getAutoKM {Coxmos}

getAutoKM

Description

Generates a Kaplan-Meier plot for the specified Coxmos model. The plot can be constructed based on the model's Linear Predictor value, the PLS-COX component, or the original variable level.

Usage

getAutoKM(
  type = "LP",
  model,
  comp = 1:2,
  top = 10,
  ori_data = TRUE,
  BREAKTIME = NULL,
  n.breaks = 20,
  only_sig = FALSE,
  alpha = 0.05,
  title = NULL,
  verbose = FALSE
)

Arguments

type

Character. Kaplan Meier for complete model linear predictor ("LP"), for PLS components ("COMP") or for original variables ("VAR") (default: LP).

model

Coxmos model.

comp

Numeric vector. Vector of length two. Select which components to plot (default: c(1,2)).

top

Numeric. Show "top" first variables. If top = NULL, all variables are shown (default: 10).

ori_data

Logical. Compute the Kaplan-Meier plot with the raw-data or the normalize-data to compute the best cut-point for splitting the data into two groups. Only used when type = "VAR" (default: TRUE).

BREAKTIME

Numeric. Size of time to split the data into "total_time / BREAKTIME + 1" points. If BREAKTIME = NULL, "n.breaks" is used (default: NULL).

n.breaks

Numeric. If BREAKTIME is NULL, "n.breaks" is the number of time-break points to compute (default: 20).

only_sig

Logical. If "only_sig" = TRUE, then only significant log-rank test variables are returned (default: FALSE).

alpha

Numeric. Numerical values are regarded as significant if they fall below the threshold (default: 0.05).

title

Character. Kaplan-Meier plot title (default: NULL).

verbose

Logical. If verbose = TRUE, extra messages could be displayed (default: FALSE).

Details

The getAutoKM function offers a flexible approach to visualize survival analysis results using the Kaplan-Meier method. Depending on the type parameter, the function can generate plots based on different aspects of the Coxmos model:

• "LP": Uses the Linear Predictor value of the model.

• "COMP": Utilizes the PLS-COX component.

• "VAR": Operates at the original variable level.

The function provides options to customize the number of components (comp), the number of top variables (top), and whether to use raw or normalized data (ori_data). Additionally, users can specify the time intervals (BREAKTIME and n.breaks) for the Kaplan-Meier plot. If significance testing is desired, the function can filter out non-significant variables based on the log-rank test (only_sig and alpha parameters).

It's essential to ensure that the provided model is of the correct class (Coxmos). The function will return an error message if an incompatible model is supplied.

Value

A list of two elements per each model in the list: info_logrank_num: A list of two data.frames with the numerical variables categorize as qualitative and the cutpoint to divide the data into two groups. LST_PLOTS: A list with the Kaplan-Meier Plots.

Author(s)

Pedro Salguero Garcia. Maintainer: [e-mail]

References

Kaplan EL, Kaplan EL, Meier P (1958). “Nonparametric Estimation from Incomplete Observations.” Journal of the American Statistical Association. doi:10.1007/978-1-4612-4380-9_25, https://link.springer.com/chapter/10.1007/978-1-4612-4380-9_25.

Examples

data("X_proteomic")
data("Y_proteomic")
set.seed(123)
index_train <- caret::createDataPartition(Y_proteomic$event, p = .5, list = FALSE, times = 1)
X_train <- X_proteomic[index_train,1:50]
Y_train <- Y_proteomic[index_train,]
X_test <- X_proteomic[-index_train,1:50]
Y_test <- Y_proteomic[-index_train,]
splsicox.model <- splsicox(X_train, Y_train, n.comp = 2, penalty = 0.5, x.center = TRUE,
x.scale = TRUE)
getAutoKM(type = "LP", model = splsicox.model)