FRESA.CAD (version 2.0.2)

plotModels.ROC: Plot test ROC curves of each cross-validation model

Description

This function plots test ROC curves of each model found in the cross validation process. It will also aggregate the models into a single prediction performance, plotting the resulting ROC curve (models coherence). Furthermore, it will plot the mean sensitivity for a given set of specificities.

Usage

plotModels.ROC(modelPredictions,
	        number.of.models=0,
	        specificities=c(0.95,0.90,0.80,0.70,0.60,0.50,0.40,0.30,0.20,0.10,0.05),
	        theCVfolds=1,
            ...)

Arguments

modelPredictions

A data frame returned by the crossValidationFeatureSelection function, either the Models.testPrediction, the FullModel.testPrediction, the Models.CVtestPredictions, the TestRetrained.blindPredictio

number.of.models

The maximum number of models to plot

specificities

Vector containing the specificities at which the ROC sensitivities will be calculated

theCVfolds

the number of folds performed in a Cross-validation experiment

...

Additional parameters for the roc function (pROC package)

Value

• ROC.AUCs
  A vector with the AUC of each ROC
• mean.sensitivities
  A vector with the mean sensitivity at the specificities given by specificities
• model.sensitivities
  A matrix where each row represents the sensitivitiy at the specificities given by specificities for a different ROC
• specificities
  The specificities used to calculate the sensitivities
• senAUC
  The AUC of the ROC curve that resulted from using mean.sensitivities

Examples

# Start the graphics device driver to save all plots in a pdf format
	pdf(file = "Example.pdf")
	# Get the stage C prostate cancer data from the rpart package
	library(rpart)
	data(stagec)
	# Split the stages into several columns
	dataCancer <- cbind(stagec[,c(1:3,5:6)],
	                    gleason4 = 1*(stagec[,7] == 4),
	                    gleason5 = 1*(stagec[,7] == 5),
	                    gleason6 = 1*(stagec[,7] == 6),
	                    gleason7 = 1*(stagec[,7] == 7),
	                    gleason8 = 1*(stagec[,7] == 8),
	                    gleason910 = 1*(stagec[,7] >= 9),
	                    eet = 1*(stagec[,4] == 2),
	                    diploid = 1*(stagec[,8] == "diploid"),
	                    tetraploid = 1*(stagec[,8] == "tetraploid"),
	                    notAneuploid = 1-1*(stagec[,8] == "aneuploid"))
	# Remove the incomplete cases
	dataCancer <- dataCancer[complete.cases(dataCancer),]
	# Load a pre-stablished data frame with the names and descriptions of all variables
	data(cancerVarNames)
	# Rank the variables:
	# - Analyzing the raw data
	# - According to the zIDI
	rankedDataCancer <- univariateRankVariables(variableList = cancerVarNames,
	                                            formula = "Surv(pgtime, pgstat) ~ 1",
	                                            Outcome = "pgstat",
	                                            data = dataCancer,
	                                            categorizationType = "Raw",
	                                            type = "COX",
	                                            rankingTest = "zIDI",
	                                            description = "Description")
	# Get a Cox proportional hazards model using:
	# - The top 7 ranked variables
	# - 10 bootstrap loops in the feature selection procedure
	# - The zIDI as the feature inclusion criterion
	# - 5 bootstrap loops in the backward elimination procedure
	# - A 5-fold cross-validation in the feature selection, 
	#            update, and backward elimination procedures
	# - A 10-fold cross-validation in the model validation procedure
	# - First order interactions in the update procedure
	cancerModel <- crossValidationFeatureSelection(size = 7,
	                                               loops = 10,
	                                               Outcome = "pgstat",
	                                               timeOutcome = "pgtime",
	                                               variableList = rankedDataCancer,
	                                               data = dataCancer,
	                                               type = "COX",
	                                               selectionType = "zIDI",
	                                               elimination.bootstrap.steps = 5,
	                                               trainRepetition = 5,
	                                               CVfolds = 10,
	                                               interaction = c(1,2))
	# Plot the results of the blind test set predictions made at each 
	# fold of the cross-validation
	cancerModelPlot <- plotModels.ROC(cancerModel$Models.testPrediction)
	# Shut down the graphics device driver
	dev.off()