Package 'FeatureExtraction'

Title: Generating Features for a Cohort
Description: An R interface for generating features for a cohort using data in the Common Data Model. Features can be constructed using default or custom made feature definitions. Furthermore it's possible to aggregate features and get the summary statistics.
Authors: Martijn Schuemie [aut], Marc Suchard [aut], Patrick Ryan [aut], Jenna Reps [aut], Anthony Sena [aut], Ger Inberg [aut, cre], Observational Health Data Science and Informatics [cph]
Maintainer: Ger Inberg <[email protected]>
License: Apache License 2.0
Version: 3.7.2
Built: 2024-11-17 05:57:02 UTC
Source: https://github.com/ohdsi/featureextraction

Help Index

Get covariate settings

Description

Get covariate settings

Usage

.createLooCovariateSettings(useLengthOfObs = TRUE)

Arguments

useLengthOfObs

if length of observations should be used

Value

Returns an object of type covariateSettings, containing settings for the covariates.

Get covariate information from the database

Description

Get covariate information from the database

Usage

.getDbLooCovariateData(
  connection,
  tempEmulationSchema = NULL,
  cdmDatabaseSchema,
  cohortTable = "#cohort_person",
  cohortIds = c(-1),
  cdmVersion = "5",
  rowIdField = "subject_id",
  covariateSettings,
  aggregated = FALSE,
  minCharacterizationMean = 0
)

Arguments

connection

A connection to the server containing the schema as created using the connect function in the DatabaseConnector package. Either the connection or connectionDetails argument should be specified.
tempEmulationSchema

Some database platforms like Oracle and Impala do not truly support temp tables. To emulate temp tables, provide a schema with write privileges where temp tables can be created.
cdmDatabaseSchema

The name of the database schema that contains the OMOP CDM instance. Requires read permissions to this database. On SQL Server, this should specify both the database and the schema, so for example 'cdm_instance.dbo'.
cohortTable

Name of the (temp) table holding the cohort for which we want to construct covariates
cohortIds

For which cohort ID(s) should covariates be constructed? If set to -1, covariates will be constructed for all cohorts in the specified cohort table.
cdmVersion

Define the OMOP CDM version used: currently supported is "5".
rowIdField

The name of the field in the cohort table that is to be used as the row_id field in the output table. This can be especially usefull if there is more than one period per person.
covariateSettings

Either an object of type covariateSettings as created using one of the createCovariate functions, or a list of such objects.
aggregated

Should aggregate statistics be computed instead of covariates per cohort entry?
minCharacterizationMean

The minimum mean value for binary characterization output. Values below this will be cut off from output. This will help reduce the file size of the characterization output, but will remove information on covariates that have very low values. The default is 0.

Value

Returns an object of type covariateData, containing information on the covariates.

Aggregate covariate data

Description

Aggregate covariate data

Usage

aggregateCovariates(covariateData)

Arguments

covariateData

An object of type covariateData as generated using getDbCovariateData.

Value

An object of class covariateData.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)
aggregatedCovariateData <- aggregateCovariates(covariateData)

Compute standardized difference of mean for all covariates.

Description

Computes the standardized difference for all covariates between two cohorts. The standardized difference is defined as the difference between the mean divided by the overall standard deviation.

Usage

computeStandardizedDifference(
  covariateData1,
  covariateData2,
  cohortId1 = NULL,
  cohortId2 = NULL
)

Arguments

covariateData1

The covariate data of the first cohort. Needs to be in aggregated format.
covariateData2

The covariate data of the second cohort. Needs to be in aggregated format.
cohortId1

If provided, covariateData1 will be restricted to this cohort. If not provided, covariateData1 is assumed to contain data on only 1 cohort.
cohortId2

If provided, covariateData2 will be restricted to this cohort. If not provided, covariateData2 is assumed to contain data on only 1 cohort.

Value

A data frame with means and standard deviations per cohort as well as the standardized difference of mean.

Examples

binaryCovDataFile <- system.file("testdata/binaryCovariateData.zip",
  package = "FeatureExtraction"
)
covariateData1 <- loadCovariateData(binaryCovDataFile)
covariateData2 <- loadCovariateData(binaryCovDataFile)
covDataDiff <- computeStandardizedDifference(
  covariateData1,
  covariateData2,
  cohortId1 = 1,
  cohortId2 = 2
)

Convert prespecified covariate settings into detailed covariate settings

Description

Convert prespecified covariate settings into detailed covariate settings

Usage

convertPrespecSettingsToDetailedSettings(covariateSettings)

Arguments

covariateSettings

An object of type covariateSettings as created for example by the createCovariateSettings function.

Details

For advanced users only.

Value

An object of type covariateSettings, to be used in other functions.

Examples

covSettings <- createDefaultCovariateSettings()
detailedSettings <- convertPrespecSettingsToDetailedSettings(covariateSettings = covSettings)

Covariate Data

Description

CovariateData is an S4 class that inherits from Andromeda. It contains information on covariates, which can be either captured on a per-person basis, or aggregated across the cohort(s).

By default covariates refer to a specific time period, with for example different covariate IDs for whether a diagnosis code was observed in the year before and month before index date. However, a CovariateData can also be temporal, meaning that next to a covariate ID there is also a time ID, which identifies the (user specified) time window the covariate was captured.

A CovariateData object is typically created using getDbCovariateData, can only be saved using saveCovariateData, and loaded using loadCovariateData.

Usage

## S4 method for signature 'CovariateData'
show(object)

## S4 method for signature 'CovariateData'
summary(object)

Arguments

object

An object of class 'CovariateData'.

See Also

isCovariateData, isAggregatedCovariateData, isTemporalCovariateData

Create detailed covariate settings

Description

Create detailed covariate settings

Usage

createAnalysisDetails(
  analysisId,
  sqlFileName,
  parameters,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

analysisId

An integer between 0 and 999 that uniquely identifies this analysis.
sqlFileName

The name of the parameterized SQL file embedded in the featureExtraction package.
parameters

The list of parameter values used to render the template SQL.
includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Details

creates an object specifying in detail how covariates should be constructed from data in the CDM model. Warning: this function is for advanced users only.

Value

An object of type analysisDetail, to be used in createDetailedCovariateSettings or createDetailedTemporalCovariateSettings.

Examples

analysisDetails <- createAnalysisDetails(
  analysisId = 1,
  sqlFileName = "DemographicsGender.sql",
  parameters = list(
    analysisId = 1,
    analysisName = "Gender",
    domainId = "Demographics"
  ),
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Create cohort attribute covariate settings

Description

Create cohort attribute covariate settings

Usage

createCohortAttrCovariateSettings(
  analysisId = -1,
  attrDatabaseSchema,
  attrDefinitionTable = "attribute_definition",
  cohortAttrTable = "cohort_attribute",
  includeAttrIds = c(),
  isBinary = FALSE,
  missingMeansZero = FALSE
)

Arguments

analysisId

A unique identifier for this analysis.
attrDatabaseSchema

The database schema where the attribute definition and cohort attribute table can be found.
attrDefinitionTable

The name of the attribute definition table.
cohortAttrTable

The name of the cohort attribute table.
includeAttrIds

(optional) A list of attribute definition IDs to restrict to.
isBinary

Needed for aggregation: Are these binary variables? Binary variables should only have the values 0 or 1.
missingMeansZero

Needed for aggregation: For continuous values, should missing values be interpreted as 0?

Details

Creates an object specifying where the cohort attributes can be found to construct covariates. The attributes should be defined in a table with the same structure as the attribute_definition table in the Common Data Model. It should at least have these columns:

attribute_definition_id

A unique identifier of type integer.

attribute_name

A short description of the attribute.

The cohort attributes themselves should be stored in a table with the same format as the cohort_attribute table in the Common Data Model. It should at least have these columns:

cohort_definition_id

A key to link to the cohort table.

subject_id

A key to link to the cohort table.

cohort_start_date

A key to link to the cohort table.

attribute_definition_id

An foreign key linking to the attribute definition table.

value_as_number

A real number.

Value

An object of type covariateSettings, to be used in other functions.

Examples

covariateSettings <- createCohortAttrCovariateSettings(
  analysisId = 1,
  attrDatabaseSchema = "main",
  attrDefinitionTable = "attribute_definition",
  cohortAttrTable = "cohort_attribute",
  includeAttrIds = c(1),
  isBinary = FALSE,
  missingMeansZero = FALSE
)

Create settings for covariates based on other cohorts

Description

Create settings for covariates based on other cohorts

Usage

createCohortBasedCovariateSettings(
  analysisId,
  covariateCohortDatabaseSchema = NULL,
  covariateCohortTable = NULL,
  covariateCohorts,
  valueType = "binary",
  startDay = -365,
  endDay = 0,
  includedCovariateIds = c(),
  warnOnAnalysisIdOverlap = TRUE
)

Arguments

analysisId

A unique identifier for this analysis.
covariateCohortDatabaseSchema

The database schema where the cohorts used to define the covariates can be found. If set to NULL, the database schema will be guessed, for example using the same one as for the main cohorts.
covariateCohortTable

The table where the cohorts used to define the covariates can be found. If set to NULL, the table will be guessed, for example using the same one as for the main cohorts.
covariateCohorts

A data frame with at least two columns: 'cohortId' and 'cohortName'. The cohort ID should correspond to the cohort_definition_id of the cohort to use for creating a covariate.
valueType

Either 'binary' or 'count'. When valueType = 'count', the covariate value will be the number of times the cohort was observed in the window.
startDay

What is the start day (relative to the index date) of the covariate window?
endDay

What is the end day (relative to the index date) of the covariate window?
includedCovariateIds

A list of covariate IDs that should be restricted to.
warnOnAnalysisIdOverlap

Warn if the provided 'analysisId' overlaps with any predefined analysis as available in the 'createCovariateSettings()' function.

