highmlr: Machine learning feature selection for high dimensional...

In highMLR: Machine Learning Feature Selection for High Dimensional Survival Data

Machine learning feature selection for high dimensional survival data

Description

Fits one of several survival ML methods and returns a unified 'highmlr_fit' object summarising the selected features, their importance/coefficients, and (optionally) out-of-sample performance.

Usage

highmlr(
  data,
  time,
  status,
  features = NULL,
  method = c("coxnet", "rsf", "aorsf", "xgboost", "stability", "univariate", "pseudo",
    "finegray"),
  engine = NULL,
  recipe = NULL,
  resampling = c("cv", "bootstrap", "holdout", "none"),
  folds = 5L,
  tune = FALSE,
  top_n = 50L,
  parallel = FALSE,
  seed = NULL,
  ...
)

Arguments

data	A data frame containing 'time', 'status', and the candidate features (or a superset). Rows with missing time/status are dropped.
time	Character scalar: name of the survival time column.
status	Character scalar: name of the event indicator column. For right-censored methods: 1 = event, 0 = censored. For Fine-Gray (method = "finegray"): 0 = censored, 1 = event of interest, 2+ = competing event(s).
features	Character vector of candidate feature column names. If 'NULL' (default), all columns except 'time' and 'status' are used.
method	One of '"coxnet"', '"rsf"', '"aorsf"', '"xgboost"', '"stability"', '"univariate"', '"pseudo"', '"finegray"'.
engine	Optional engine override.
recipe	Optional preprocessing recipe object (currently accepted for forward compatibility; not yet applied).
resampling	One of '"cv"', '"bootstrap"', '"holdout"', '"none"'.
folds	Integer, number of CV folds (default 5).
tune	Logical. Internal tuning (currently coxnet only).
top_n	Integer. For ranking-based methods, keep this many top features (default 50).
parallel	Logical. Use future-based parallelism for the embarrassingly parallel parts.
seed	Optional integer for reproducibility.
...	Additional arguments passed to the method-specific fitter.

Value

An object of class 'highmlr_fit'. See [new_highmlr_fit()].

Examples

if (requireNamespace("glmnet", quietly = TRUE)) {
  data(hnscc)
  fit <- highmlr(hnscc, time = "OS", status = "Death",
                 method = "coxnet", resampling = "cv", folds = 5)
  print(fit)
}

highMLR documentation built on May 23, 2026, 5:07 p.m.