nomogramEx {nomogramEx} | R Documentation |
Extract Equations from a Nomogram
Description
A nomogram can not be easily applied, because it is difficult to calculate the points or even the survival probability. The package, including a function of nomogramEx(), is to extract the polynomial equations to calculate the points of each variable, and the survival probability corresponding to the total points.
Usage
nomogramEx(nomo,np,digit)
Arguments
nomo |
a object of nomogram() |
np |
the number of predicitons in your nomogram, for example: if you predicted 3- and 6- month, np=2, default is 2 |
digit |
the number of decimal digits, default is 9 |
Value
list |
the result is a list including polynomial equations to calculate the points of each variable, and the polynomial equations to calculate the probability of points |
Note
The polynomial equations extracted by this package are equal and less than cubic function.
Update:
Version 1.0: 1.the order of variables in the polynomial equations is opposite. 2.the number of the demical digits can not be controled.
Version 2.0: 1.the argument 'lp' from the 'nomogram' function can not be recognized.
Author(s)
Zhicheng Du<dgdzc@hotmail.com>, Yuantao Hao<haoyt@mail.sysu.edu.cn>
See Also
nothing
Examples
if(require("rms")){
n <-1000
age <- rnorm(n,50,10)
sex <- factor(sample(c('female','male'),n,TRUE))
sex <- as.numeric(sex)
ddist <- datadist(age,sex)
options(datadist='ddist')
cens <- 15*runif(n)
time <- -log(runif(n))/0.02*exp(.04*(age-50)+.8*(sex=='Female'))
death <- ifelse(time <= cens,1,0)
time <- pmin(time,cens)
units(time)="month"
f <- cph(formula(Surv(time,death)~sex+age),x=TRUE,y=TRUE,surv=TRUE,time.inc=3)
surv <- Survival(f)
nomo <- nomogram(f, fun=list(function(x) surv(3,x),function(x) surv(6,x)),
lp=TRUE,funlabel=c("3-Month Survival Prob","6-Month Survival Prob"))
nomogramEx(nomo=nomo,np=2,digit=9)
}