Details

Creates an object specifying covariates to be constructed based on the presence of other cohorts.

Value

An object of type covariateSettings, to be used in other functions.

Create settings for temporal covariates based on other cohorts

Description

Create settings for temporal covariates based on other cohorts

Usage

createCohortBasedTemporalCovariateSettings(
  analysisId,
  covariateCohortDatabaseSchema = NULL,
  covariateCohortTable = NULL,
  covariateCohorts,
  valueType = "binary",
  temporalStartDays = -365:-1,
  temporalEndDays = -365:-1,
  includedCovariateIds = c(),
  warnOnAnalysisIdOverlap = TRUE
)

Arguments

analysisId

A unique identifier for this analysis.
covariateCohortDatabaseSchema

The database schema where the cohorts used to define the covariates can be found. If set to NULL, the database schema will be guessed, for example using the same one as for the main cohorts.
covariateCohortTable

The table where the cohorts used to define the covariates can be found. If set to NULL, the table will be guessed, for example using the same one as for the main cohorts.
covariateCohorts

A data frame with at least two columns: 'cohortId' and 'cohortName'. The cohort ID should correspond to the cohort_definition_id of the cohort to use for creating a covariate.
valueType

Either 'binary' or 'count'. When valueType = 'count', the covariate value will be the number of times the cohort was observed in the window.
temporalStartDays

A list of integers representing the start of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The start day is included in the time period.
temporalEndDays

A list of integers representing the end of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The end day is included in the time period.
includedCovariateIds

A list of covariate IDs that should be restricted to.
warnOnAnalysisIdOverlap

Warn if the provided 'analysisId' overlaps with any predefined analysis as available in the 'createTemporalCovariateSettings()' function.

Details

Creates an object specifying temporal covariates to be constructed based on the presence of other cohorts.

Value

An object of type covariateSettings, to be used in other functions.

Create covariate settings

Description

Create covariate settings

Usage

createCovariateSettings(
  useDemographicsGender = FALSE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = FALSE,
  useDemographicsRace = FALSE,
  useDemographicsEthnicity = FALSE,
  useDemographicsIndexYear = FALSE,
  useDemographicsIndexMonth = FALSE,
  useDemographicsPriorObservationTime = FALSE,
  useDemographicsPostObservationTime = FALSE,
  useDemographicsTimeInCohort = FALSE,
  useDemographicsIndexYearMonth = FALSE,
  useCareSiteId = FALSE,
  useConditionOccurrenceAnyTimePrior = FALSE,
  useConditionOccurrenceLongTerm = FALSE,
  useConditionOccurrenceMediumTerm = FALSE,
  useConditionOccurrenceShortTerm = FALSE,
  useConditionOccurrencePrimaryInpatientAnyTimePrior = FALSE,
  useConditionOccurrencePrimaryInpatientLongTerm = FALSE,
  useConditionOccurrencePrimaryInpatientMediumTerm = FALSE,
  useConditionOccurrencePrimaryInpatientShortTerm = FALSE,
  useConditionEraAnyTimePrior = FALSE,
  useConditionEraLongTerm = FALSE,
  useConditionEraMediumTerm = FALSE,
  useConditionEraShortTerm = FALSE,
  useConditionEraOverlapping = FALSE,
  useConditionEraStartLongTerm = FALSE,
  useConditionEraStartMediumTerm = FALSE,
  useConditionEraStartShortTerm = FALSE,
  useConditionGroupEraAnyTimePrior = FALSE,
  useConditionGroupEraLongTerm = FALSE,
  useConditionGroupEraMediumTerm = FALSE,
  useConditionGroupEraShortTerm = FALSE,
  useConditionGroupEraOverlapping = FALSE,
  useConditionGroupEraStartLongTerm = FALSE,
  useConditionGroupEraStartMediumTerm = FALSE,
  useConditionGroupEraStartShortTerm = FALSE,
  useDrugExposureAnyTimePrior = FALSE,
  useDrugExposureLongTerm = FALSE,
  useDrugExposureMediumTerm = FALSE,
  useDrugExposureShortTerm = FALSE,
  useDrugEraAnyTimePrior = FALSE,
  useDrugEraLongTerm = FALSE,
  useDrugEraMediumTerm = FALSE,
  useDrugEraShortTerm = FALSE,
  useDrugEraOverlapping = FALSE,
  useDrugEraStartLongTerm = FALSE,
  useDrugEraStartMediumTerm = FALSE,
  useDrugEraStartShortTerm = FALSE,
  useDrugGroupEraAnyTimePrior = FALSE,
  useDrugGroupEraLongTerm = FALSE,
  useDrugGroupEraMediumTerm = FALSE,
  useDrugGroupEraShortTerm = FALSE,
  useDrugGroupEraOverlapping = FALSE,
  useDrugGroupEraStartLongTerm = FALSE,
  useDrugGroupEraStartMediumTerm = FALSE,
  useDrugGroupEraStartShortTerm = FALSE,
  useProcedureOccurrenceAnyTimePrior = FALSE,
  useProcedureOccurrenceLongTerm = FALSE,
  useProcedureOccurrenceMediumTerm = FALSE,
  useProcedureOccurrenceShortTerm = FALSE,
  useDeviceExposureAnyTimePrior = FALSE,
  useDeviceExposureLongTerm = FALSE,
  useDeviceExposureMediumTerm = FALSE,
  useDeviceExposureShortTerm = FALSE,
  useMeasurementAnyTimePrior = FALSE,
  useMeasurementLongTerm = FALSE,
  useMeasurementMediumTerm = FALSE,
  useMeasurementShortTerm = FALSE,
  useMeasurementValueAnyTimePrior = FALSE,
  useMeasurementValueLongTerm = FALSE,
  useMeasurementValueMediumTerm = FALSE,
  useMeasurementValueShortTerm = FALSE,
  useMeasurementRangeGroupAnyTimePrior = FALSE,
  useMeasurementRangeGroupLongTerm = FALSE,
  useMeasurementRangeGroupMediumTerm = FALSE,
  useMeasurementRangeGroupShortTerm = FALSE,
  useMeasurementValueAsConceptAnyTimePrior = FALSE,
  useMeasurementValueAsConceptLongTerm = FALSE,
  useMeasurementValueAsConceptMediumTerm = FALSE,
  useMeasurementValueAsConceptShortTerm = FALSE,
  useObservationAnyTimePrior = FALSE,
  useObservationLongTerm = FALSE,
  useObservationMediumTerm = FALSE,
  useObservationShortTerm = FALSE,
  useObservationValueAsConceptAnyTimePrior = FALSE,
  useObservationValueAsConceptLongTerm = FALSE,
  useObservationValueAsConceptMediumTerm = FALSE,
  useObservationValueAsConceptShortTerm = FALSE,
  useCharlsonIndex = FALSE,
  useDcsi = FALSE,
  useChads2 = FALSE,
  useChads2Vasc = FALSE,
  useHfrs = FALSE,
  useDistinctConditionCountLongTerm = FALSE,
  useDistinctConditionCountMediumTerm = FALSE,
  useDistinctConditionCountShortTerm = FALSE,
  useDistinctIngredientCountLongTerm = FALSE,
  useDistinctIngredientCountMediumTerm = FALSE,
  useDistinctIngredientCountShortTerm = FALSE,
  useDistinctProcedureCountLongTerm = FALSE,
  useDistinctProcedureCountMediumTerm = FALSE,
  useDistinctProcedureCountShortTerm = FALSE,
  useDistinctMeasurementCountLongTerm = FALSE,
  useDistinctMeasurementCountMediumTerm = FALSE,
  useDistinctMeasurementCountShortTerm = FALSE,
  useDistinctObservationCountLongTerm = FALSE,
  useDistinctObservationCountMediumTerm = FALSE,
  useDistinctObservationCountShortTerm = FALSE,
  useVisitCountLongTerm = FALSE,
  useVisitCountMediumTerm = FALSE,
  useVisitCountShortTerm = FALSE,
  useVisitConceptCountLongTerm = FALSE,
  useVisitConceptCountMediumTerm = FALSE,
  useVisitConceptCountShortTerm = FALSE,
  longTermStartDays = -365,
  mediumTermStartDays = -180,
  shortTermStartDays = -30,
  endDays = 0,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

useDemographicsGender

Gender of the subject. (analysis ID 1)
useDemographicsAge

Age of the subject on the index date (in years). (analysis ID 2)
useDemographicsAgeGroup

Age of the subject on the index date (in 5 year age groups) (analysis ID 3)
useDemographicsRace

Race of the subject. (analysis ID 4)
useDemographicsEthnicity

Ethnicity of the subject. (analysis ID 5)
useDemographicsIndexYear

Year of the index date. (analysis ID 6)
useDemographicsIndexMonth

Month of the index date. (analysis ID 7)
useDemographicsPriorObservationTime

Number of continuous days of observation time preceding the index date. (analysis ID 8)
useDemographicsPostObservationTime

Number of continuous days of observation time following the index date. (analysis ID 9)
useDemographicsTimeInCohort

Number of days of observation time during cohort period. (analysis ID 10)
useDemographicsIndexYearMonth

Both calendar year and month of the index date in a single variable. (analysis ID 11)
useCareSiteId

Care site associated with the cohort start, pulled from the visit_detail, visit_occurrence, or person table, in that order. (analysis ID 12)
useConditionOccurrenceAnyTimePrior

One covariate per condition in the condition_occurrence table starting any time prior to index. (analysis ID 101)
useConditionOccurrenceLongTerm

One covariate per condition in the condition_occurrence table starting in the long term window. (analysis ID 102)
useConditionOccurrenceMediumTerm

One covariate per condition in the condition_occurrence table starting in the medium term window. (analysis ID 103)
useConditionOccurrenceShortTerm

