rsf.default {randomSurvivalForest}R Documentation

Random Survival Forest Entry Point

Description

Random Survival Forests (RSF) (Ishwaran, Kogalur, Blackstone and Lauer, 2007) is an extension of Breiman's Random Forests (Breiman, 2001) to right-censored survival analysis settings. A forest of survival trees is grown in order to estimate an ensemble cumulative hazard function (CHF). Trees can be grown using several different survival tree splitting rules. An “out-of-bag” estimate of Harrell's concordance index (Harrell, 1982) is provided for assessing prediction accuracy of the CHF. Variable importance (VIMP) can be computed for single, as well as grouped variables, as a means to filter variables and to assess variable predictiveness. RSF can be used to predict on test data. Missing data (x-variables, survival times, censoring indicators) can be imputed on both training and test data. Note this is the default generic method for the package.

Usage

## Default S3 method:
rsf(formula,
    data = NULL,
    ntree = 1000,
    mtry = NULL,
    nodesize = NULL,
    splitrule = c("logrank", "conserve", "logrankscore", "logrankrandom", "random")[1],
    importance = c("randomsplit", "permute", "none")[1],
    big.data = FALSE,
    na.action = c("na.omit", "na.impute")[1],
    nimpute = 1,
    predictorWt = NULL,
    forest = FALSE,
    proximity = FALSE,
    varUsed = NULL,  
    seed = NULL,
    do.trace = FALSE,
    ...)

Arguments

formula A symbolic description of the model to be fit. Details for model specification are given below.
data Data frame containing the data used in the formula. Missing values allowed. See na.action for details.
ntree Number of trees to grow. This should not be set to a number too small, in order to ensure that every input row gets predicted at least a few times.
mtry Number of variables randomly sampled at each split. The default is sqrt(p), where p equals the number of variables.
nodesize Minimum number of deaths with unique survival times required for a terminal node. Default is roughly min(3,round(0.632*ndead)). Larger values cause smaller trees to be grown.
splitrule Splitting rule used to grow trees. See details below.
importance Method used to compute variable importance. See details below.
big.data Logical. Set this value to true when the number of variables p is very large, or the data is very large. See details below.
na.action Action to be taken if the data contain NA's. Possible values are na.omit and na.impute. Default is na.omit, which removes the entire record if even one of its entries is NA (applies only to entries specifically called in 'formula'). The action na.impute implements a sophisticated tree imputation technique. See details below.
nimpute Number of times missing data algorithm is to be iterated.
predictorWt Vector of non-negative weights where entry k represents the likehood of selecting variable k as a candidate for splitting. Default is to use uniform weights. Vector must be of dimension p, where p equals the number of variables.
forest Logical. Should the forest object be returned? Used for prediction on new data. Default is FALSE.
proximity Logical. Should proximity measure between observations be calculated? Creates an nxn matrix (which can be huge). Default is FALSE.
varUsed Analyzes which variables are used (split upon) in the topology of the forest. Default is NULL. Possible values are all.trees, by.tree. See details below.
seed Seed for random number generator. Must be a negative integer (the R wrapper handles incorrectly set seed values).
do.trace Logical. Should trace output be enabled? Default is FALSE. Integer values can also be passed. A positive value causes output to be printed each do.trace iteration.
... Further arguments passed to or from other methods.

Details

There are 5 different splitting rules available for growing trees. The default rule, logrank, splits nodes by maximization of the log-rank test statistic (Segal, 1988; Leblanc and Crowley, 1993). conserve splits nodes by finding daughters closest to the conservation of events principle (see Naftel, Blackstone and Turner, 1985). logrankscore uses a standardized log-rank statistic (Hothorn and Lausen, 2003). random implements pure random splitting: a variable is randomly selected from the mtry variables in a node and the node is split using a random split point (Lin and Jeon, 2006). logrankrandom is a variant of random. A random split point is chosen for each of the mtry variables, and the variable with maximum log-rank test is used to split the node at its random split point.

A detailed study carried out by Ishwaran et al. (2007) found logrank and logrankscore to be the most accurate in terms of prediction error, followed by conserve. Computationally, random is by far fastest, followed closely by logrankrandom. Surprisingly, random can have decent performance, while logrankrandom often has performance close to logrank. If users want speed and good accuracy, logrankrandom is the best compromise. Alternatively, to reduce computations for very large data sets, users can try discretizing continuous variables and/or the observed survival times. Discretization does not have to be overly granular for substantial gains to be seen.

