Merge pull request #2 from ohdsi-studies/develop

v1.0.0 release

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: EhdenAlopecia 
-Version: 0.1
+Version: 1.0.0
 Authors@R: person("Ross", "Williams", , "r.williams@derasmusmc.nl", role = c("aut", "cre"))
 Description: This package creates the cohorts for this EHDEN Alopecia study study. Based on this cohort diagnostics, incidence and prevalence rates and treatment patterns are analysis are performed.
 License: Apache License (>= 2)
@@ -15,12 +15,13 @@ Imports:
     zip,
     magrittr,
     checkmate,
-    duckdb,
     log4r,
     lubridate,
-    rlang
+    rlang,
+    readr
 Suggests: 
     testthat (>= 3.0.0),
     rmarkdown,
-    checkmate
+    checkmate,
+    duckdb,
 Config/testthat/edition: 3

NAMESPACE

@@ -1,4 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
 export("%>%")
+export(createCohorts)
+export(runStudy)
 importFrom(magrittr,"%>%")

R/createCohorts.R

@@ -4,9 +4,8 @@
 #' @param cohortTable Name of the table to be created where cohorts will be stored
 #' @param cdmDatabaseSchema name of the schema where the cdm is stored
 #' @param cohortDatabaseSchema name of a schema with write access for the creation of cohort table
-#' @return 
 #'
-#' @examples
+#' @export
 createCohorts <- function(connectionDetails, 
                           cohortTable, 
                           cdmDatabaseSchema, 
@@ -29,7 +28,7 @@ createCohorts <- function(connectionDetails,
   cohortJson <- readChar(cohortJsonFileName, file.info(cohortJsonFileName)$size)
   cohortExpression <- CirceR::cohortExpressionFromJson(cohortJson)
   cohortSql <- CirceR::buildCohortQuery(cohortExpression, options = CirceR::createGenerateOptions(generateStats = FALSE))
-  cohortsToCreate <- rbind(cohortsToCreate, data.frame(cohortId = i,
+  cohortsToCreate <- rbind(cohortsToCreate, data.frame(cohortId = 91+i,
                                                        cohortName = cohortName, 
                                                        sql = cohortSql,
                                                        stringsAsFactors = FALSE))
@@ -54,4 +53,5 @@ createCohorts <- function(connectionDetails,
                                                  cohortDatabaseSchema = cohortDatabaseSchema,
                                                  cohortTable = cohortTableNames$cohortTable)
   print(cohortCounts)
+  return(cohortsGenerated)
 }

R/runStudy.R

@@ -1,8 +1,26 @@
-runStudy <- function(connectionDetails, 
+#' run the main elements of the study
+#'
+#' @param connectionDetails connection details generated using DatabaseConnector::createConnectionDetails()
+#' @param cohortTable Name of the table to be created where cohorts will be stored
+#' @param cdmDatabaseSchema name of the schema where the cdm is stored
+#' @param cohortDatabaseSchema name of a schema with write access for the creation of cohort table
+#' @param instantiateCohorts choose whether to instantiate the cohorts on your database
+#' @param runDiagnostics choose whether to run the cohort diagnostics 
+#' @param outputFolder The folder where the results should be written
+#' @param databaseId a short name that can identify the database used
+#' @param minCellCount the minimum number of patients that can be shared for any single count in the results
+#'
+#' @export
+
+runStudy <- function(connectionDetails,
                      cohortTable, 
                      cdmDatabaseSchema, 
                      cohortDatabaseSchema,
-                     instantiateCohorts) {
+                     instantiateCohorts = FALSE,
+                     runDiagnostics = FALSE,
+                     outputFolder,
+                     databaseId,
+                     minCellCount) {
 
   if (instantiateCohorts){
     createCohorts(connectionDetails = connectionDetails, 
@@ -12,19 +30,15 @@ runStudy <- function(connectionDetails,
   }
 
