createModelDesign: Specify settings for deceloping a single model

In OHDSI/PatientLevelPrediction: Developing patient level prediction using data in the OMOP Common Data Model

Specify settings for deceloping a single model

Description

Specify settings for deceloping a single model

Usage

createModelDesign(
  targetId,
  outcomeId,
  restrictPlpDataSettings = createRestrictPlpDataSettings(),
  populationSettings = createStudyPopulationSettings(),
  covariateSettings = FeatureExtraction::createDefaultCovariateSettings(),
  featureEngineeringSettings = NULL,
  sampleSettings = NULL,
  preprocessSettings = NULL,
  modelSettings = NULL,
  splitSettings = createDefaultSplitSetting(type = "stratified", testFraction = 0.25,
    trainFraction = 0.75, splitSeed = 123, nfold = 3),
  runCovariateSummary = T
)

Arguments

targetId	The id of the target cohort that will be used for data extraction (e.g., the ATLAS id)
outcomeId	The id of the outcome that will be used for data extraction (e.g., the ATLAS id)
restrictPlpDataSettings	The settings specifying the extra restriction settings when extracting the data created using createRestrictPlpDataSettings().
populationSettings	The population settings specified by createStudyPopulationSettings()
covariateSettings	The covariate settings, this can be a list or a single 'covariateSetting' object.
featureEngineeringSettings	Either NULL or an object of class featureEngineeringSettings specifying any feature engineering used during model development
sampleSettings	Either NULL or an object of class sampleSettings with the over/under sampling settings used for model development
preprocessSettings	Either NULL or an object of class preprocessSettings created using createPreprocessingSettings()
modelSettings	The model settings such as setLassoLogisticRegression()
splitSettings	The train/validation/test splitting used by all analyses created using createDefaultSplitSetting()
runCovariateSummary	Whether to run the covariateSummary

Details

This specifies a single analysis for developing as single model

Value

A list with analysis settings used to develop a single prediction model

OHDSI/PatientLevelPrediction documentation built on April 27, 2024, 8:11 p.m.