A typical formula has the form Survrsf(time, censoring) ~ terms, where time is survival time and censoring is a binary censoring indicator. Note that censoring must be coded as 0=censored and 1=death (event) and time must be strictly positive.

Variables which are encoded as factors will be coerced into dummy variables. These dummy variables will be automatically labelled using the original variable name. For example, if marital status is a variable named “marital” encoded as a factor with levels “S”, “M” and “D”, two new dummy variables will be created labeled “maritalM” and “maritalS”.

Variable importance (VIMP) is computed similar to Breiman (2001), although there are two ways to perturb a variable to determine its VIMP (randomsplit, permute). The default method is randomsplit which works as follows. To calculate VIMP for a variable x, out-of-bag (OOB) cases are dropped down the bootstrap (in-bag) survival tree. A case is assigned a daughter node randomly whenever an x-split is encountered. An OOB ensemble cumulative hazard function (CHF) is computed from the forest of such trees and its OOB error rate calculated. The VIMP for x is the difference between this and the OOB error rate for the original forest (without random node assignment using x). If permute is used, then x is randomly permuted in OOB data and dropped down the in-bag tree (random assignment is not used).

Prediction error is measured by 1-C, where C is Harrell's concordance index. Prediction error is between 0 and 1, and measures how well the ensemble can correctly rank (classify) two individuals in terms of survival. A value of 0.5 is no better than random guessing. A value of 0 is perfect. Because VIMP is based on the concordance index, VIMP indicates how much misclassification increases, or decreases, for a new test case if a given variable were not available for that case (given that the forest was grown using that variable).

For very large data sets, or data with a large number of variables, users should consider setting the logical flag big.data to TRUE. This bypasses the large overhead needed by R in creating design matrices and parsing formula. Be aware, however, that variables are not processed and are interpreted as is when this option is turned on. Think of the data frame as containing time and censoring information and the rest of the data as the pre-processed design matrix when this option is on. Side effects are that all variables (including factors) are converted to numeric mode and transformations used in the formula (such as logs etc.) are ignored.

Setting na.action to na.impute implements a tree imputation method whereby missing data (x-variables or outcomes) are imputed dynamically as a tree is grown by randomly sampling from the distribution within the current node (Ishwaran et al. 2007). OOB data is not used in imputation to avoid biasing prediction error and VIMP estimates. Final imputation for integer valued variables and censoring indicators use a maximal class rule, whereas continuous variables and survival time use a mean rule. Records in which all outcome and x-variable information are missing are removed. Variables having all missing values are removed. The algorithm can be iterated by setting nimpute to a positive integer greater than 1. A few iterations should be used in heavy missing data settings to improve accuracy of imputed values (see Ishwaran et al., 2007). Note if the algorithm is iterated, a side effect is that missing values in returned objects predictors, time and cens are replaced by imputed values. Further, imputed objects such as imputedData are set to NULL.

If varUsed=all.trees, a vector of size p is returned. Each element contains a count of the number of times a split has occurred on this variable. If varUsed=by.tree, a matrix of size ntreexp is returned. Each element [i][j] contains a count of the number of times a split has occurred on variable [j] in tree [i].

Value

An object of class (rsf, grow), which is a list with the following components:

call The original call to rsf.
formula The formula used in the call.
n Sample size of the data (depends upon NA's, see na.action).
ndead Number of deaths.
ntree Number of trees grown.
mtry Number of variables randomly selected for splitting at each node.
nodesize Minimum size of terminal nodes.
splitrule Splitting rule used.
time Vector of length n of survival times.
cens Vector of length n of censoring information (0=censored, 1=death).
timeInterest Sorted unique event times. Ensemble values are given for these time points only.
predictorNames A character vector of the variable names used in growing the forest.
predictorWt Vector of non-negative weights used for randomly sampling variables for splitting.
predictors Matrix of x-variables used to grow the forest.
ensemble A matrix of the bootstrap ensemble CHF with each row corresponding to an individual's CHF evaluated at each of the time points in timeInterest.
oob.ensemble Same as ensemble, but based on the OOB CHF.
mortality A vector of length n, with each value containing the bootstrap ensemble mortality for an individual in the data. Ensemble mortality values should be interpreted in terms of total number of deaths.
oob.mortality Same as mortality, but based on oob.ensemble.
err.rate Vector of length ntree containing OOB error rates for the ensemble, with the b-th element being the error rate for the ensemble formed using the first b trees. Error rates are measured using 1-C, where C is Harrell's concordance index.
leaf.count Number of terminal nodes for each tree in the forest. Vector of length ntree. A value of zero indicates a rejected tree (sometimes occurs when imputing missing data). Values of one indicate tree stumps.
importance VIMP for each variable.
forest If forest=TRUE, the forest object is returned. This object can then be used for prediction with new test data sets.
proximity If proximity=TRUE, a matrix of dimension nxn recording the frequency pairs of data points occur within the same terminal node. Value returned is a vector of the lower diagonal of the matrix. Use plot.proximity() to extract this information.
varUsed Count of the number of times a variable is used in growing the forest. Can be a vector, matrix, or NULL.
imputedIndv Vector of indices for cases with missing values. Can be NULL.
imputedData Matrix of imputed data. First two columns are censoring and survival time, respectively. Remaining columns are the x-variables. Row i contains imputed outcomes and x-variables for row imputedIndv[i] of predictors. Can be NULL.