   if (runDiagnostics){
-    executeDiagnostics(cohortDefinitionSet,
+    cohortDefinitionSet <- readr::read_csv("inst/cohortDefinitionSet.csv")
+    CohortDiagnostics::executeDiagnostics(cohortDefinitionSet = cohortDefinitionSet,
                        connectionDetails = connectionDetails,
                        cohortTable = cohortTable,
                        cohortDatabaseSchema = cohortDatabaseSchema,
                        cdmDatabaseSchema = cdmDatabaseSchema,
-                       exportFolder = exportFolder,
-                       databaseId = "MyCdm",
-                       minCellCount = 5
-    )
-    CohortGenerator::dropCohortStatsTables(
-      connectionDetails = connectionDetails,
-      cohortDatabaseSchema = cohortDatabaseSchema,
-      cohortTableNames = cohortTableNames
+                       exportFolder = outputFolder,
+                       databaseId = databaseId,
+                       minCellCount = minCellCount
     )
   }
 }

README.md

@@ -1 +1,115 @@
-# EhdenAlopecia
+# EHDEN Alopecia
+
+Analytic software to perform large-scale distributed analysis of patients with Alopecia as part of the EHDEN study-athon
+
+<img src="https://img.shields.io/badge/Study%20Status-Started-blue.svg" alt="Study Status: Started">
+
+- Analytics use case(s): Population-Level Estimation
+- Study type: Clinical Application
+- Tags: -
+- Study lead: 
+- Study lead forums tag: 
+- Study start date: 1 November 2023
+- Study end date: -
+- Protocol: To be added
+- Publications: -
+- Results explorer: -
+
+# Requirements
+
+
+A database in Common Data Model version 5 in one of these platforms: SQL Server, Oracle, PostgreSQL, IBM Netezza, Apache Impala, Amazon RedShift, Google BigQuery, or Microsoft APS.
+R version 4.0.5
+On Windows: RTools
+Java
+100 GB of free disk space
+
+# How to run
+See the instructions at https://ohdsi.github.io/Hades/rSetup.html for configuring your R environment, including Java and RStudio.
+
+Clone the EhdenAlopecia package into your local R environment.
+
+Open your study package in RStudio. Use the following code to install all the dependencies:
+```R
+install.packages(c("DBI",
+    "dplyr",
+    "glue",
+    "zip",
+    "magrittr",
+    "checkmate",
+    "log4r",
+    "lubridate",
+    "rlang",
+    "readr")
+)
+```
+
+In RStudio, select 'Build' then 'Install and Restart' to install the  package.
+
+After succesfully installing the package. Open the extras/codeTorun.R and run the following code
+
+```R
+#Load the library
+
+library(EhdenAlopecia)
+# database metadata and connection details -----
+# The name/ acronym for the database
+databaseId <- ""
+
+# Database connection details -----
+#connection details
+#User specified input
+
+
+# Details for connecting to the server:
+dbms <- ""
+user <- ""
+pw <- ""
+server <- ""
+port <- ""
+
+connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = dbms,
+                                                                server = server,
+                                                                user = user,
+                                                                password = pw,
+                                                                port = port)
+
+
+cdmDatabaseSchema <- ""
+cohortDatabaseSchema <- ""
+
+
+# Name of table prefix to use in the result schema for tables created during the study.
+# Notes:
+# - if there is an existing table in your results schema with the same names it
+#   will be overwritten
+# - name must be lower case
+cohortTable <- "alopecia_ehden"
+
+
+# minimum counts that can be displayed according to data governance
+minCellCount <- 5
+
+#specify where to save the results
+outputFolder <- "results"
+
+
+#choose analysis to run
+instantiateCohorts <- TRUE
+runDiagnostics <- TRUE
+
+
+### Do not edit below here
+
+EhdenAlopecia::runStudy(
+  connectionDetails = connectionDetails, 
+  cohortTable = cohortTable, 
+  cdmDatabaseSchema = cdmDatabaseSchema, 
+  cohortDatabaseSchema = cohortDatabaseSchema,
+  instantiateCohorts = instantiateCohorts,
+  runDiagnostics = runDiagnostics,
+  outputFolder = outputFolder,
+  databaseId = databaseId,
+  minCellCount = minCellCount
+)
+```

