↓ Skip to main content

Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths

Overview of attention for article published in BMC Medicine, November 2015
Altmetric Badge

About this Attention Score

  • In the top 25% of all research outputs scored by Altmetric
  • Good Attention Score compared to outputs of the same age (76th percentile)
  • Average Attention Score compared to outputs of the same age and source

Mentioned by

twitter
8 tweeters

Citations

dimensions_citation
16 Dimensions

Readers on

mendeley
35 Mendeley
citeulike
1 CiteULike
Title
Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths
Published in
BMC Medicine, November 2015
DOI 10.1186/s12916-015-0521-2
Pubmed ID
Authors

Pierre Miasnikof, Vasily Giannakeas, Mireille Gomes, Lukasz Aleksandrowicz, Alexander Y. Shestopaloff, Dewan Alam, Stephen Tollman, Akram Samarikhalaj, Prabhat Jha

Abstract

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. 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. 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). 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.

Twitter Demographics

The data shown below were collected from the profiles of 8 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 35 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
United States 1 3%
Unknown 34 97%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 7 20%
Student > Master 7 20%
Student > Bachelor 5 14%
Researcher 4 11%
Student > Doctoral Student 3 9%
Other 5 14%
Unknown 4 11%
Readers by discipline Count As %
Medicine and Dentistry 9 26%
Computer Science 6 17%
Social Sciences 6 17%
Nursing and Health Professions 2 6%
Agricultural and Biological Sciences 2 6%
Other 3 9%
Unknown 7 20%

Attention Score in Context

This research output has an Altmetric Attention Score of 5. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 10 March 2016.
All research outputs
#1,425,192
of 7,377,175 outputs
Outputs from BMC Medicine
#1,032
of 1,514 outputs
Outputs of similar age
#65,277
of 285,441 outputs
Outputs of similar age from BMC Medicine
#37
of 54 outputs
Altmetric has tracked 7,377,175 research outputs across all sources so far. Compared to these this one has done well and is in the 80th percentile: it's in the top 25% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 1,514 research outputs from this source. They typically receive a lot more attention than average, with a mean Attention Score of 28.7. This one is in the 31st percentile – i.e., 31% of its peers scored the same or lower than it.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 285,441 tracked outputs that were published within six weeks on either side of this one in any source. This one has done well, scoring higher than 76% of its contemporaries.
We're also able to compare this research output to 54 others from the same source and published within six weeks on either side of this one. This one is in the 31st percentile – i.e., 31% of its contemporaries scored the same or lower than it.