The Naive Bayes Classifier (NBC) uses training data containing death cases to learn probabilities for known causes of death based on given symptoms. The NBC can then use the learned probabilities to predict the cause of death for cases in a set of testing data given the same symptoms.

This shiny application acts as a graphical user interface (GUI) for the nbc4va R package, which implements the naive bayes classifier for verbal autopsy data as described by Miasnikof et al (2015).

Author

• Richard Wen <wenr@smh.ca>

References

• Miasnikof P, Giannakeas V, Gomes M, Aleksandrowicz L, Shestopaloff AY, Alam D, Tollman S, Samarikhalaj, Jha P. Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths. BMC Medicine. 2015;13:286. doi:10.1186/s12916-015-0521-2.