inst/doc/a01_extraction.R

In syrona: Stratified Prevalence Comparison Across OMOP CDM Datasets

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

## ----eval=FALSE---------------------------------------------------------------
# library(syrona)
# 
# # Direct connection
# db <- syrona_connect_pg(
#   host = "db-server.example.com",
#   dbname = "omop",
#   user = "analyst",
#   cdm_schema = "cdm",
#   write_schema = "results_analyst"
# )
# 
# # Via SSH tunnel (start tunnel first: ssh -L 5432:localhost:5432 user@server)
# db <- syrona_connect_pg(
#   host = "localhost",
#   dbname = "omop",
#   user = "analyst",
#   cdm_schema = "ohdsi_cdm_202511",
#   write_schema = "results_analyst"
# )

## ----eval=FALSE---------------------------------------------------------------
# # Read-only (default) - safe for shared databases
# db <- syrona_connect("path/to/omop.duckdb")
# 
# # Writable - needed if you want to create cohort tables in the same DB
# db <- syrona_connect("path/to/omop.duckdb", read_only = FALSE)

## ----eval=FALSE---------------------------------------------------------------
# tables <- extract_all("Dataset_A", db = db)

## ----eval=FALSE---------------------------------------------------------------
# # Conditions only (fastest)
# tables <- extract_all("Dataset_A", db = db, domains = "conditions")
# 
# # Drugs only
# tables <- extract_all("Dataset_A", db = db, domains = "drugs")
# 
# # Conditions + procedures (no drugs)
# tables <- extract_all("Dataset_A", db = db, domains = c("conditions", "procedures"))

## ----eval=FALSE---------------------------------------------------------------
# # This connects, extracts, and disconnects automatically
# tables <- extract_all("Synthetic", db = "path/to/omop.duckdb")

## ----eval=FALSE---------------------------------------------------------------
# # List all extracted datasets
# list_datasets()
# #> [1] "Dataset_A" "Dataset_B" "Synthetic"
# 
# # Load a previously extracted dataset
# d <- load_dataset("Dataset_A")
# names(d)
# #> [1] "condition_prevalence" "condition_info" "condition_chapters" ...

## ----eval=FALSE---------------------------------------------------------------
# syrona_disconnect(db)