tunePLANN: Tune a Survival Neural Network Based on the PLANN Method

In survivalSL: Super Learner for Survival Prediction from Censored Data

Tune a Survival Neural Network Based on the PLANN Method

Description

This function finds the optimal inter, size, decay, maxit, and MaxNWts parameters for the survival neural network by using cross-validation and the concordance index.

Usage

tunePLANN(times, failures, group=NULL, cov.quanti=NULL, cov.quali=NULL,
data, cv=10, inter, size, decay, maxit, MaxNWts, seed=NULL)

Arguments

times	The name of the variable related the numeric vector with the follow-up times.
failures	The name of the variable related the numeric vector with the event indicators (0=right censored, 1=event).
group	The name of the variable related to the exposure/treatment. This variable shall have only two modalities encoded 0 for the untreated/unexposed patients and 1 for the treated/exposed ones. The default value is NULL: no specific exposure/treatment is considered. When a specific exposure/treatment is considered, it will be forced in the algorithm or related interactions will be tested when possible.
cov.quanti	The name(s) of the variable(s) related to the possible quantitative covariates. These variables must be numeric.
cov.quali	The name(s) of the variable(s) related to the possible qualitative covariates. These variables must be numeric with two levels: 0 and 1. A complete disjunctive form must be used for covariates with more levels.
data	A data frame for training the model in which to look for the variables related to the status of the follow-up time (times), the event (failures), the optional treatment/exposure (group) and the covariables included in the previous model (cov.quanti and cov.quali).
cv	The value of the number of folds. The default value is 10.
inter	The length of the intervals.
size	The number of units in the hidden layer.
decay	The parameter for weight decay.
maxit	The maximum number of iterations.
MaxNWts	The maximum allowable number of weights.
seed	A numeric value for random seed for reproducibility. The default is NULL.

Details

This function is based is based on the survivalPLANN package.

Value

optimal	The value of inter, size, decay, maxit, and MaxNWts that gives the maximum mean cross-validated C-index.
results	The data frame with the mean cross-validated C-index according to inter, size, decay, maxit, and MaxNWts.

References

Biganzoli E, Boracchi P, Mariani L, and et al. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med, 17:1169-86, 1998.

Examples

data(dataDIVAT2)

# The hyper-parameter grid needs to be more precise and the maximum number
# of iterations > 1000. We have reduced the arguments to respect examples requiring
# less than 5 seconds for packages on the CRAN.

tune.model <- tunePLANN(times="times", failures="failures", data=dataDIVAT2[1:300,],
  cov.quanti=c("age"),  cov.quali=c("hla", "retransplant", "ecd"), cv=3,
  inter=1, size=c(16, 32), decay=0.01, maxit=50, MaxNWts=10000, seed=42)

tune.model$optimal # the optimal hyperparameters

tune.model$results # the C-index for the tested grid

survivalSL documentation built on April 4, 2025, 3:55 a.m.