One covariate per condition in the condition_occurrence table starting in the short term window. (analysis ID 104)
useConditionOccurrencePrimaryInpatientAnyTimePrior

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting any time prior to index. (analysis ID 105)
useConditionOccurrencePrimaryInpatientLongTerm

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting in the long term window. (analysis ID 106)
useConditionOccurrencePrimaryInpatientMediumTerm

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting in the medium term window. (analysis ID 107)
useConditionOccurrencePrimaryInpatientShortTerm

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting in the short term window. (analysis ID 108)
useConditionEraAnyTimePrior

One covariate per condition in the condition_era table overlapping with any time prior to index. (analysis ID 201)
useConditionEraLongTerm

One covariate per condition in the condition_era table overlapping with any part of the long term window. (analysis ID 202)
useConditionEraMediumTerm

One covariate per condition in the condition_era table overlapping with any part of the medium term window. (analysis ID 203)
useConditionEraShortTerm

One covariate per condition in the condition_era table overlapping with any part of the short term window. (analysis ID 204)
useConditionEraOverlapping

One covariate per condition in the condition_era table overlapping with the end of the risk window. (analysis ID 205)
useConditionEraStartLongTerm

One covariate per condition in the condition_era table starting in the long term window. (analysis ID 206)
useConditionEraStartMediumTerm

One covariate per condition in the condition_era table starting in the medium term window. (analysis ID 207)
useConditionEraStartShortTerm

One covariate per condition in the condition_era table starting in the short term window. (analysis ID 208)
useConditionGroupEraAnyTimePrior

One covariate per condition era rolled up to groups in the condition_era table overlapping with any time prior to index. (analysis ID 209)
useConditionGroupEraLongTerm

One covariate per condition era rolled up to groups in the condition_era table overlapping with any part of the long term window. (analysis ID 210)
useConditionGroupEraMediumTerm

One covariate per condition era rolled up to groups in the condition_era table overlapping with any part of the medium term window. (analysis ID 211)
useConditionGroupEraShortTerm

One covariate per condition era rolled up to groups in the condition_era table overlapping with any part of the short term window. (analysis ID 212)
useConditionGroupEraOverlapping

One covariate per condition era rolled up to groups in the condition_era table overlapping with the end of the risk window. (analysis ID 213)
useConditionGroupEraStartLongTerm

One covariate per condition era rolled up to groups in the condition_era table starting in the long term window. (analysis ID 214)
useConditionGroupEraStartMediumTerm

One covariate per condition era rolled up to groups in the condition_era table starting in the medium term window. (analysis ID 215)
useConditionGroupEraStartShortTerm

One covariate per condition era rolled up to groups in the condition_era table starting in the short term window. (analysis ID 216)
useDrugExposureAnyTimePrior

One covariate per drug in the drug_exposure table starting any time prior to index. (analysis ID 301)
useDrugExposureLongTerm

One covariate per drug in the drug_exposure table starting in the long term window. (analysis ID 302)
useDrugExposureMediumTerm

One covariate per drug in the drug_exposure table starting in the medium term window. (analysis ID 303)
useDrugExposureShortTerm

One covariate per drug in the drug_exposure table starting in the short term window. (analysis ID 304)
useDrugEraAnyTimePrior

One covariate per drug in the drug_era table overlapping with any time prior to index. (analysis ID 401)
useDrugEraLongTerm

One covariate per drug in the drug_era table overlapping with any part of the long term window. (analysis ID 402)
useDrugEraMediumTerm

One covariate per drug in the drug_era table overlapping with any part of the medium term window. (analysis ID 403)
useDrugEraShortTerm

One covariate per drug in the drug_era table overlapping with any part of the short term window. (analysis ID 404)
useDrugEraOverlapping

One covariate per drug in the drug_era table overlapping with the end of the risk window. (analysis ID 405)
useDrugEraStartLongTerm

One covariate per drug in the drug_era table starting in the long term window. (analysis ID 406)
useDrugEraStartMediumTerm

One covariate per drug in the drug_era table starting in the medium term window. (analysis ID 407)
useDrugEraStartShortTerm

One covariate per drug in the drug_era table starting in the short term window. (analysis ID 408)
useDrugGroupEraAnyTimePrior

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with any time prior to index. (analysis ID 409)
useDrugGroupEraLongTerm

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with any part of the long term window. (analysis ID 410)
useDrugGroupEraMediumTerm

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with any part of the medium term window. (analysis ID 411)
useDrugGroupEraShortTerm

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with any part of the short term window. (analysis ID 412)
useDrugGroupEraOverlapping

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with the end of the risk window. (analysis ID 413)
useDrugGroupEraStartLongTerm

One covariate per drug rolled up to ATC groups in the drug_era table starting in the long term window. (analysis ID 414)
useDrugGroupEraStartMediumTerm

One covariate per drug rolled up to ATC groups in the drug_era table starting in the medium term window. (analysis ID 415)
useDrugGroupEraStartShortTerm

One covariate per drug rolled up to ATC groups in the drug_era table starting in the short term window. (analysis ID 416)
useProcedureOccurrenceAnyTimePrior

One covariate per procedure in the procedure_occurrence table any time prior to index. (analysis ID 501)
useProcedureOccurrenceLongTerm

One covariate per procedure in the procedure_occurrence table in the long term window. (analysis ID 502)
useProcedureOccurrenceMediumTerm

One covariate per procedure in the procedure_occurrence table in the medium term window. (analysis ID 503)
useProcedureOccurrenceShortTerm

One covariate per procedure in the procedure_occurrence table in the short term window. (analysis ID 504)
useDeviceExposureAnyTimePrior

One covariate per device in the device exposure table starting any time prior to index. (analysis ID 601)
useDeviceExposureLongTerm

One covariate per device in the device exposure table starting in the long term window. (analysis ID 602)
useDeviceExposureMediumTerm

One covariate per device in the device exposure table starting in the medium term window. (analysis ID 603)
useDeviceExposureShortTerm

One covariate per device in the device exposure table starting in the short term window. (analysis ID 604)
useMeasurementAnyTimePrior

One covariate per measurement in the measurement table any time prior to index. (analysis ID 701)
useMeasurementLongTerm

One covariate per measurement in the measurement table in the long term window. (analysis ID 702)
useMeasurementMediumTerm

One covariate per measurement in the measurement table in the medium term window. (analysis ID 703)
useMeasurementShortTerm

One covariate per measurement in the measurement table in the short term window. (analysis ID 704)
useMeasurementValueAnyTimePrior

One covariate containing the value per measurement-unit combination any time prior to index. (analysis ID 705)
useMeasurementValueLongTerm

One covariate containing the value per measurement-unit combination in the long term window. (analysis ID 706)
useMeasurementValueMediumTerm

One covariate containing the value per measurement-unit combination in the medium term window. (analysis ID 707)
useMeasurementValueShortTerm

One covariate containing the value per measurement-unit combination in the short term window. (analysis ID 708)
useMeasurementRangeGroupAnyTimePrior

Covariates indicating whether measurements are below, within, or above normal range any time prior to index. (analysis ID 709)
useMeasurementRangeGroupLongTerm

Covariates indicating whether measurements are below, within, or above normal range in the long term window. (analysis ID 710)
useMeasurementRangeGroupMediumTerm

Covariates indicating whether measurements are below, within, or above normal range in the medium term window. (analysis ID 711)
useMeasurementRangeGroupShortTerm

Covariates indicating whether measurements are below, within, or above normal range in the short term window. (analysis ID 712)
useMeasurementValueAsConceptAnyTimePrior

One covariate per measurement-value concept combination any time prior to index. (analysis ID 713)
useMeasurementValueAsConceptLongTerm

One covariate per measurement-value concept combination in the long term window. (analysis ID 714)
useMeasurementValueAsConceptMediumTerm

One covariate per measurement-value concept combination in the medium term window. (analysis ID 715)
useMeasurementValueAsConceptShortTerm

One covariate per measurement-value concept combination in the short term window. (analysis ID 716)
useObservationAnyTimePrior

One covariate per observation in the observation table any time prior to index. (analysis ID 801)
useObservationLongTerm

One covariate per observation in the observation table in the long term window. (analysis ID 802)
useObservationMediumTerm

One covariate per observation in the observation table in the medium term window. (analysis ID 803)
useObservationShortTerm

One covariate per observation in the observation table in the short term window. (analysis ID 804)
useObservationValueAsConceptAnyTimePrior

One covariate per observation-value concept combination any time prior to index. (analysis ID 805)
useObservationValueAsConceptLongTerm

One covariate per observation-value concept combination in the long term window. (analysis ID 806)
useObservationValueAsConceptMediumTerm

One covariate per observation-value concept combination in the medium term window. (analysis ID 807)
useObservationValueAsConceptShortTerm

One covariate per observation-value concept combination in the short term window. (analysis ID 808)
useCharlsonIndex

The Charlson comorbidity index (Romano adaptation) using all conditions prior to the window end. (analysis ID 901)
useDcsi

The Diabetes Comorbidity Severity Index (DCSI) using all conditions prior to the window end. (analysis ID 902)
useChads2

The CHADS2 score using all conditions prior to the window end. (analysis ID 903)
useChads2Vasc

The CHADS2VASc score using all conditions prior to the window end. (analysis ID 904)
useHfrs

The Hospital Frailty Risk Score score using all conditions prior to the window end. (analysis ID 926)
useDistinctConditionCountLongTerm

The number of distinct condition concepts observed in the long term window. (analysis ID 905)
useDistinctConditionCountMediumTerm

The number of distinct condition concepts observed in the medium term window. (analysis ID 906)
useDistinctConditionCountShortTerm

The number of distinct condition concepts observed in the short term window. (analysis ID 907)
useDistinctIngredientCountLongTerm

