inst/doc/introduction.R

In CondiS: Censored Data Imputation for Direct Modeling

## ---- include = FALSE---------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

## ----setup--------------------------------------------------------------------
# install.packages("CondiS", dependencies = c("survival", "caret"))

library(CondiS)

## ----message=FALSE, warning=FALSE, fig.height=5, fig.width=7------------------
library(kernlab)
library(purrr)
library(tidyverse)
library(survival)

data(cancer, package="survival")

status <- pmax(rotterdam$recur, rotterdam$death)
rfstime <- with(rotterdam, ifelse(recur==1, rtime, dtime))
rotterdam <- rotterdam[2:11]
rotterdam$status = status
rotterdam$rfstime = rfstime
fit <- survfit(Surv(rfstime, status) ~ 1, data = rotterdam)


# Obtain the imputed survival time
pred_time = CondiS(rfstime, status)
rotterdam$pred_time = pred_time
rotterdam$status2 = rep(1,length(status))
fit_2 <- survfit(Surv(pred_time, status2) ~ 1, data = rotterdam)

# Visualization
library(survminer)

combined <-
  list(Censored = fit,
       CondiS = fit_2)

ggsurvplot(
  combined,
  data = rotterdam,
  combine = TRUE,
  censor = TRUE,
  risk.table = TRUE,
  palette = "jco"
)


## -----------------------------------------------------------------------------
covariates = rotterdam[,1:10]

# Update the imputed survival time
pred_time_2 = CondiS_X(pred_time, status, covariates)

rotterdam$pred_time_2 = pred_time_2

## -----------------------------------------------------------------------------
# Pre-process the data
library(caret)

preproc <- preProcess(rotterdam[,1:10], method = c('center', 'scale'))
trainPreProc <- predict(preproc, rotterdam[,1:10])
  
train_control <- trainControl(method = "repeatedcv")

# Train-test split
set.seed(42)
smp_size <- floor(0.75 * nrow(rotterdam))
train_ind <- sample(seq_len(nrow(rotterdam)), size = smp_size)

train <- rotterdam[train_ind, ]
test <- rotterdam[-train_ind, ]


fit_svm = train(
      pred_time ~ .-status-status2-rfstime-pred_time,
      data = train,
      method = "svmRadial",
      trControl = train_control,
      na.action = na.omit
    )

pred_svm = predict(fit_svm, test)

# Mean absolute error (MAE)

calc_MAE <- function(actual,predicted)
{
  error <- actual - predicted
  mean(abs(error))
}

## In the testing set:

# The MAE of CondiS-imputed survival time and SVM-predicted survival time is:

calc_MAE(test$pred_time,pred_svm)

# The MAE of the CondiS-X-imputed survival time and the SVM-predicted survival time is:

calc_MAE(test$pred_time_2,pred_svm)