Note

The key deliverable is the matrix ensemble containing the bootstrap ensemble CHF function for each individual evaluated at a set of distinct time points (an OOB ensemble, oob.ensemble, is also returned). The vector mortality (likewise oob.mortality) is a weighted sum over the columns of ensemble, weighted by the number of individuals at risk at the different time points. Entry i of the vector represents the estimated total mortality of individual i in terms of total number of deaths. In other words, if i has a mortality value of 100, then if all individuals had the same x-values as i, there would be on average 100 deaths in the dataset.

Different R wrappers are provided with the package to aid in interpreting the ensemble.

Author(s)

Hemant Ishwaran hemant.ishwaran@gmail.com and Udaya B. Kogalur ubk2101@columbia.edu

References

L. Breiman (2001). Random forests, Machine Learning, 45:5-32.

F.E. Harrell et al. (1982). Evaluating the yield of medical tests, J. Amer. Med. Assoc., 247:2543-2546.

T. Hothorn and B. Lausen (2003). On the exact distribution of maximally selected rank statistics, Computational Statistics & Data Analysis, 43:121-137.

H. Ishwaran, U.B. Kogalur, E.H. Blackstone and M.S. Lauer (2007). Random survival forests, Cleveland Clinic Technical Report.

H. Ishwaran, U.B. Kogalur (2007). Random survival forests for R, Rnews, 7/2:25-31.

H. Ishwaran (2007). Variable importance in binary regression trees and forests, Electronic J. Statist., 1:519-537.

M. LeBlanc and J. Crowley (1993). Survival trees by goodness of split, J. Amer. Stat. Assoc., 88:457-467.

A. Liaw and M. Wiener (2002). Classification and regression by randomForest, R News, 2:18-22.

Y. Lin and Y. Jeon (2006). Random forests and adaptive nearest neighbors, J. Amer. Stat. Assoc., 101:578-590.

D.C. Naftel, E.H. Blackstone and M.E. Turner (1985). Conservation of events, unpublished notes.

M. R. Segal. (1988). Regression trees for censored data, Biometrics, 44:35-47.

See Also

plot.ensemble, plot.variable, plot.error, plot.proximity, predict.rsf, print.rsf, find.interaction, pmml_to_rsf, rsf_to_pmml, Survrsf.

Examples

# Example 1:  Veteran's Administration lung cancer trial from
# Kalbfleisch & Prentice.  Randomized trial of two treatment
# regimens for lung cancer.  Minimal argument call.  Print
# results, then plot error rate and importance values.

data(veteran, package = "randomSurvivalForest")
veteran.out <- rsf(Survrsf(time, status)~., data = veteran)
print(veteran.out)
plot(veteran.out)

# Example 2:  Richer argument call.
# Note that forest option is set to true to illustrate 
# how one might use 'rsf' for prediction (see 'rsf.predict'
# for more details).

data(veteran, package = "randomSurvivalForest")
veteran.f <- as.formula(Survrsf(time, status)~.)
ntree <- 200
mtry <- 2
nodesize <- 3
splitrule <- "logrankrandom"
varUsed <- "by.tree"
forest <- TRUE
proximity <- TRUE
seed <- -1
do.trace <- 25
veteran2.out <- rsf(veteran.f, veteran, ntree, mtry, nodesize, splitrule,
                    varUsed = varUsed, forest = forest, proximity = proximity,
                    seed = seed, do.trace = do.trace)
print(veteran2.out)
plot.proximity(veteran2.out)