The number of distinct ingredients observed in the long term window. (analysis ID 908)
useDistinctIngredientCountMediumTerm

The number of distinct ingredients observed in the medium term window. (analysis ID 909)
useDistinctIngredientCountShortTerm

The number of distinct ingredients observed in the short term window. (analysis ID 910)
useDistinctProcedureCountLongTerm

The number of distinct procedures observed in the long term window. (analysis ID 911)
useDistinctProcedureCountMediumTerm

The number of distinct procedures observed in the medium term window. (analysis ID 912)
useDistinctProcedureCountShortTerm

The number of distinct procedures observed in the short term window. (analysis ID 913)
useDistinctMeasurementCountLongTerm

The number of distinct measurements observed in the long term window. (analysis ID 914)
useDistinctMeasurementCountMediumTerm

The number of distinct measurements observed in the medium term window. (analysis ID 915)
useDistinctMeasurementCountShortTerm

The number of distinct measurements observed in the short term window. (analysis ID 916)
useDistinctObservationCountLongTerm

The number of distinct observations observed in the long term window. (analysis ID 917)
useDistinctObservationCountMediumTerm

The number of distinct observations observed in the medium term window. (analysis ID 918)
useDistinctObservationCountShortTerm

The number of distinct observations observed in the short term window. (analysis ID 919)
useVisitCountLongTerm

The number of visits observed in the long term window. (analysis ID 920)
useVisitCountMediumTerm

The number of visits observed in the medium term window. (analysis ID 921)
useVisitCountShortTerm

The number of visits observed in the short term window. (analysis ID 922)
useVisitConceptCountLongTerm

The number of visits observed in the long term window, stratified by visit concept ID. (analysis ID 923)
useVisitConceptCountMediumTerm

The number of visits observed in the medium term window, stratified by visit concept ID. (analysis ID 924)
useVisitConceptCountShortTerm

The number of visits observed in the short term window, stratified by visit concept ID. (analysis ID 925)
longTermStartDays

What is the start day (relative to the index date) of the long-term window?
mediumTermStartDays

What is the start day (relative to the index date) of the medium-term window?
shortTermStartDays

What is the start day (relative to the index date) of the short-term window?
endDays

What is the end day (relative to the index date) of the window?
includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Details

creates an object specifying how covariates should be constructed from data in the CDM model.

Value

An object of type covariateSettings, to be used in other functions.

Examples

settings <- createCovariateSettings(
  useDemographicsGender = TRUE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = TRUE,
  useDemographicsRace = TRUE,
  useDemographicsEthnicity = TRUE,
  useDemographicsIndexYear = TRUE,
  useDemographicsIndexMonth = TRUE,
  useDemographicsPriorObservationTime = FALSE,
  useDemographicsPostObservationTime = FALSE,
  useDemographicsTimeInCohort = FALSE,
  useDemographicsIndexYearMonth = FALSE,
  useCareSiteId = FALSE,
  useConditionOccurrenceAnyTimePrior = FALSE,
  useConditionOccurrenceLongTerm = FALSE,
  useConditionOccurrenceMediumTerm = FALSE,
  useConditionOccurrenceShortTerm = FALSE,
  useConditionOccurrencePrimaryInpatientAnyTimePrior = FALSE,
  useConditionOccurrencePrimaryInpatientLongTerm = FALSE,
  useConditionOccurrencePrimaryInpatientMediumTerm = FALSE,
  useConditionOccurrencePrimaryInpatientShortTerm = FALSE,
  useConditionEraAnyTimePrior = FALSE,
  useConditionEraLongTerm = FALSE,
  useConditionEraMediumTerm = FALSE,
  useConditionEraShortTerm = FALSE,
  useConditionEraOverlapping = FALSE,
  useConditionEraStartLongTerm = FALSE,
  useConditionEraStartMediumTerm = FALSE,
  useConditionEraStartShortTerm = FALSE,
  useConditionGroupEraAnyTimePrior = FALSE,
  useConditionGroupEraLongTerm = TRUE,
  useConditionGroupEraMediumTerm = FALSE,
  useConditionGroupEraShortTerm = TRUE,
  useConditionGroupEraOverlapping = FALSE,
  useConditionGroupEraStartLongTerm = FALSE,
  useConditionGroupEraStartMediumTerm = FALSE,
  useConditionGroupEraStartShortTerm = FALSE,
  useDrugExposureAnyTimePrior = FALSE,
  useDrugExposureLongTerm = FALSE,
  useDrugExposureMediumTerm = FALSE,
  useDrugExposureShortTerm = FALSE,
  useDrugEraAnyTimePrior = FALSE,
  useDrugEraLongTerm = FALSE,
  useDrugEraMediumTerm = FALSE,
  useDrugEraShortTerm = FALSE,
  useDrugEraOverlapping = FALSE,
  useDrugEraStartLongTerm = FALSE,
  useDrugEraStartMediumTerm = FALSE,
  useDrugEraStartShortTerm = FALSE,
  useDrugGroupEraAnyTimePrior = FALSE,
  useDrugGroupEraLongTerm = TRUE,
  useDrugGroupEraMediumTerm = FALSE,
  useDrugGroupEraShortTerm = TRUE,
  useDrugGroupEraOverlapping = TRUE,
  useDrugGroupEraStartLongTerm = FALSE,
  useDrugGroupEraStartMediumTerm = FALSE,
  useDrugGroupEraStartShortTerm = FALSE,
  useProcedureOccurrenceAnyTimePrior = FALSE,
  useProcedureOccurrenceLongTerm = TRUE,
  useProcedureOccurrenceMediumTerm = FALSE,
  useProcedureOccurrenceShortTerm = TRUE,
  useDeviceExposureAnyTimePrior = FALSE,
  useDeviceExposureLongTerm = TRUE,
  useDeviceExposureMediumTerm = FALSE,
  useDeviceExposureShortTerm = TRUE,
  useMeasurementAnyTimePrior = FALSE,
  useMeasurementLongTerm = TRUE,
  useMeasurementMediumTerm = FALSE,
  useMeasurementShortTerm = TRUE,
  useMeasurementValueAnyTimePrior = FALSE,
  useMeasurementValueLongTerm = FALSE,
  useMeasurementValueMediumTerm = FALSE,
  useMeasurementValueShortTerm = FALSE,
  useMeasurementRangeGroupAnyTimePrior = FALSE,
  useMeasurementRangeGroupLongTerm = TRUE,
  useMeasurementRangeGroupMediumTerm = FALSE,
  useMeasurementRangeGroupShortTerm = TRUE,
  useMeasurementValueAsConceptAnyTimePrior = FALSE,
  useMeasurementValueAsConceptLongTerm = TRUE,
  useMeasurementValueAsConceptMediumTerm = FALSE,
  useMeasurementValueAsConceptShortTerm = TRUE,
  useObservationAnyTimePrior = FALSE,
  useObservationLongTerm = TRUE,
  useObservationMediumTerm = FALSE,
  useObservationShortTerm = TRUE,
  useObservationValueAsConceptAnyTimePrior = FALSE,
  useObservationValueAsConceptLongTerm = TRUE,
  useObservationValueAsConceptMediumTerm = FALSE,
  useObservationValueAsConceptShortTerm = TRUE,
  useCharlsonIndex = TRUE,
  useDcsi = TRUE,
  useChads2 = TRUE,
  useChads2Vasc = TRUE,
  useHfrs = FALSE,
  useDistinctConditionCountLongTerm = FALSE,
  useDistinctConditionCountMediumTerm = FALSE,
  useDistinctConditionCountShortTerm = FALSE,
  useDistinctIngredientCountLongTerm = FALSE,
  useDistinctIngredientCountMediumTerm = FALSE,
  useDistinctIngredientCountShortTerm = FALSE,
  useDistinctProcedureCountLongTerm = FALSE,
  useDistinctProcedureCountMediumTerm = FALSE,
  useDistinctProcedureCountShortTerm = FALSE,
  useDistinctMeasurementCountLongTerm = FALSE,
  useDistinctMeasurementCountMediumTerm = FALSE,
  useDistinctMeasurementCountShortTerm = FALSE,
  useDistinctObservationCountLongTerm = FALSE,
  useDistinctObservationCountMediumTerm = FALSE,
  useDistinctObservationCountShortTerm = FALSE,
  useVisitCountLongTerm = FALSE,
  useVisitCountMediumTerm = FALSE,
  useVisitCountShortTerm = FALSE,
  useVisitConceptCountLongTerm = FALSE,
  useVisitConceptCountMediumTerm = FALSE,
  useVisitConceptCountShortTerm = FALSE,
  longTermStartDays = -365,
  mediumTermStartDays = -180,
  shortTermStartDays = -30,
  endDays = 0,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Create default covariate settings

Description

Create default covariate settings

Usage

createDefaultCovariateSettings(
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Value

An object of type covariateSettings, to be used in other functions.

Examples

covSettings <- createDefaultCovariateSettings(
  includedCovariateConceptIds = c(1),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(2),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c(1)
)

Create default covariate settings

Description

Create default covariate settings

Usage

createDefaultTemporalCovariateSettings(
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Value

An object of type covariateSettings, to be used in other functions.

Examples

covSettings <- createDefaultTemporalCovariateSettings(
  includedCovariateConceptIds = c(1),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(2),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c(1)
)

Create detailed covariate settings

Description

Create detailed covariate settings

Usage

createDetailedCovariateSettings(analyses = list())

Arguments

analyses

A list of analysisDetail objects as created using createAnalysisDetails.

Details

creates an object specifying in detail how covariates should be constructed from data in the CDM model. Warning: this function is for advanced users only.

Value

An object of type covariateSettings, to be used in other functions.

