Skip to contents

Configuration

a01_configuration.Rmd

Initiating database connection

We use the CDMConnector package to establish the database connection. You can configure the connection either by reading credentials from a .Renviron file or explicitly writing them in your script.

################################################################################
#
# Initiate the database connection
#
#################################################################################

user <- Sys.getenv("DB_USERNAME")
pw <- Sys.getenv("DB_PASSWORD")
server <- stringr::str_c(Sys.getenv("DB_HOST"), "/", Sys.getenv("DB_NAME"))
port <- Sys.getenv("DB_PORT")

cdmSchema <-
  Sys.getenv("OHDSI_CDM") # Schema which contains the OHDSI Common Data Model
cdmVocabSchema <-
  Sys.getenv("OHDSI_VOCAB") # Schema which contains the OHDSI Common Data Model vocabulary tables.
cdmResultsSchema <-
  Sys.getenv("OHDSI_RESULTS") # Schema which contains "cohort" table (is not mandatory)
writeSchema <-
  Sys.getenv("OHDSI_WRITE") # Schema for temporary tables, will be deleted
writePrefix <- "c2t_"

db = DBI::dbConnect(
  RPostgres::Postgres(),
  dbname = Sys.getenv("DB_NAME"),
  host = Sys.getenv("DB_HOST"),
  user = Sys.getenv("DB_USERNAME"),
  password = Sys.getenv("DB_PASSWORD"),
  port  = port
)

cdm <- CDMConnector::cdmFromCon(
  con = db,
  cdmSchema = cdmSchema,
  achillesSchema = cdmResultsSchema,
  writeSchema = c(schema = writeSchema, prefix = writePrefix),
)

Configuration

To enhance the user experience, an R environment named studyEnv is created, which consolidates the necessary parameters required for running the study. This environment simplifies managing inputs and ensures consistency across functions. Input description available here. Below is an example configuration with default values:

################################################################################
#
# Configure study settings
#
################################################################################

studyEnv <- cohort2TrajectoryConfiguration(
  cdm = cdm,
  studyName = "Cohort2Trajectory",
  baseUrl = "http://localhost:8080/WebAPI",
  pathToStudy = getwd(),
  atlasTargetCohort = NULL,
  atlasStateCohorts = NULL,
  stateCohortLabels = NULL,
  stateCohortPriorityOrder = NULL,
  stateCohortMandatory = NULL,
  stateCohortAbsorbing = NULL,
  stateSelectionType = NULL,
  oocFix = "None",
  trajectoryType = "Discrete",
  lengthOfStay = NULL,
  outOfCohortAllowed = FALSE,
  runSavedStudy = FALSE,
  useCDM = TRUE,
  trajectoryDataObject = NULL,
  pathToData = './Cohort2Trajectory/Data/importedData.csv',
  allowedStatesList = createStateList(stateCohortLabels),
  mergeStates = FALSE,
  mergeThreshold = 0.5,
  batchSize = 1000
)


Configuration with ATLAS generated cohorts 


studyEnv <- cohort2TrajectoryConfiguration(
    baseUrl = "http://localhost:8080/WebAPI",     #<--- URL for API
    useCDM = TRUE,                                #<--- set use CDM TRUE
    studyName = "nameForStudy",
    pathToStudy = getwd(),
    atlasTargetCohort = 1,                 #<--- existing cohort's id
    atlasStateCohorts = c(2, 3),           #<--- existing cohorts' ids
    stateCohortLabels = c("label_for_cohort1", "label_for_cohort2"),
    stateCohortMandatory = c("label_for_cohort2"),
    stateCohortAbsorbing = c("label_for_cohort2"),
    outOfCohortAllowed = FALSE,
    trajectoryType = "Discrete",
    lengthOfStay = 30,
    stateSelectionType = "Priority",
    stateCohortPriorityOrder = c("label_for_cohort1", "label_for_cohort2"),
    runSavedStudy = FALSE,
    batchSize = 10
  )


Configuration with saved study 


studyEnv <- cohort2TrajectoryConfiguration(
    baseUrl = NULL,     
    useCDM = FALSE,                                
    studyName = "nameForStudy",                   #<--- name of the study in trajectorySettings.csv
    pathToStudy = getwd(),
    stateCohortLabels = c("label_for_cohort1", "label_for_cohort2"),
    runSavedStudy = TRUE,                           #<--- set run saved study to true
    batchSize = 10
  )


Configuration with data as input 


studyEnv <- cohort2TrajectoryConfiguration(
    baseUrl = NULL,   
    useCDM = FALSE,                       
    trajectoryDataObject = rawData,               #<--- eg output of read.csv
    studyName = "nameForStudy",
    pathToStudy = getwd(),
    stateCohortMandatory = c("label_for_cohort2"),
    stateCohortAbsorbing = c("label_for_cohort2"),
    outOfCohortAllowed = FALSE,
    trajectoryType = "Discrete",
    lengthOfStay = 30,
    stateSelectionType = "Priority",
    stateCohortPriorityOrder = c("label_for_cohort1", "label_for_cohort2"),
    runSavedStudy = FALSE,
    batchSize = 10
  )


Configuration with path to data as input 


studyEnv <- cohort2TrajectoryConfiguration(
    baseUrl = NULL,   
    useCDM = FALSE,                       
    pathToData = paste0(getwd(), "/path/to/data/data.csv")), #<--- path to data as input
    studyName = "nameForStudy",
    pathToStudy = getwd(),
    stateCohortMandatory = c("label_for_cohort2"),
    stateCohortAbsorbing = c("label_for_cohort2"),
    outOfCohortAllowed = FALSE,
    trajectoryType = "Discrete",
    lengthOfStay = 30,
    stateSelectionType = "Priority",
    stateCohortPriorityOrder = c("label_for_cohort1", "label_for_cohort2"),
    runSavedStudy = FALSE,
    batchSize = 10
  )