Introduction
Richard Wen
rrwen.dev@gmail.com
The nbc4va package implements the Naive Bayes Classifier (NBC)
algorithm for verbal autopsy data based on code and methods provided by
Miasnikof
et al (2015).
This package is intended to be used for experimenting with the NBC
algorithm to predict causes of death using verbal autopsy data.
Acknowledgements
This package was developed at the Centre for Global Health Research
(CGHR) in Toronto, Ontario, Canada. The original NBC algorithm code was
developed by Pierre Miaskinof and Vasily Giannakeas. The original
performance metrics code was provided by Dr. Mireille Gomes whom also
offered guidance in metrics implementation and user testing. Special
thanks to Richard Zehang Li for providing a standard structure for the
package and Patrycja Kolpak for user testing of the GUI.
Quick Start
Run the nbc4va Graphical User Interface (GUI) and follow the
instructions in your browser:
library(nbc4va)
nbc4vaGUI()
Exit the GUI by closing the browser window and pressing
Esc
in a R console to stop the GUI process.
Background Knowledge
Before using the nbc4va package, ensure that the training and testing
data inputs are formatted correctly and that the terms used in this
package are understood:
- It is strongly suggested to review the Methods section for an understanding of terms and
metrics
- Please also review the input data specifications detailed in the Data section
Using the Package
The nbc4va package contains help sections with code samples and
references for usage:
- The Basic Usage section is suited for
users of all levels
- The Advanced Usage section is suited
for users of the package that have some R programming experience
- The Functions section provides an organized
list of package functions with brief descriptions
Getting Help
By using the help()
function (or ?
shortform) in an R console, you can access details about particular
functions and methods in the nbc4va
package:
library(nbc4va) # load the nbc4va package
# View this help page as a vignette
browseVignettes("nbc4va")
# Access details about certain functions
help("nbc4va") # access the nbc4va package docs
help("nbc4vaGUI") # access GUI details
help("nbc4vaIO") # access file in and out details
help("nbc") # access the nbc algorithm function
help("summary.nbc") # access the summary function
help("plot.nbc") # access the results plot function
# Access details about example data
help("nbc4vaData")
help("nbc4vaDataRaw")
# Alternative short forms
?nbc4va
?nbc4vaGUI
?nbc4vaIO
?nbc
?nbc4vaData
?nbc4vaDataRaw
?summary.nbc
?plot.nbc
Citing this Package
- 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. 10.1186/s12916-015-0521-2.
To view citation information for the nbc4va package, use the code
below in an R console:
library(nbc4va)
citation("nbc4va")
Basic Usage
This section provides details on the basic usage of the nbc4va
package which includes bringing up the Graphic User Interface and
running the Naive Bayes Classifier algorithm using file input and
output.
User Interface
The simplest way to use the package is to open the Graphical User
Interface (GUI) in your default web browser with
nbc4vaGUI()
.
Once the GUI is loaded, follow the instructions to fit a NBC model to
your training.csv
and to evaluate its performance with your
testing.csv
data.
Example of GUI
If nbc4vaGUI()
is called sucessfully, the GUI shown in
the image below should be available in your web browser.
![](data:image/png;base64,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)
Sample Code for GUI
Run the following code using nbc4vaGUI()
in a R console
to open the GUI in your web browser:
library(nbc4va) # load the package
nbc4vaGUI() # open the GUI in your web browser
Close the GUI by pressing escape while you are in the R console.
References for GUI
See the Methods section for definitions of
performance metrics and terms in the model results.
Advanced Usage
This section provides details on the advanced usage of the nbc4va
package which includes training a NBC model, evaluating NBC model
performance, and plotting the top predicted causes from the NBC
model.
The documentation written here is intended for users of R that
understand the different data structures of R such as:
It is also required to understand the basic data types:
Training a NBC Model
Run the following code using nbc()
in a R console to
train a NBC model:
library(nbc4va)
# Create training and testing dataframes
data(nbc4vaData) # example data
train <- nbc4vaData[1:50, ]
test <- nbc4vaData[51:100, ]
# Train a nbc model
# The "results" variable is a nbc list-like object with elements accessible by $
# Set "known" to indicate whether or not testing causes are known in "test"
results <- nbc(train, test, known=TRUE)
# Obtain the probabilities and predictions
prob <- results$prob.causes # vector of probabilities for each test case
pred <- results$pred.causes # vector of top predictions for each test case
# View the "prob" and "pred", the names are the case ids
head(prob)
head(pred)
References for Training a NBC Model
See the Methods section for the NBC algorithm
details.