Examples

analysisDetails <- createAnalysisDetails(
  analysisId = 1,
  sqlFileName = "DemographicsGender.sql",
  parameters = list(
    analysisId = 1,
    analysisName = "Gender",
    domainId = "Demographics"
  ),
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)
covSettings <- createDetailedCovariateSettings(analyses = analysisDetails)

Create detailed temporal covariate settings

Description

Create detailed temporal covariate settings

Usage

createDetailedTemporalCovariateSettings(
  analyses = list(),
  temporalStartDays = -365:-1,
  temporalEndDays = -365:-1
)

Arguments

analyses

A list of analysis detail objects as created using createAnalysisDetails.
temporalStartDays

A list of integers representing the start of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The start day is included in the time period.
temporalEndDays

A list of integers representing the end of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The end day is included in the time period.

Details

creates an object specifying in detail how temporal covariates should be constructed from data in the CDM model. Warning: this function is for advanced users only.

Value

An object of type covariateSettings, to be used in other functions.

Examples

analysisDetails <- createAnalysisDetails(
  analysisId = 1,
  sqlFileName = "DemographicsGender.sql",
  parameters = list(
    analysisId = 1,
    analysisName = "Gender",
    domainId = "Demographics"
  ),
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)
covSettings <- createDetailedTemporalCovariateSettings(
  analyses = analysisDetails,
  temporalStartDays = -365:-1,
  temporalEndDays = -365:-1
)

Creates an empty covariate data object

Description

Creates an empty covariate data object

Usage

createEmptyCovariateData(cohortIds, aggregated, temporal)

Arguments

cohortIds

For which cohort IDs should the covariate data be created?
aggregated

if the data should be aggregated
temporal

if the data is temporary

Value

an empty object of class CovariateData

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)

Create a table 1

Description

Creates a formatted table of cohort characteristics, to be included in publications or reports. Allows for creating a table describing a single cohort, or a table comparing two cohorts.

Usage

createTable1(
  covariateData1,
  covariateData2 = NULL,
  cohortId1 = NULL,
  cohortId2 = NULL,
  specifications = getDefaultTable1Specifications(),
  output = "two columns",
  showCounts = FALSE,
  showPercent = TRUE,
  percentDigits = 1,
  valueDigits = 1,
  stdDiffDigits = 2
)

Arguments

covariateData1

The covariate data of the cohort to be included in the table.
covariateData2

The covariate data of the cohort to also be included, when comparing two cohorts.
cohortId1

If provided, covariateData1 will be restricted to this cohort. If not provided, covariateData1 is assumed to contain data on only 1 cohort.
cohortId2

If provided, covariateData2 will be restricted to this cohort. If not provided, covariateData2 is assumed to contain data on only 1 cohort.
specifications

Specifications of which covariates to display, and how.
output

The output format for the table. Options are output = "two columns", output = "one column", or output = "list".
showCounts

Show the number of cohort entries having the binary covariate?
showPercent

Show the percentage of cohort entries having the binary covariate?
percentDigits

Number of digits to be used for percentages.
valueDigits

Number of digits to be used for the values of continuous variables.
stdDiffDigits

Number of digits to be used for the standardized differences.

Value

A data frame, or, when output = "list" a list of two data frames.

Examples

eunomiaConnectionDetails <- Eunomia::getEunomiaConnectionDetails()
covSettings <- createDefaultCovariateSettings()
Eunomia::createCohorts(
  connectionDetails = eunomiaConnectionDetails,
  cdmDatabaseSchema = "main",
  cohortDatabaseSchema = "main",
  cohortTable = "cohort"
)
covData1 <- getDbCovariateData(
  connectionDetails = eunomiaConnectionDetails,
  tempEmulationSchema = NULL,
  cdmDatabaseSchema = "main",
  cdmVersion = "5",
  cohortTable = "cohort",
  cohortDatabaseSchema = "main",
  cohortTableIsTemp = FALSE,
  cohortId = 1,
  rowIdField = "subject_id",
  covariateSettings = covSettings,
  aggregated = TRUE
)
covData2 <- getDbCovariateData(
  connectionDetails = eunomiaConnectionDetails,
  tempEmulationSchema = NULL,
  cdmDatabaseSchema = "main",
  cdmVersion = "5",
  cohortTable = "cohort",
  cohortDatabaseSchema = "main",
  cohortTableIsTemp = FALSE,
  cohortId = 2,
  rowIdField = "subject_id",
  covariateSettings = covSettings,
  aggregated = TRUE
)
table1 <- createTable1(
  covariateData1 = covData1,
  covariateData2 = covData2,
  cohortId1 = 1,
  cohortId2 = 2,
  specifications = getDefaultTable1Specifications(),
  output = "one column",
  showCounts = FALSE,
  showPercent = TRUE,
  percentDigits = 1,
  valueDigits = 1,
  stdDiffDigits = 2
)

Create covariate settings for a table 1

Description

Creates a covariate settings object for generating only those covariates that will be included in a table 1. This function works by filtering the covariateSettings object for the covariates in the specifications object.

Usage

createTable1CovariateSettings(
  specifications = getDefaultTable1Specifications(),
  covariateSettings = createDefaultCovariateSettings(),
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

specifications

A specifications object for generating a table using the createTable1 function.
covariateSettings

The covariate settings object to use as the basis for the filtered covariate settings.
includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Value

A covariate settings object, for example to be used when calling the getDbCovariateData function.

Examples

table1CovSettings <- createTable1CovariateSettings(
  specifications = getDefaultTable1Specifications(),
  covariateSettings = createDefaultCovariateSettings(),
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Create covariate settings

Description

Create covariate settings

Usage

createTemporalCovariateSettings(
  useDemographicsGender = FALSE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = FALSE,
  useDemographicsRace = FALSE,
  useDemographicsEthnicity = FALSE,
  useDemographicsIndexYear = FALSE,
  useDemographicsIndexMonth = FALSE,
  useDemographicsPriorObservationTime = FALSE,
  useDemographicsPostObservationTime = FALSE,
  useDemographicsTimeInCohort = FALSE,
  useDemographicsIndexYearMonth = FALSE,
  useCareSiteId = FALSE,
  useConditionOccurrence = FALSE,
  useConditionOccurrencePrimaryInpatient = FALSE,
  useConditionEraStart = FALSE,
  useConditionEraOverlap = FALSE,
  useConditionEraGroupStart = FALSE,
  useConditionEraGroupOverlap = FALSE,
  useDrugExposure = FALSE,
  useDrugEraStart = FALSE,
  useDrugEraOverlap = FALSE,
  useDrugEraGroupStart = FALSE,
  useDrugEraGroupOverlap = FALSE,
  useProcedureOccurrence = FALSE,
  useDeviceExposure = FALSE,
  useMeasurement = FALSE,
  useMeasurementValue = FALSE,
  useMeasurementRangeGroup = FALSE,
  useMeasurementValueAsConcept = FALSE,
  useObservation = FALSE,
  useObservationValueAsConcept = FALSE,
  useCharlsonIndex = FALSE,
  useDcsi = FALSE,
  useChads2 = FALSE,
  useChads2Vasc = FALSE,
  useHfrs = FALSE,
  useDistinctConditionCount = FALSE,
  useDistinctIngredientCount = FALSE,
  useDistinctProcedureCount = FALSE,
  useDistinctMeasurementCount = FALSE,
  useDistinctObservationCount = FALSE,
  useVisitCount = FALSE,
  useVisitConceptCount = FALSE,
  temporalStartDays = -365:-1,
  temporalEndDays = -365:-1,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

useDemographicsGender

Gender of the subject. (analysis ID 1)
useDemographicsAge

Age of the subject on the index date (in years). (analysis ID 2)
useDemographicsAgeGroup

Age of the subject on the index date (in 5 year age groups) (analysis ID 3)
useDemographicsRace

Race of the subject. (analysis ID 4)
useDemographicsEthnicity

Ethnicity of the subject. (analysis ID 5)
useDemographicsIndexYear

Year of the index date. (analysis ID 6)
useDemographicsIndexMonth

Month of the index date. (analysis ID 7)
useDemographicsPriorObservationTime

Number of days of observation time preceding the index date. (analysis ID 8)
useDemographicsPostObservationTime

Number of days of observation time preceding the index date. (analysis ID 9)
useDemographicsTimeInCohort

Number of days of observation time preceding the index date. (analysis ID 10)
useDemographicsIndexYearMonth

Calendar month of the index date. (analysis ID 11)
useCareSiteId

Care site associated with the cohort start, pulled from the visit_detail, visit_occurrence, or person table, in that order. (analysis ID 12)
useConditionOccurrence

One covariate per condition in the condition_occurrence table starting in the time window. (analysis ID 101)
useConditionOccurrencePrimaryInpatient

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting in the time window. (analysis ID 102)
useConditionEraStart

One covariate per condition in the condition_era table starting in the time window. (analysis ID 201)
useConditionEraOverlap

One covariate per condition in the condition_era table overlapping with any part of the time window. (analysis ID 202)
useConditionEraGroupStart

One covariate per condition era rolled up to SNOMED groups in the condition_era table starting in the time window. (analysis ID 203)
useConditionEraGroupOverlap

One covariate per condition era rolled up to SNOMED groups in the condition_era table overlapping with any part of the time window. (analysis ID 204)
useDrugExposure

One covariate per drug in the drug_exposure table starting in the time window. (analysis ID 301)
useDrugEraStart

One covariate per drug in the drug_era table starting in the time window. (analysis ID 401)
useDrugEraOverlap

One covariate per drug in the drug_era table overlapping with any part of the time window. (analysis ID 402)
useDrugEraGroupStart

One covariate per drug rolled up to ATC groups in the drug_era table starting in the time window. (analysis ID 403)
useDrugEraGroupOverlap

One covariate per drug rolled up to ATC groups in the drug_era table overlapping with any part of the time window. (analysis ID 404)
useProcedureOccurrence