extras/codeToRun.R

@@ -15,69 +15,83 @@
 # SECTION 1: Installing
 # *******************************************************
 #
-# 1. See the instructions at https://ohdsi.github.io/Hades/rSetup.html for configuring your R environment, including Java and RStudio.
-#
-# 2. In RStudio, create a new project by cloning https://github.com/darwin-eu-studies/P1C3001AsthmaBackgroundRates
-#
-# 3. Install renv package
-install.packages("renv")
-#
-# 4. Build the local library. This may take a while:
-renv::restore()
-#
-# 5. Build the R package in the Build menu  -> Install
+# See the instructions at https://ohdsi.github.io/Hades/rSetup.html for configuring your R environment, including Java and RStudio.
+# Follow these instructions for setting up your R environment, including RTools and Java.
+
+# Clone the EhdenAlopecia package into your local R environment.
+
+# Open your study package in RStudio. Use the following code to install all the dependencies:
+
+# In RStudio, select 'Build' then 'Install and Restart' to install the package.
+
+# After succesfully installing the package, run the following code
 
 # *******************************************************
 # SECTION 2: Running the package -------------------------------------------------------------------------------
 # *******************************************************
 #
 # Edit the variables below to the correct values for your environment:
 
+#Load the library
 
-# library(testthat)
-
+library(EhdenAlopecia)
 # database metadata and connection details -----
 # The name/ acronym for the database
-# IMPORTANT: to use names CPRD, IMASIS, IPCI, IQVIA_GERMANY_DA, SIDIAP for these databases.
-dbName <- " "
+databaseId <- ""
 
 # Database connection details -----
-# In this study we also use the DBI package to connect to the database
-# set up the dbConnect details below (see https://dbi.r-dbi.org/articles/dbi for
-# more details)
-# you may need to install another package for this
-# eg for postgres
-# conn <- dbConnect(
-#   RPostgres::Postgres(),
-#   dbname = server_dbi,
-#   port = port,
-#   host = host,
-#   user = user,
-#   password = password
-# )
-conn <- DBI::dbConnect("....")
-
-# The name of the schema that contains the OMOP CDM with patient-level data
-cdmDatabaseSchema <- "...."
-
-# The name of the schema where results tables will be created
-resultsDatabaseSchema <- "...."
+#connection details
+#User specified input
+
+
+# Details for connecting to the server:
+dbms <- ""
+user <- ""
+pw <- ""
+server <- ""
+port <- ""
+
+connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = dbms,
+                                                                server = server,
+                                                                user = user,
+                                                                password = pw,
+                                                                port = port)
+
+
+cdmDatabaseSchema <- ""
+cohortDatabaseSchema <- ""
+
 
 # Name of table prefix to use in the result schema for tables created during the study.
 # Notes:
 # - if there is an existing table in your results schema with the same names it
 #   will be overwritten
 # - name must be lower case
-tablePrefix <- ""
+cohortTable <- "alopecia_ehden"
+
 
 # minimum counts that can be displayed according to data governance
-minimumCounts <- 5
+minCellCount <- 5
+
+#specify where to save the results
+outputFolder <- "results"
+
 
+#choose analysis to run
 instantiateCohorts <- TRUE
-runDiagnostics <- FALSE
+runDiagnostics <- TRUE
+
+
+### Do not edit below here
 
-runStudy(connectionDetails, 
-         cohortTable, 
-         cdmDatabaseSchema, 
-         cohortDatabaseSchema,
-         instantiateCohorts)
+EhdenAlopecia::runStudy(
+  connectionDetails = connectionDetails, 
+  cohortTable = cohortTable, 
+  cdmDatabaseSchema = cdmDatabaseSchema, 
+  cohortDatabaseSchema = cohortDatabaseSchema,
+  instantiateCohorts = instantiateCohorts,
+  runDiagnostics = runDiagnostics,
+  outputFolder = outputFolder,
+  databaseId = databaseId,
+  minCellCount = minCellCount
+)