 2022 18:32 |
Publisher | Figshare |
Downloads
Data / Code
Filename: File1-WHO_DeathCauseCategories.doc
Description: Mapping of WHO cause of death categories
Content type: Dataset
File size: 51kB
Mime-Type: application/msword
Filename: File4-MDS_Cause_of_death.doc
Description: Sensitivity and specificity of assignment by cause of death in Indian Million Death Study
Content type: Dataset
File size: 70kB
Mime-Type: application/msword
Filename: File6-Matlab_Cause_of_death.doc
Description: Sensitivity and specificity of assignment by cause of death, on Matlab data
Content type: Dataset
File size: 70kB
Mime-Type: application/msword
Documentation
Filename: File3-InterVA-4_TariffMethods.doc
Description: Description of InterVA-4 and Open-source Tariff Method
Content type: Textual content
File size: 26kB
Mime-Type: application/msword
Filename: File5-Agincourt_Cause_of_death.doc
Description: Sensitivity and specificity of assignment by cause of death, on Agincourt data
Content type: Dataset
File size: 72kB
Mime-Type: application/msword
Study Instrument
Filename: File2-Rcode.zip
Description: R code used to produce the results in this study
Content type: Software
File size: 103kB
Mime-Type: application/x-zip