One covariate per procedure in the procedure_occurrence table in the time window. (analysis ID 501)
useDeviceExposure

One covariate per device in the device exposure table starting in the timewindow. (analysis ID 601)
useMeasurement

One covariate per measurement in the measurement table in the time window. (analysis ID 701)
useMeasurementValue

One covariate containing the value per measurement-unit combination in the time window. If multiple values are found, the last is taken. (analysis ID 702)
useMeasurementRangeGroup

Covariates indicating whether measurements are below, within, or above normal range within the time period. (analysis ID 703)
useMeasurementValueAsConcept

One covariate per measurement-value concept combination within the time period. (analysis ID 704)
useObservation

One covariate per observation in the observation table in the time window. (analysis ID 801)
useObservationValueAsConcept

One covariate per observation-value concept combination within the time period. (analysis ID 802)
useCharlsonIndex

The Charlson comorbidity index (Romano adaptation) using all conditions prior to the window end. (analysis ID 901)
useDcsi

The Diabetes Comorbidity Severity Index (DCSI) using all conditions prior to the window end. (analysis ID 902)
useChads2

The CHADS2 score using all conditions prior to the window end. (analysis ID 903)
useChads2Vasc

The CHADS2VASc score using all conditions prior to the window end. (analysis ID 904)
useHfrs

The Hospital Frailty Risk Score score using all conditions prior to the window end. (analysis ID 926)
useDistinctConditionCount

The number of distinct condition concepts observed in the time window. (analysis ID 905)
useDistinctIngredientCount

The number of distinct ingredients observed in the time window. (analysis ID 906)
useDistinctProcedureCount

The number of distinct procedures observed in the time window. (analysis ID 907)
useDistinctMeasurementCount

The number of distinct measurements observed in the time window. (analysis ID 908)
useDistinctObservationCount

The number of distinct observations in the time window. (analysis ID 909)
useVisitCount

The number of visits observed in the time window. (analysis ID 910)
useVisitConceptCount

The number of visits observed in the time window, stratified by visit concept ID. (analysis ID 911)
temporalStartDays

A list of integers representing the start of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The start day is included in the time period.
temporalEndDays

A list of integers representing the end of a time period, relative to the index date. 0 indicates the index date, -1 indicates the day before the index date, etc. The end day is included in the time period.
includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Details

creates an object specifying how covariates should be constructed from data in the CDM model.

Value

An object of type covariateSettings, to be used in other functions.

Examples

settings <- createTemporalCovariateSettings(
  useDemographicsGender = TRUE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = TRUE,
  useDemographicsRace = TRUE,
  useDemographicsEthnicity = TRUE,
  useDemographicsIndexYear = TRUE,
  useDemographicsIndexMonth = TRUE,
  useDemographicsPriorObservationTime = FALSE,
  useDemographicsPostObservationTime = FALSE,
  useDemographicsTimeInCohort = FALSE,
  useDemographicsIndexYearMonth = FALSE,
  useCareSiteId = FALSE,
  useConditionOccurrence = FALSE,
  useConditionOccurrencePrimaryInpatient = FALSE,
  useConditionEraStart = FALSE,
  useConditionEraOverlap = FALSE,
  useConditionEraGroupStart = FALSE,
  useConditionEraGroupOverlap = TRUE,
  useDrugExposure = FALSE,
  useDrugEraStart = FALSE,
  useDrugEraOverlap = FALSE,
  useDrugEraGroupStart = FALSE,
  useDrugEraGroupOverlap = TRUE,
  useProcedureOccurrence = TRUE,
  useDeviceExposure = TRUE,
  useMeasurement = TRUE,
  useMeasurementValue = FALSE,
  useMeasurementRangeGroup = TRUE,
  useMeasurementValueAsConcept = TRUE,
  useObservation = TRUE,
  useObservationValueAsConcept = TRUE,
  useCharlsonIndex = TRUE,
  useDcsi = TRUE,
  useChads2 = TRUE,
  useChads2Vasc = TRUE,
  useHfrs = FALSE,
  useDistinctConditionCount = FALSE,
  useDistinctIngredientCount = FALSE,
  useDistinctProcedureCount = FALSE,
  useDistinctMeasurementCount = FALSE,
  useDistinctObservationCount = FALSE,
  useVisitCount = FALSE,
  useVisitConceptCount = FALSE,
  temporalStartDays = -365:-1,
  temporalEndDays = -365:-1,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Create covariate settings

Description

Create covariate settings

Usage

createTemporalSequenceCovariateSettings(
  useDemographicsGender = FALSE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = FALSE,
  useDemographicsRace = FALSE,
  useDemographicsEthnicity = FALSE,
  useDemographicsIndexYear = FALSE,
  useDemographicsIndexMonth = FALSE,
  useConditionOccurrence = FALSE,
  useConditionOccurrencePrimaryInpatient = FALSE,
  useConditionEraStart = FALSE,
  useConditionEraGroupStart = FALSE,
  useDrugExposure = FALSE,
  useDrugEraStart = FALSE,
  useDrugEraGroupStart = FALSE,
  useProcedureOccurrence = FALSE,
  useDeviceExposure = FALSE,
  useMeasurement = FALSE,
  useMeasurementValue = FALSE,
  useObservation = FALSE,
  timePart = "month",
  timeInterval = 1,
  sequenceEndDay = -1,
  sequenceStartDay = -730,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Arguments

useDemographicsGender

Gender of the subject. (analysis ID 1)
useDemographicsAge

Age of the subject on the index date (in years). (analysis ID 2)
useDemographicsAgeGroup

Age of the subject on the index date (in 5 year age groups) (analysis ID 3)
useDemographicsRace

Race of the subject. (analysis ID 4)
useDemographicsEthnicity

Ethnicity of the subject. (analysis ID 5)
useDemographicsIndexYear

Year of the index date. (analysis ID 6)
useDemographicsIndexMonth

Month of the index date. (analysis ID 7)
useConditionOccurrence

One covariate per condition in the condition_occurrence table starting in the time window. (analysis ID 101)
useConditionOccurrencePrimaryInpatient

One covariate per condition observed as a primary diagnosis in an inpatient setting in the condition_occurrence table starting in the time window. (analysis ID 102)
useConditionEraStart

One covariate per condition in the condition_era table starting in the time window. (analysis ID 201)
useConditionEraGroupStart

One covariate per condition era rolled up to SNOMED groups in the condition_era table starting in the time window. (analysis ID 203)
useDrugExposure

One covariate per drug in the drug_exposure table starting in the time window. (analysis ID 301)
useDrugEraStart

One covariate per drug in the drug_era table starting in the time window. (analysis ID 401)
useDrugEraGroupStart

One covariate per drug rolled up to ATC groups in the drug_era table starting in the time window. (analysis ID 403)
useProcedureOccurrence

One covariate per procedure in the procedure_occurrence table in the time window. (analysis ID 501)
useDeviceExposure

One covariate per device in the device exposure table starting in the timewindow. (analysis ID 601)
useMeasurement

One covariate per measurement in the measurement table in the time window. (analysis ID 701)
useMeasurementValue

One covariate containing the value per measurement-unit combination in the time window. If multiple values are found, the last is taken. (analysis ID 702)
useObservation

One covariate per observation in the observation table in the time window. (analysis ID 801)
timePart

The interval scale ('DAY', 'MONTH', 'YEAR')
timeInterval

Fixed interval length for timeId using the 'timePart' scale. For example, a 'timePart' of DAY with 'timeInterval' 30 has timeIds where timeId 1 is day 0 to day 29, timeId 2 is day 30 to day 59, etc.
sequenceEndDay

What is the end day (relative to the index date) of the data extraction?
sequenceStartDay

What is the start day (relative to the index date) of the data extraction?
includedCovariateConceptIds

A list of concept IDs that should be used to construct covariates.
addDescendantsToInclude

Should descendant concept IDs be added to the list of concepts to include?
excludedCovariateConceptIds

A list of concept IDs that should NOT be used to construct covariates.
addDescendantsToExclude

Should descendant concept IDs be added to the list of concepts to exclude?
includedCovariateIds

A list of covariate IDs that should be restricted to.

Details

creates an object specifying how covariates should be constructed from data in the CDM model.

Value

An object of type covariateSettings, to be used in other functions.

Examples

settings <- createTemporalSequenceCovariateSettings(
  useDemographicsGender = TRUE,
  useDemographicsAge = FALSE,
  useDemographicsAgeGroup = TRUE,
  useDemographicsRace = TRUE,
  useDemographicsEthnicity = TRUE,
  useDemographicsIndexYear = TRUE,
  useDemographicsIndexMonth = TRUE,
  useConditionOccurrence = FALSE,
  useConditionOccurrencePrimaryInpatient = FALSE,
  useConditionEraStart = FALSE,
  useConditionEraGroupStart = FALSE,
  useDrugExposure = FALSE,
  useDrugEraStart = FALSE,
  useDrugEraGroupStart = FALSE,
  useProcedureOccurrence = TRUE,
  useDeviceExposure = TRUE,
  useMeasurement = TRUE,
  useMeasurementValue = FALSE,
  useObservation = TRUE,
  timePart = "DAY",
  timeInterval = 1,
  sequenceEndDay = -1,
  sequenceStartDay = -730,
  includedCovariateConceptIds = c(),
  addDescendantsToInclude = FALSE,
  excludedCovariateConceptIds = c(),
  addDescendantsToExclude = FALSE,
  includedCovariateIds = c()
)

Filter covariates by cohort definition IDs

Description

Filter covariates by cohort definition IDs

Usage

filterByCohortDefinitionId(covariateData, cohortId = 1, cohortIds = c(1))

Arguments

covariateData

An object of type CovariateData
cohortId

DEPRECATED The cohort definition IDs to keep.
cohortIds

The cohort definition IDs to keep.