For complete function specifications and usage of nbc()
,
use the code below in an R console:
Evaluating a NBC Model
Run the following code using summary.nbc()
in a R
console to evaluate a NBC model:
library(nbc4va)
# Create training and testing dataframes
data(nbc4vaData)
train <- nbc4vaData[1:50, ]
test <- nbc4vaData[51:100, ]
# Train a nbc model
results <- nbc(train, test, known=TRUE)
# Automatically calculate metrics with summary
# The "brief" variable is a nbc_summary list-like object
# The "brief" variable is "results", but with additional metrics
brief <- summary(results)
# Obtain the calculated metrics
metrics <- brief$metrics.all # vector of overall metrics
causeMetrics <- brief$metrics.causes # dataframe of metrics by cause
# Access the calculatd metrics
metrics[["CSMFaccuracy"]]
metrics[["Sensitivity"]]
View(causeMetrics)
References for Evaluating a NBC Model
See the Methods section for definitions of
performance metrics and terms in the output.
For complete method specifications and usage of
summary.nbc()
, use the code below in a R console:
library(nbc4va)
?summary.nbc
Plotting the Top Predicted Causes
Run the following code using plot.nbc()
in a R console
to produce a bar plot of the top predicted causes:
library(nbc4va)
# Create training and testing data
data(nbc4vaData)
train <- nbc4vaData[1:50, ]
test <- nbc4vaData[51:100, ]
# Train a nbc model and plot the top 5 causes if possible
results <- nbc(train, test, known=TRUE)
plot(results, top=5)
plot(results, top=5, footnote=FALSE) # remove footnote
Example of Plotting the Top Predicted Causes
The image below shows a plot of the top causes of death by predicted
CSMFs using plot.nbc()
on a NBC model trained using the
example data nbc4vaData
included in the package.
![](data:image/png;base64,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)
References for Plotting the Top Predicted Causes
See the Methods section for definition of CSMF
and related metrics in the footnote of the plot.
For complete method specifications and usage of
plot.nbc()
, use the code below in a R console:
library(nbc4va)
?plot.nbc
Data
This documentation page provides details on the training and testing
data formats to be used as inputs in the nbc4va package.
Training and Testing Data
The training data (consisting of cases, causes of death for each
case, and symptoms) is used as input for the Naive Bayes Classifier
(NBC) algorithm to learn the probabilities for each cause of death to
produce a NBC model.
This model can be evaluated for its performance by predicting on the
testing data cases, where the predicted causes of death are compared to
the causes of death in the testing data.
The process of learning the probabilities to produce the NBC model is
known as training, and the process of evaluating the predictive
performance of the trained model is known as testing.
Key points:
- The training data is used to build the NBC model
- The testing data is used to evaluate the NBC model’s predictive
performance
- Ideally, the testing data should not have the same cases in the
training data
- Both the training and testing data must have the same symptoms
Examples of Data
The image below shows an example of the training data.
![](data:image/png;base64,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)
The image below shows an example of the corresponding testing
data.
![](data:image/png;base64,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)
The image below shows an example of the corresponding testing data
without any causes.
![](data:image/png;base64,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)
Symptom Imputation Example
Given a symptom column containing the values of each case (1, 0, 0,
1, 99, 99):
- 1 represents presence of the symptom
- 0 represents absence of the symptom
- 99 is treated as unknown as to whether the symptom is present or
absent
The imputation is applied as follows:
- The unknown values (99, 99) are randomly imputed according to the
known values (1, 0, 0, 1).
- The known values contain half (2/4) the values as 1s and half (2/4)
the values as 0s.
- Thus, the imputation results in half (1/2) the unknown values as 1s
and half (1/2) of the unknown values as 0s to match the known values
distribution.
- The possible combinations for replacing the unknown values (99, 99)
are then (1, 0) and (0, 1).
The symptom imputation method preserves the approximate distribution
of the known values in an attempt to avoid dropping entire cases or
symptoms.
Sample Code for Data
Run the following code using nbc4vaData()
in the R
console to view the example data included in the nbc4va package:
library(nbc4va) # load the nbc4va package
data(nbc4vaData) # load the example data
View(nbc4vaData) # view the sample data in the nbc4va package
data(nbc4vaDataRaw) # load the example data with unknown symptom values
View(nbc4vaDataRaw) # view the sample data with unknown symptom values
Methods
This section provides details on the implementation of the Naive
Bayes Classifier algorithm, definition of uncommon terms, and
calculation of performance metrics.
