Dev (#38)

* Fix three bugs in feasibility assessment workflow (#34) * Hotfix conn variable * Fix the issue with site_path and paste() * Add missing schema variable to table name * Characterization Analysis Tutorial (#37) * Simplified phenotype definition generation * DVC controlled initial phenotype definition information * Initial draft of the characterization scheme * Cleaned up repository of misc files * Added todo for README for the future * Added additional todos for characterization work * Completed to-dos for database connections and queries * Added todos and did initial review * Completed todos and added set-up and testing documents * Tweaking tutorial to better accommodate Julia packages * Removed Julia installation instructions * Added OHDSI HADES packages * Placeholder for baseline directory * Get patients who match a condition set * Query patients to get their age, race, and gender * Overhaul of characterization script to only require HADES and SQL * Updated baseline characterization scheme * Updated instructions to the README --------- Co-authored-by: TheCedarPrince <[email protected]> * Updated for release of v0.1.0 of package * Updated for release of v0.1.0 of package --------- Co-authored-by: Kyle Zollo <[email protected]> Co-authored-by: malinahy <[email protected]>
ohdsi-studies · Feb 28, 2023 · 1202414 · 1202414
1 parent 8a231a0
commit 1202414
Show file tree

Hide file tree

Showing 24 changed files with 2,015 additions and 1,146 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,7 +5,28 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
-## [0.0.2] - January 23rd, 2022
+## [0.1.0] - February 28th, 2023 
+
+New minor release for package to execute baseline characterizations 
+
+### Added  
+
+- Characterization script added
+- Instructions for characterization script
+- Queries to run for characterization
+- `renv` environment management
+- `Rprofile` for RStudio work
+
+### Changed 
+
+- Directory for data now includes a `baseline` folder 
+- `study` now includes in progress `test` scripts 
+
+### Fixed 
+
+- Numerous issues opened by @kzollove (thank you!)
+
+## [0.0.2] - January 23rd, 2023
 
 Patch release of MentalHealthEquity package for small updates and compliance
 

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: MentalHealthEquity
 Title: Assessing Health Equity in Mental Healthcare Delivery Using a
     Federated Network Research Model
-Version: 0.0.2
+Version: 0.1.0
 Authors@R: 
     person("Jacob", "Zelko", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0003-4531-1614"))

diff --git a/_scripts/conceptDefinitions.R b/_scripts/conceptDefinitions.R
diff --git a/_scripts/description_updater.R b/_scripts/description_updater.R
@@ -8,7 +8,7 @@ usethis.description <- list(
         Language = "en",
 	Package = "MentalHealthEquity",
 	Title = "Assessing Health Equity in Mental Healthcare Delivery Using a Federated Network Research Model",
-	Version = "0.0.2",
+	Version = "0.1.0",
 	Description = "This is a network research package which assesses health disparities in populations with chronic mental illness. There are two components in this package: a feasibility component (to assess site feasibility) and a study component (to generate statistics of interest at each site)."
 )
 

diff --git a/study/R/atlasUtilities.R → _scripts/phenotype_definition_generator.R b/study/R/atlasUtilities.R → _scripts/phenotype_definition_generator.R
@@ -99,3 +99,29 @@ get_atlas_concept_set <- function(filename) {
   concept_set_df <- do.call(rbind, cohort_list)
   return(concept_set_df)
 }
+
+# Getting concept sets for condition using concept ID and writing to json file
+bipolar_id <- 436665
+depression_id <- 440383
+suicidality_id <- 4273391
+
+ids <- c(bipolar_id, depression_id, suicidality_id)
+names <- c("bipolar", "depression", "suicidality")
+
+base_filename <- "data/concept_sets/"
+
+# Output condition concept set JSON file paths
+condition_paths <- paste0(base_filename, names, "_computable_phenotype_definition.csv")
+
+# Write condition concept set JSON representation to files
+condition_json <- lapply(ids, FUN = get_atlas_concept)
+mapply(FUN = write, condition_json, condition_paths)
+
+# Output condition concept set CSV file paths
+concept_paths <- paste0(base_filename, names, "_concept_set.csv")
+concept_sets <- lapply(condition_paths, FUN = get_atlas_concept_set)
+
+# Write concepts from concept set to CSV
+for (i in 1:length(concept_paths)) {
+  write.csv(concept_sets[[i]], concept_paths[[i]])
+}
diff --git a/data/baseline/placeholder b/data/baseline/placeholder
diff --git a/feasibility/feasibility_assessment_instructions.Rmd b/feasibility/feasibility_assessment_instructions.Rmd
@@ -133,8 +133,8 @@ And here is the code block needed to update:
 ```{r, eval = FALSE}
 site_name <- "Fill in here"
 
-site_path <- paste("../data/", site_name, sep = ""), row.names = FALSE
-dir.create(path = site_name)
+site_path <- paste("../data/", site_name, sep = "")
+dir.create(path = site_path)
 ```
 
 #### Stratified Person Query 

diff --git a/feasibility/sql/state_person.R b/feasibility/sql/state_person.R
@@ -7,7 +7,7 @@ FROM (
     "LOCATION_1"."state"
   FROM @schema.location AS "LOCATION_1"
 ) AS "LOCATION_2"
-JOIN person AS "PERSON_1" ON ("LOCATION_2"."location_id" = "PERSON_1"."location_id")
+JOIN @schema.person AS "PERSON_1" ON ("LOCATION_2"."location_id" = "PERSON_1"."location_id")
 GROUP BY "LOCATION_2".state;', schema = schema)
 location_sql <- translate(sql = location_sql, targetDialect = dbms)
 

diff --git a/feasibility/tests/test_environment.R b/feasibility/tests/test_environment.R
@@ -55,7 +55,7 @@ test_that("Running query", {
 # Testing feasibility assessment queries
 ##############################################################
 
-connection <- DatabaseConnector::connect(eunomia_details)
+conn <- DatabaseConnector::connect(eunomia_details)
 
 schema <- "main"
 dbms <- "sqlite"

diff --git a/phenotypes/bipolar_computable_phenotype_definition.json b/phenotypes/bipolar_computable_phenotype_definition.json
@@ -0,0 +1,23 @@
+{
+  "items": [
+    {
+      "concept": {
+        "CONCEPT_ID": 436665,
+        "CONCEPT_NAME": "Bipolar disorder",
+        "STANDARD_CONCEPT": "S",
+        "STANDARD_CONCEPT_CAPTION": "Standard",
+        "INVALID_REASON": "V",
+        "INVALID_REASON_CAPTION": "Valid",
+        "CONCEPT_CODE": "13746004",
+        "DOMAIN_ID": "Condition",
+        "VOCABULARY_ID": "SNOMED",
+        "CONCEPT_CLASS_ID": "Clinical Finding",
+        "VALID_START_DATE": 1012435200000,
+        "VALID_END_DATE": 4102358400000
+      },
+      "isExcluded": false,
+      "includeDescendants": true,
+      "includeMapped": true
+    }
+  ]
+}