Value

An object of type covariateData.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = c(1, 2),
  aggregated = TRUE,
  temporal = FALSE
)

covData <- filterByCohortDefinitionId(
  covariateData = covariateData,
  cohortIds = c(1)
)

Filter covariates by row ID

Description

Filter covariates by row ID

Usage

filterByRowId(covariateData, rowIds)

Arguments

covariateData

An object of type CovariateData
rowIds

A vector containing the rowIds to keep.

Value

An object of type covariateData.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)

covData <- filterByRowId(
  covariateData = covariateData,
  rowIds = 1
)

Getcovariate information from the database through the cohort_attribute table

Description

Constructs covariates using the cohort_attribute table.

Usage

getDbCohortAttrCovariatesData(
  connection,
  oracleTempSchema = NULL,
  cdmDatabaseSchema,
  cohortTable = "#cohort_person",
  cohortId = -1,
  cohortIds = c(-1),
  cdmVersion = "5",
  rowIdField = "subject_id",
  covariateSettings,
  aggregated = FALSE,
  tempEmulationSchema = NULL
)

Arguments

connection

A connection to the server containing the schema as created using the connect function in the DatabaseConnector package.
oracleTempSchema

DEPRECATED: use tempEmulationSchema instead.
cdmDatabaseSchema

The name of the database schema that contains the OMOP CDM instance. Requires read permissions to this database. On SQL Server, this should specifiy both the database and the schema, so for example 'cdm_instance.dbo'.
cohortTable

Name of the table holding the cohort for which we want to construct covariates. If it is a temp table, the name should have a hash prefix, e.g. '#temp_table'. If it is a non-temp table, it should include the database schema, e.g. 'cdm_database.cohort'.
cohortId

DEPRECATED:For which cohort ID should covariates be constructed? If set to -1, covariates will be constructed for all cohorts in the specified cohort table.
cohortIds

For which cohort ID(s) should covariates be constructed? If set to c(-1), covariates will be constructed for all cohorts in the specified cohort table.
cdmVersion

The version of the Common Data Model used. Currently only cdmVersion = "5" is supported.
rowIdField

The name of the field in the cohort temp table that is to be used as the row_id field in the output table. This can be especially usefull if there is more than one period per person.
covariateSettings

An object of type covariateSettings as created using the createCohortAttrCovariateSettings function.
aggregated

Should aggregate statistics be computed instead of covariates per cohort entry?
tempEmulationSchema

Some database platforms like Oracle and Impala do not truly support temp tables. To emulate temp tables, provide a schema with write privileges where temp tables can be created.

Details

This function uses the data in the CDM to construct a large set of covariates for the provided cohort. The cohort is assumed to be in an existing temp table with these fields: 'subject_id', 'cohort_definition_id', 'cohort_start_date'. Optionally, an extra field can be added containing the unique identifier that will be used as rowID in the output. Typically, users don't call this function directly but rather use the getDbCovariateData function instead.

Value

Returns an object of type CovariateData, which is an Andromeda object containing information on the baseline covariates. Information about multiple outcomes can be captured at once for efficiency reasons. This object is a list with the following components:

covariates

An ffdf object listing the baseline covariates per person in the cohorts. This is done using a sparse representation: covariates with a value of 0 are omitted to save space. The covariates object will have three columns: rowId, covariateId, and covariateValue. The rowId is usually equal to the person_id, unless specified otherwise in the rowIdField argument.

covariateRef

A table describing the covariates that have been extracted.

. The CovariateData object will also have a metaData attribute, a list of objects with information on how the covariateData object was constructed.

Examples

connectionDetails <- Eunomia::getEunomiaConnectionDetails()
Eunomia::createCohorts(
  connectionDetails = connectionDetails,
  cdmDatabaseSchema = "main",
  cohortDatabaseSchema = "main",
  cohortTable = "cohort"
)
connection <- DatabaseConnector::connect(connectionDetails)
covariateSettings <- createCohortAttrCovariateSettings(
  attrDatabaseSchema = "main",
  cohortAttrTable = "cohort_attribute",
  attrDefinitionTable = "attribute_definition",
  includeAttrIds = c(1),
  isBinary = FALSE,
  missingMeansZero = FALSE
)

covData <- getDbCohortAttrCovariatesData(
  connection = connection,
  tempEmulationSchema = NULL,
  cdmDatabaseSchema = "main",
  cdmVersion = "5",
  cohortTable = "cohort",
  cohortIds = 1,
  rowIdField = "subject_id",
  covariateSettings = covariateSettings,
  aggregated = FALSE
)

Get covariate information from the database based on other cohorts

Description

Constructs covariates using other cohorts.

Usage

getDbCohortBasedCovariatesData(
  connection,
  oracleTempSchema = NULL,
  cdmDatabaseSchema,
  cohortTable = "#cohort_person",
  cohortId = -1,
  cohortIds = c(-1),
  cdmVersion = "5",
  rowIdField = "subject_id",
  covariateSettings,
  aggregated = FALSE,
  minCharacterizationMean = 0,
  tempEmulationSchema = NULL
)

Arguments

connection

A connection to the server containing the schema as created using the connect function in the DatabaseConnector package.
oracleTempSchema

DEPRECATED: use tempEmulationSchema instead.
cdmDatabaseSchema

The name of the database schema that contains the OMOP CDM instance. Requires read permissions to this database. On SQL Server, this should specifiy both the database and the schema, so for example 'cdm_instance.dbo'.
cohortTable

Name of the table holding the cohort for which we want to construct covariates. If it is a temp table, the name should have a hash prefix, e.g. '#temp_table'. If it is a non-temp table, it should include the database schema, e.g. 'cdm_database.cohort'.
cohortId

DEPRECATED:For which cohort ID should covariates be constructed? If set to -1, covariates will be constructed for all cohorts in the specified cohort table.
cohortIds

For which cohort ID(s) should covariates be constructed? If set to c(-1), covariates will be constructed for all cohorts in the specified cohort table.
cdmVersion

The version of the Common Data Model used. Currently only cdmVersion = "5" is supported.
rowIdField

The name of the field in the cohort temp table that is to be used as the row_id field in the output table. This can be especially usefull if there is more than one period per person.
covariateSettings

An object of type covariateSettings as created using the createCohortBasedCovariateSettings or createCohortBasedTemporalCovariateSettings functions.
aggregated

Should aggregate statistics be computed instead of covariates per cohort entry?
minCharacterizationMean

The minimum mean value for binary characterization output. Values below this will be cut off from output. This will help reduce the file size of the characterization output, but will remove information on covariates that have very low values. The default is 0.
tempEmulationSchema

Some database platforms like Oracle and Impala do not truly support temp tables. To emulate temp tables, provide a schema with write privileges where temp tables can be created.

Details

This function uses the data in the CDM to construct a large set of covariates for the provided cohort. The cohort is assumed to be in an existing temp table with these fields: 'subject_id', 'cohort_definition_id', 'cohort_start_date'. Optionally, an extra field can be added containing the unique identifier that will be used as rowID in the output. Typically, users don't call this function directly but rather use the getDbCovariateData function instead.

Value

Returns an object of type CovariateData, which is an Andromeda object containing information on the baseline covariates. Information about multiple outcomes can be captured at once for efficiency reasons. This object is a list with the following components:

covariates

An ffdf object listing the baseline covariates per person in the cohorts. This is done using a sparse representation: covariates with a value of 0 are omitted to save space. The covariates object will have three columns: rowId, covariateId, and covariateValue. The rowId is usually equal to the person_id, unless specified otherwise in the rowIdField argument.

covariateRef

A table describing the covariates that have been extracted.

. The CovariateData object will also have a metaData attribute, a list of objects with information on how the covariateData object was constructed.

Get covariate information from the database

Description

Uses one or several covariate builder functions to construct covariates.

Usage

getDbCovariateData(
  connectionDetails = NULL,
  connection = NULL,
  oracleTempSchema = NULL,
  cdmDatabaseSchema,
  cdmVersion = "5",
  cohortTable = "cohort",
  cohortDatabaseSchema = cdmDatabaseSchema,
  cohortTableIsTemp = FALSE,
  cohortId = -1,
  cohortIds = c(-1),
  rowIdField = "subject_id",
  covariateSettings,
  aggregated = FALSE,
  minCharacterizationMean = 0,
  tempEmulationSchema = NULL
)

Arguments

connectionDetails

An R object of type connectionDetails created using the function createConnectionDetails in the DatabaseConnector package. Either the connection or connectionDetails argument should be specified.
connection

A connection to the server containing the schema as created using the connect function in the DatabaseConnector package. Either the connection or connectionDetails argument should be specified.
oracleTempSchema

DEPRECATED: use tempEmulationSchema instead.
cdmDatabaseSchema

The name of the database schema that contains the OMOP CDM instance. Requires read permissions to this database. On SQL Server, this should specify both the database and the schema, so for example 'cdm_instance.dbo'.
cdmVersion

Define the OMOP CDM version used: currently supported is "5".
cohortTable

Name of the (temp) table holding the cohort for which we want to construct covariates
cohortDatabaseSchema

If the cohort table is not a temp table, specify the database schema where the cohort table can be found. On SQL Server, this should specify both the database and the schema, so for example 'cdm_instance.dbo'.
cohortTableIsTemp

Is the cohort table a temp table?
cohortId

DEPRECATED:For which cohort ID(s) should covariates be constructed? If set to -1, covariates will be constructed for all cohorts in the specified cohort table.
cohortIds

For which cohort ID(s) should covariates be constructed? If set to c(-1), covariates will be constructed for all cohorts in the specified cohort table.
rowIdField

The name of the field in the cohort table that is to be used as the row_id field in the output table. This can be especially usefull if there is more than one period per person.
covariateSettings

Either an object of type covariateSettings as created using one of the createCovariate functions, or a list of such objects.
aggregated

Should aggregate statistics be computed instead of covariates per cohort entry? If aggregated is set to FALSE, the results returned will be based on each subject_id and cohort_start_date in your cohort table. If your cohort contains multiple entries for the same subject_id (due to different cohort_start_date values), you must carefully set the rowIdField so you can identify the patients properly. See issue #229 for more discussion on this parameter.
minCharacterizationMean

The minimum mean value for characterization output. Values below this will be cut off from output. This will help reduce the file size of the characterization output, but will remove information on covariates that have very low values. The default is 0.
tempEmulationSchema

Some database platforms like Oracle and Impala do not truly support temp tables. To emulate temp tables, provide a schema with write privileges where temp tables can be created.