# Take a peek at the forest ...
head(veteran2.out$forest$nativeArray)

# Average number of times a variable was split on.
apply(veteran2.out$varUsed,2,mean)

# Partial plot of top variable.
plot.variable(veteran2.out, partial = TRUE, n.pred=1)

## Not run: 
# Example 3:  Veteran data again. Look specifically at
# Karnofsky performance score.  Compare to Kaplan-Meier.
# Assumes "survival" library is loaded.

if (library("survival", logical.return = TRUE))
{
        data(veteran, package = "randomSurvivalForest")
        veteran3.out <- rsf(Survrsf(time, status)~karno,
                       veteran,
                       ntree = 1000)
        plot.ensemble(veteran3.out)
        par(mfrow = c(1,1))
        plot(survfit(Surv(time, status)~karno, data = veteran))
}

# Example 4:  Primary biliary cirrhosis (PBC) of the liver.
# Data found in Appendix D.1 of Fleming and Harrington, Counting
# Processes and Survival Analysis, Wiley, 1991 (only differences
# are that age is in days and sex and stage variables are not
# missing for observations 313-418).  

data(pbc, package = "randomSurvivalForest") 
pbc.out <- rsf(Survrsf(days,status)~., pbc, ntree = 1000)
print(pbc.out)

# Example 5:  Same as Example 4, but with imputation for missing values.

data(pbc, package = "randomSurvivalForest") 
pbc2.out <- rsf(Survrsf(days,status)~., pbc, ntree = 1000, na.action="na.impute")
# summary of analysis
print(pbc2.out)
# Combine original data + imputed data.
pbc.imputed.data <- cbind(status=pbc2.out$cens, days=pbc2.out$time, pbc2.out$predictors)
pbc.imputed.data[pbc2.out$imputedIndv,] <- pbc2.out$imputedData
tail(pbc)
tail(pbc.imputed.data)
# Iterate the missing data algorithm.
# Use random splitting to increase speed.
# Use trace to track algorithm in detail.
# Note that a side effect of iterating is that the original data
# are replaced by imputed values.
pbc3.out <- rsf(Survrsf(days,status)~., pbc, ntree = 1000,
         splitrule = "logrankrandom",  na.action="na.impute", nimpute=3, do.trace = 100)
pbc.iterate.imputed.data <- cbind(status=pbc3.out$cens,
         days=pbc3.out$time, pbc3.out$predictors)

# Example 6:  Compare Cox regression to RSF (PBC data).
# Compute OOB estimate of Harrell's concordance 
# index for Cox regression using B = 100 bootstrap draws.
# Assumes "Hmisc" and "survival" libraries are loaded. 

if (library("survival", logical.return = TRUE) 
    & library("Hmisc", logical.return = TRUE))
{
    data(pbc, package = "randomSurvivalForest")
    pbc3.out <- rsf(Survrsf(days,status)~., pbc, mtry = 2, ntree = 1000)
    B <- 100 
    cox.err <- rep(NA, B) 
    cox.f <- as.formula(Surv(days,status)~.)  
    pbc.data <- pbc[apply(is.na(pbc), 1, sum) == 0,] ##remove NA's 
    cat("Out-of-bag Cox Analysis ...", "\n")
    for (b in 1:B) {
        cat("Cox bootstrap", b, "\n") 
        bag.sample <- sample(1:dim(pbc.data)[1],
                             dim(pbc.data)[1],
                             replace = TRUE) 
        oob.sample <- setdiff(1:dim(pbc.data)[1], bag.sample)
        train <- pbc.data[bag.sample,]
        test <- pbc.data[oob.sample,]
        cox.out <- coxph(cox.f, train)
        cox.out <- tryCatch({coxph(cox.f, train)}, error=function(ex){NULL})
        if (is.list(cox.out)) {
          cox.predict <- predict(cox.out, test)
          cox.err[b] <- rcorr.cens(cox.predict, 
                 Surv(pbc.data$days[oob.sample], pbc.data$status[oob.sample]))[1]
        }
     }
     cat("Error rates:", "\n")
     cat("Random Survival Forests:", pbc3.out$err.rate[pbc3.out$ntree], "\n")
     cat("         Cox Regression:", mean(cox.err, na.rm = TRUE), "\n")
}

# Example 7:  Using an external data set.

file.in <- "other.data"
other.data <- read.table(file.in, header = TRUE)
rsf.f <- as.formula(Survrsf(time, status)~.)
rsf.out <- rsf(formula = rsf.f, data = other.data) 

## End(Not run)

[Package randomSurvivalForest version 3.2.3 Index]