runMultiplePlp: Run a list of predictions analyses

In OHDSI/PatientLevelPrediction: Develop Clinical Prediction Models Using the Common Data Model

Run a list of predictions analyses

Description

Run a list of predictions analyses

Usage

runMultiplePlp(
  databaseDetails = createDatabaseDetails(),
  modelDesignList = list(createModelDesign(targetId = 1, outcomeId = 2, modelSettings =
    setLassoLogisticRegression()), createModelDesign(targetId = 1, outcomeId = 3,
    modelSettings = setLassoLogisticRegression())),
  onlyFetchData = FALSE,
  cohortDefinitions = NULL,
  logSettings = createLogSettings(verbosity = "DEBUG", timeStamp = TRUE, logName =
    "runPlp Log"),
  saveDirectory = NULL,
  sqliteLocation = file.path(saveDirectory, "sqlite")
)

Arguments

databaseDetails	The database settings created using createDatabaseDetails()
modelDesignList	A list of model designs created using createModelDesign()
onlyFetchData	Only fetches and saves the data object to the output folder without running the analysis.
cohortDefinitions	A list of cohort definitions for the target and outcome cohorts
logSettings	The setting specifying the logging for the analyses created using createLogSettings()
saveDirectory	Name of the folder where all the outputs will written to.
sqliteLocation	(optional) The location of the sqlite database with the results

Details

This function will run all specified predictions as defined using .

Value

A data frame with the following columns:

⁠analysisId⁠	The unique identifier for a set of analysis choices.
⁠targetId⁠	The ID of the target cohort populations.
⁠outcomeId⁠	The ID of the outcomeId.
⁠dataLocation⁠	The location where the plpData was saved
⁠the settings ids⁠	The ids for all other settings used for model development.

Examples

 
connectionDetails <- Eunomia::getEunomiaConnectionDetails()
databaseDetails <- createDatabaseDetails(connectionDetails = connectionDetails,
                                         cdmDatabaseSchema = "main",
                                         cohortDatabaseSchema = "main",
                                         cohortTable = "cohort",
                                         outcomeDatabaseSchema = "main",
                                         outcomeTable = "cohort",
                                         targetId = 1,
                                         outcomeIds = 2)
Eunomia::createCohorts(connectionDetails = connectionDetails)
covariateSettings <- 
 FeatureExtraction::createCovariateSettings(useDemographicsGender = TRUE,
                                            useDemographicsAge = TRUE,
                                            useConditionOccurrenceLongTerm = TRUE)
# GI Bleed in users of celecoxib
modelDesign <- createModelDesign(targetId = 1, 
                                 outcomeId = 3, 
                                 modelSettings = setLassoLogisticRegression(seed = 42),
                                 populationSettings = createStudyPopulationSettings(),
                                 restrictPlpDataSettings = createRestrictPlpDataSettings(),
                                 covariateSettings = covariateSettings,
                                 splitSettings = createDefaultSplitSetting(splitSeed = 42),
                                 preprocessSettings = createPreprocessSettings())
# GI Bleed in users of NSAIDs
modelDesign2 <- createModelDesign(targetId = 4,
                                  outcomeId = 3,
                                  modelSettings = setLassoLogisticRegression(seed = 42),
                                  populationSettings = createStudyPopulationSettings(),
                                  restrictPlpDataSettings = createRestrictPlpDataSettings(),
                                  covariateSettings = covariateSettings,
                                  splitSettings = createDefaultSplitSetting(splitSeed = 42),
                                  preprocessSettings = createPreprocessSettings())
saveLoc <- file.path(tempdir(), "runMultiplePlp")
multipleResults <- runMultiplePlp(databaseDetails = databaseDetails,
                                  modelDesignList = list(modelDesign, modelDesign2),
                                  saveDirectory = saveLoc)
# You should see results for two developed models in the ouutput. The output is as well
# uploaded to a sqlite database in the saveLoc/sqlite folder, 
dir(saveLoc)
# The dir output should show two Analysis_ folders with the results, 
# two targetId_ folders with th extracted data, and a sqlite folder with the database
# The results can be explored in the shiny app by calling viewMultiplePlp(saveLoc)

# clean up (viewing the results in the shiny app is won't work after this)
unlink(saveLoc, recursive = TRUE)

OHDSI/PatientLevelPrediction documentation built on Feb. 14, 2025, 9:44 a.m.