plot.diag {DiagnosisMed} | R Documentation |
This function draw a simple nomogram from an object created by diagnosis or diagnosisI
## S3 method for class 'diag': plot(x, print = FALSE, ...)
x |
An object from diagnosis or diagnosisI |
print |
If TRUE, plot.diag will print in the output window the table with all pre-test and its corresponding post-test probabilities. Default is FALSE |
... |
Further generic options for plot function |
plot.diag will draw a very simple nomogram as many examples from wikipedia http://en.wikipedia.org/wiki/Nomogram. This is not a generic nomogram as shown in many evidenced based medicine texts, because this one shows only pre-test and post-test variations with a fixed positive likelihood ratio. This likelihood is a statistic from an object created by diagnosis or diagnosisI function. Its usage is the same as applying the Bayes theorem where the pre-test odds times positive likelihood ratio equals the pos-test odd (transforming the odds to probabilities). To use it, draw, with a rule, a vertical line from a desired pre-test probability, and to find the corresponding post-test probability, draw a horizontal line from the intersection of the curve and the vertical line toward the vertical axis.
Bug reports, malfunctioning, or suggestions for further improvements or contributions can be sent, preferentially, through the DiagnosisMed email list, or R-Forge website https://r-forge.r-project.org/projects/diagnosismed/.
Pedro Brasil - diagnosismed-list@lists.r-forge.r-project.org
JA Knotterus, The Evidence Based Clinical Diagnosis; BMJBooks, 2002
diagnosis
,nomogram,epi.nomogram,ROC
#This will draw a ROC curve mytest<-diagnosisI(364,22,17,211, print=TRUE, plot=TRUE) #This is different, and will draw a nomogram mytest<-diagnosisI(364,22,17,211) plot(mytest) #Draw a nomogram and print it's table - printing is optional mytest<-diagnosisI(364,22,17,211) plot(mytest,print=TRUE) # The same as plot(diagnosisI(364,22,17,211),print=TRUE)