PatientLevelPrediction (version 6.4.0)

fitPlp: fitPlp

Description

Train various models using a default parameter grid search or user specified parameters

Usage

fitPlp(trainData, modelSettings, search = "grid", analysisId, analysisPath)

Value

An object of class plpModel containing:

model

The trained prediction model

preprocessing

The preprocessing required when applying the model

prediction

The cohort data.frame with the predicted risk column added

modelDesign

A list specifiying the modelDesign settings used to fit the model

trainDetails

The model meta data

covariateImportance

The covariate importance for the model

Arguments

trainData

An object of type trainData created using splitData data extracted from the CDM.

modelSettings

An object of class modelSettings created using one of the createModelSettings functions

search

The search strategy for the hyper-parameter selection (currently not used)

analysisId

The id of the analysis

analysisPath

The path of the analysis

Details

The user can define the machine learning model to train

Examples

  # takes too long 
# simulate data
data("simulationProfile")
plpData <- simulatePlpData(simulationProfile, n=1000)
# create study population, split into train/test and preprocess with default settings
population <- createStudyPopulation(plpData, outcomeId = 3)
data <- splitData(plpData, population, createDefaultSplitSetting())
data$Train$covariateData <- preprocessData(data$Train$covariateData)
saveLoc <- file.path(tempdir(), "fitPlp")
# fit a lasso logistic regression model using the training data
plpModel <- fitPlp(data$Train, modelSettings=setLassoLogisticRegression(seed=42),
                   analysisId=1, analysisPath=saveLoc)
# show evaluationSummary for model
evaluatePlp(plpModel$prediction)$evaluationSummary
# clean up
unlink(saveLoc, recursive = TRUE)