Details

This function uses the data in the CDM to construct a large set of covariates for the provided cohort. The cohort is assumed to be in an existing table with these fields: 'subject_id', 'cohort_definition_id', 'cohort_start_date'. Optionally, an extra field can be added containing the unique identifier that will be used as rowID in the output.

Value

Returns an object of type covariateData, containing information on the covariates.

Examples

eunomiaConnectionDetails <- Eunomia::getEunomiaConnectionDetails()
covSettings <- createDefaultCovariateSettings()
Eunomia::createCohorts(
  connectionDetails = eunomiaConnectionDetails,
  cdmDatabaseSchema = "main",
  cohortDatabaseSchema = "main",
  cohortTable = "cohort"
)
covData <- getDbCovariateData(
  connectionDetails = eunomiaConnectionDetails,
  tempEmulationSchema = NULL,
  cdmDatabaseSchema = "main",
  cdmVersion = "5",
  cohortTable = "cohort",
  cohortDatabaseSchema = "main",
  cohortTableIsTemp = FALSE,
  cohortIds = -1,
  rowIdField = "subject_id",
  covariateSettings = covSettings,
  aggregated = FALSE
)

Get default covariate information from the database

Description

Constructs a large default set of covariates for one or more cohorts using data in the CDM schema. Includes covariates for all drugs, drug classes, condition, condition classes, procedures, observations, etc.

Usage

getDbDefaultCovariateData(
  connection,
  oracleTempSchema = NULL,
  cdmDatabaseSchema,
  cohortTable = "#cohort_person",
  cohortId = -1,
  cohortIds = c(-1),
  cdmVersion = "5",
  rowIdField = "subject_id",
  covariateSettings,
  targetDatabaseSchema,
  targetCovariateTable,
  targetCovariateRefTable,
  targetAnalysisRefTable,
  aggregated = FALSE,
  minCharacterizationMean = 0,
  tempEmulationSchema = NULL
)

Arguments

connection

A connection to the server containing the schema as created using the connect function in the DatabaseConnector package.
oracleTempSchema

DEPRECATED: use tempEmulationSchema instead.
cdmDatabaseSchema

The name of the database schema that contains the OMOP CDM instance. Requires read permissions to this database. On SQL Server, this should specifiy both the database and the schema, so for example 'cdm_instance.dbo'.
cohortTable

Name of the table holding the cohort for which we want to construct covariates. If it is a temp table, the name should have a hash prefix, e.g. '#temp_table'. If it is a non-temp table, it should include the database schema, e.g. 'cdm_database.cohort'.
cohortId

DEPRECATED:For which cohort ID should covariates be constructed? If set to -1, covariates will be constructed for all cohorts in the specified cohort table.
cohortIds

For which cohort ID(s) should covariates be constructed? If set to c(-1), covariates will be constructed for all cohorts in the specified cohort table.
cdmVersion

The version of the Common Data Model used. Currently only cdmVersion = "5" is supported.
rowIdField

The name of the field in the cohort temp table that is to be used as the row_id field in the output table. This can be especially usefull if there is more than one period per person.
covariateSettings

Either an object of type covariateSettings as created using one of the createCovariate functions, or a list of such objects.
targetDatabaseSchema

(Optional) The name of the database schema where the resulting covariates should be stored.
targetCovariateTable

(Optional) The name of the table where the resulting covariates will be stored. If not provided, results will be fetched to R. The table can be a permanent table in the targetDatabaseSchema or a temp table. If it is a temp table, do not specify targetDatabaseSchema.
targetCovariateRefTable

(Optional) The name of the table where the covariate reference will be stored.
targetAnalysisRefTable

(Optional) The name of the table where the analysis reference will be stored.
aggregated

Should aggregate statistics be computed instead of covariates per cohort entry?
minCharacterizationMean

The minimum mean value for binary characterization output. Values below this will be cut off from output. This will help reduce the file size of the characterization output, but will remove information on covariates that have very low values. The default is 0.
tempEmulationSchema

Some database platforms like Oracle and Impala do not truly support temp tables. To emulate temp tables, provide a schema with write privileges where temp tables can be created.

Details

This function uses the data in the CDM to construct a large set of covariates for the provided cohort. The cohort is assumed to be in an existing temp table with these fields: 'subject_id', 'cohort_definition_id', 'cohort_start_date'. Optionally, an extra field can be added containing the unique identifier that will be used as rowID in the output. Typically, users don't call this function directly but rather use the getDbCovariateData function instead.

Value

Returns an object of type CovariateData, which is an Andromeda object containing information on the baseline covariates. Information about multiple outcomes can be captured at once for efficiency reasons. This object is a list with the following components:

covariates

An ffdf object listing the baseline covariates per person in the cohorts. This is done using a sparse representation: covariates with a value of 0 are omitted to save space. The covariates object will have three columns: rowId, covariateId, and covariateValue. The rowId is usually equal to the person_id, unless specified otherwise in the rowIdField argument.

covariateRef

A table describing the covariates that have been extracted.

. The CovariateData object will also have a metaData attribute, a list of objects with information on how the covariateData object was constructed.

Examples

connectionDetails <- Eunomia::getEunomiaConnectionDetails()
Eunomia::createCohorts(
  connectionDetails = connectionDetails,
  cdmDatabaseSchema = "main",
  cohortDatabaseSchema = "main",
  cohortTable = "cohort"
)
connection <- DatabaseConnector::connect(connectionDetails)

results <- getDbDefaultCovariateData(
  connection = connection,
  cdmDatabaseSchema = "main",
  cohortTable = "cohort",
  covariateSettings = createDefaultCovariateSettings(),
  targetDatabaseSchema = "main",
  targetCovariateTable = "ut_cov"
)

Get the default table 1 specifications

Description

Loads the default specifications for a table 1, to be used with the createTable1 function.

Usage

getDefaultTable1Specifications()

Value

A specifications objects.

Examples

defaultTable1Specs <- getDefaultTable1Specifications()

Check whether covariate data is aggregated

Description

Check whether covariate data is aggregated

Usage

isAggregatedCovariateData(x)

Arguments

x

The covariate data object to check.

Value

A logical value.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)
isAggrCovData <- isAggregatedCovariateData(covariateData)

Check whether an object is a CovariateData object

Description

Check whether an object is a CovariateData object

Usage

isCovariateData(x)

Arguments

x

The object to check.

Value

A logical value.

Examples

binaryCovDataFile <- system.file("testdata/binaryCovariateData.zip",
  package = "FeatureExtraction"
)
covData <- loadCovariateData(binaryCovDataFile)
isCovData <- isCovariateData(covData)

Check whether covariate data is temporal

Description

Check whether covariate data is temporal

Usage

isTemporalCovariateData(x)

Arguments

x

The covariate data object to check.

Value

A logical value.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)
isTempCovData <- isTemporalCovariateData(covariateData)

Load the covariate data from a folder

Description

loadCovariateData loads an object of type covariateData from a folder in the file system.

Usage

loadCovariateData(file, readOnly)

Arguments

file

The name of the folder containing the data.
readOnly

DEPRECATED: If true, the data is opened read only.

Details

The data will be written to a set of files in the folder specified by the user.

Value

An object of class CovariateData.

Examples

binaryCovDataFile <- system.file("testdata/binaryCovariateData.zip",
  package = "FeatureExtraction"
)
covData <- loadCovariateData(binaryCovDataFile)

Save the covariate data to folder

Description

saveCovariateData saves an object of type covariateData to folder.

Usage

saveCovariateData(covariateData, file)

Arguments

covariateData

An object of type covariateData as generated using getDbCovariateData.
file

The name of the folder where the data will be written. The folder should not yet exist.

Details

The data will be written to a set of files in the folder specified by the user.

Value

No return value, called for side effects.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)
# For this example we'll use a temporary file location:
fileName <- tempfile()
saveCovariateData(covariateData = covariateData, file = fileName)
# Cleaning up the file used in this example:
unlink(fileName)

Tidy covariate data

Description

Tidy covariate data

Usage

tidyCovariateData(
  covariateData,
  minFraction = 0.001,
  normalize = TRUE,
  removeRedundancy = TRUE
)

Arguments

covariateData

An object as generated using the getDbCovariateData function.
minFraction

Minimum fraction of the population that should have a non-zero value for a covariate for that covariate to be kept. Set to 0 to don't filter on frequency.
normalize

Normalize the covariates? (dividing by the max).
removeRedundancy

Should redundant covariates be removed?

Details

Normalize covariate values by dividing by the max and/or remove redundant covariates and/or remove infrequent covariates. For temporal covariates, redundancy is evaluated per time ID.

Value

An object of class CovariateData.

Examples

covariateData <- FeatureExtraction::createEmptyCovariateData(
  cohortIds = 1,
  aggregated = FALSE,
  temporal = FALSE
)

covData <- tidyCovariateData(
  covariateData = covariateData,
  minFraction = 0.001,
  normalize = TRUE,
  removeRedundancy = TRUE
)