Naive Bayes Classifier
The Naive Bayes Classifier (NBC) is a machine learning algorithm that
uses training data containing cases of deaths to learn probabilities for
known causes of death based on given symptoms. This produces a model
that can use the learned probabilities to predict the cause of death for
cases in unseen testing data with same symptoms.
The nbc4va package implements the NBC algorithm for verbal autopsy
data using code and methods built on Miasnikof
et al (2015).
Terms for Data
Symptom: Refers to the features or independent
variables with binary values of 1 for presence and 0 for absence of a
death related condition.
Cause: Refers to the target or dependent variable
containing discrete values of the causes of death.
Case: Refers to an individual death containing an
identifier, a cause of death (if known), and several symptoms.
Training Data: Refers to a dataset of cases that the
NBC algorithm learns probabilities from.
Testing Data: Refers to a dataset of cases used to
evaluate the performance of a NBC model; these cases must have the same
symptoms as the Training Data
, but with different
cases.
Terms for Metrics
True Positives: The number of cases, given a cause,
where the predicted cause is equal to the actual observed cause (Fawcett,
2005).
True Negatives: The number of cases, given a cause,
where the predicted is not the cause and the actual observed is also not
the cause (Fawcett,
2005).
False Positives: The number of cases, given a cause,
where the predicted is the cause and the actual observed is not the
cause (Fawcett,
2005).
False Negatives: The number of cases, given a cause,
where the predicted is not the cause and the actual observed is the
cause (Fawcett,
2005).
CSMF: The fraction of deaths (predicted or observed)
for a particular cause.
Calculation of Metrics at the Individual Level
The following metrics measure the performance of a model by comparing
its predicted causes individually to the matching true/observed
causes.
Sensitivity: proportion of correctly identified
positives (Powers,
2011).
\[
Sensitivity = \frac{TP}{TP+FN}
\]
where:
- \(TP\) is the number of true
positives
- \(FN\) is the number of false
negatives
- This metric measures a model’s ability to correctly predict causes
of death
PCCC: partial chance corrected concordance (Murray
et al 2011).
\[
PCCC(k) = \frac{C-\frac{k}{N}}{1-\frac{k}{N}}
\]
where:
- \(C\) is the fraction of deaths
where the true cause is in the top \(k\) causes assigned to that death
- \(k\) is the number of top causes
(constant of 1 in this package)
- \(N\) is the number of causes in
the study
- This metric measures how much better a model is than random
assignment
Calculation of Metrics at the Population Level
The following metrics measure the performance of a model by comparing
its distribution of cause predictions to a distribution of true/observed
causes for similar cases.
CSMFmaxError: cause specific mortality fraction
maximum error (Murray
et al 2011).
\[
CSMF Maximum Error = 2(1-Min(CSMF_{j}^{true})
\]
where:
- \(j\) is a true/observed cause
- \(CSMFtruej\) is the true/observed
CSMF for cause \(j\)
CSMFaccuracy: cause specific mortality fraction
accuracy (Murray
et al 2011).
\[
CSMFAccuracy = 1-\frac{\sum_{j=1}^{k} |CSMF_{j}^{true} -
CSMF_{j}^{pred}|}{CSMF Maximum Error}
\]
where:
- \(j\) is a cause
- \(CSMFtruej\) is the true/observed
CSMF for cause \(j\)
- \(CSMFpredj\) is the predicted CSMF
for cause \(j\)
- Values range from 0 to 1 with 1 meaning no error in the predicted
CSMFs, and 0 being complete error in the predicted CSMFs
References for Methods
- Fawcett T. An introduction to ROC analysis. Pattern Recognition
Letters[Internet]. 2005 Dec 19[cited 2016 Apr 29];27(8):861-874.
Available from: https://people.inf.elte.hu/kiss/13dwhdm/roc.pdf
- 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. 10.1186/s12916-015-0521-2.
- Murray CJL, Lozano R, Flaxman AD, Vahdatpour A, Lopez AD. Robust
metrics for assessing the performance of different verbal autopsy cause
assignment methods in validation studies.Popul Health Metr. 2011;9:28.
10.1186/1478-7954-9-28.
- Powers DMW. EVALUATION: FROM PRECISION, RECALL AND F-MEASURE TO ROC,
INFORMEDNESS, MARKEDNESS & CORRELATION. Journal of Machine Learning
Technologies. 2011;2(1)37-63.