getPredictionDiagnostics {OhdsiReportGenerator}R Documentation

Extract the model design diagnostics for a specific development database

Description

This function extracts the PROBAST diagnostics

Usage

getPredictionDiagnostics(
  connectionHandler,
  schema,
  plpTablePrefix = "plp_",
  cgTablePrefix = "cg_",
  databaseTable = "database_meta_data",
  databaseTablePrefix = "",
  modelDesignId = NULL,
  threshold1_2 = 0.9
)

Arguments

connectionHandler

A connection handler that connects to the database and extracts sql queries. Create a connection handler via 'ResultModelManager::ConnectionHandler$new()'.

schema

The result database schema (e.g., 'main' for sqlite)

plpTablePrefix

The prefix used for the patient level prediction results tables

cgTablePrefix

The prefix used for the cohort generator results tables

databaseTable

The name of the table with the database details (default 'database_meta_data')

databaseTablePrefix

The prefix for the database table either ” or 'plp_'

modelDesignId

The identifier for a model design to restrict results to

threshold1_2

A threshold for probast 1.2

Details

Specify the connectionHandler, the resultDatabaseSettings and (optionally) a modelDesignId and threshold1_2 a threshold value to use for the PROBAST 1.2

Value

Returns a data.frame with the columns:

See Also

Other Prediction: getPredictionCohorts(), getPredictionDiagnosticTable(), getPredictionHyperParamSearch(), getPredictionIntercept(), getPredictionModelDesigns(), getPredictionPerformanceTable(), getPredictionPerformances(), getPredictionTopPredictors()

Examples

conDet <- getExampleConnectionDetails()

connectionHandler <- ResultModelManager::ConnectionHandler$new(conDet)

diag <- getPredictionDiagnostics(
  connectionHandler = connectionHandler, 
  schema = 'main'
)


[Package OhdsiReportGenerator version 1.1.1 Index]