OHDSI/Arachne

Cohort Diagnostics strategus json execution fails

ablack3 opened this issue · 2 comments

ablack3 commented

I tried running cohort diagnostics using strategus and the execution failed.

Steps to reproduce the issue.

Generate the cohort diagnostics json specification with this R code

remotes::install_github("ohdsi/Strategus") # install the current release of Strategus
#> Skipping install of 'Strategus' from a github remote, the SHA1 (612859f3) has not changed since last install.
#>   Use `force = TRUE` to force installation

library(Strategus)
#> Loading required package: CohortGenerator
#> Loading required package: DatabaseConnector
#> Loading required package: R6
#> 
#> Attaching package: 'Strategus'
#> The following object is masked from 'package:CohortGenerator':
#> 
#>     uploadResults

cohortDefinitionSet <- CohortGenerator::getCohortDefinitionSet(
    settingsFileName = "testdata/Cohorts.csv",
    jsonFolder = "testdata/cohorts",
    sqlFolder = "testdata/sql",
    packageName = "Strategus"
)
#> Loading cohortDefinitionSet

ncoCohortSet <- CohortGenerator::readCsv(file = system.file("testdata/negative_controls_concept_set.csv",
                                                            package = "Strategus"
))

cgModule <- CohortGeneratorModule$new()

cohortDefinitionSharedResource <- cgModule$createCohortSharedResourceSpecifications(
    cohortDefinitionSet = cohortDefinitionSet
)


cohortGeneratorModuleSpecifications <- cgModule$createModuleSpecifications(
    generateStats = TRUE
)

cdModule <- CohortDiagnosticsModule$new()

cohortDiagnosticsModuleSpecifications <- cdModule$createModuleSpecifications(
    runInclusionStatistics = TRUE,
    runIncludedSourceConcepts = TRUE,
    runOrphanConcepts = TRUE,
    runTimeSeries = FALSE,
    runVisitContext = TRUE,
    runBreakdownIndexEvents = TRUE,
    runIncidenceRate = TRUE,
    runCohortRelationship = TRUE,
    runTemporalCohortCharacterization = TRUE
)

analysisSpecifications <- createEmptyAnalysisSpecificiations() |>
    addSharedResources(cohortDefinitionSharedResource) |>
    addModuleSpecifications(cohortGeneratorModuleSpecifications) |>
    addModuleSpecifications(cohortDiagnosticsModuleSpecifications) 

ParallelLogger::saveSettingsToJson(analysisSpecifications, "cohortDiagnosticsAnalysis.json")

Created on 2024-11-09 with reprex v2.1.1

The json this code generates is below:

{
  "sharedResources": [
    {
      "cohortDefinitions": [
        {
          "cohortId": 1,
          "cohortName": "Celecoxib",
          "cohortDefinition": "{\n\t\"cdmVersionRange\" : \">=5.0.0\",\n\t\"PrimaryCriteria\" : {\n\t\t\"CriteriaList\" : [\n\t\t\t{\n\t\t\t\t\"DrugEra\" : {\n\t\t\t\t\t\"CodesetId\" : 0\n\t\t\t\t}\n\t\t\t}\n\t\t],\n\t\t\"ObservationWindow\" : {\n\t\t\t\"PriorDays\" : 0,\n\t\t\t\"PostDays\" : 0\n\t\t},\n\t\t\"PrimaryCriteriaLimit\" : {\n\t\t\t\"Type\" : \"First\"\n\t\t}\n\t},\n\t\"ConceptSets\" : [\n\t\t{\n\t\t\t\"id\" : 0,\n\t\t\t\"name\" : \"Celecoxib\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"items\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"concept\" : {\n\t\t\t\t\t\t\t\"CONCEPT_ID\" : 1118084,\n\t\t\t\t\t\t\t\"CONCEPT_NAME\" : \"celecoxib\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT\" : \"S\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT_CAPTION\" : \"Standard\",\n\t\t\t\t\t\t\t\"INVALID_REASON\" : \"V\",\n\t\t\t\t\t\t\t\"INVALID_REASON_CAPTION\" : \"Valid\",\n\t\t\t\t\t\t\t\"CONCEPT_CODE\" : \"140587\",\n\t\t\t\t\t\t\t\"DOMAIN_ID\" : \"Drug\",\n\t\t\t\t\t\t\t\"VOCABULARY_ID\" : \"RxNorm\",\n\t\t\t\t\t\t\t\"CONCEPT_CLASS_ID\" : \"Ingredient\"\n\t\t\t\t\t\t},\n\t\t\t\t\t\t\"isExcluded\" : false,\n\t\t\t\t\t\t\"includeDescendants\" : false,\n\t\t\t\t\t\t\"includeMapped\" : false\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t}\n\t],\n\t\"QualifiedLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"ExpressionLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"InclusionRules\" : [],\n\t\"EndStrategy\" : {\n\t\t\"CustomEra\" : {\n\t\t\t\"DrugCodesetId\" : 0,\n\t\t\t\"GapDays\" : 30,\n\t\t\t\"Offset\" : 0\n\t\t}\n\t},\n\t\"CensoringCriteria\" : [],\n\t\"CollapseSettings\" : {\n\t\t\"CollapseType\" : \"ERA\",\n\t\t\"EraPad\" : 0\n\t},\n\t\"CensorWindow\" : {}\n}"
        },
        {
          "cohortId": 2,
          "cohortName": "Diclofenac",
          "cohortDefinition": "{\n\t\"cdmVersionRange\" : \">=5.0.0\",\n\t\"PrimaryCriteria\" : {\n\t\t\"CriteriaList\" : [\n\t\t\t{\n\t\t\t\t\"DrugEra\" : {\n\t\t\t\t\t\"CodesetId\" : 0\n\t\t\t\t}\n\t\t\t}\n\t\t],\n\t\t\"ObservationWindow\" : {\n\t\t\t\"PriorDays\" : 0,\n\t\t\t\"PostDays\" : 0\n\t\t},\n\t\t\"PrimaryCriteriaLimit\" : {\n\t\t\t\"Type\" : \"First\"\n\t\t}\n\t},\n\t\"ConceptSets\" : [\n\t\t{\n\t\t\t\"id\" : 0,\n\t\t\t\"name\" : \"Diclofenac\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"items\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"concept\" : {\n\t\t\t\t\t\t\t\"CONCEPT_ID\" : 1124300,\n\t\t\t\t\t\t\t\"CONCEPT_NAME\" : \"diclofenac\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT\" : \"S\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT_CAPTION\" : \"Standard\",\n\t\t\t\t\t\t\t\"INVALID_REASON\" : \"V\",\n\t\t\t\t\t\t\t\"INVALID_REASON_CAPTION\" : \"Valid\",\n\t\t\t\t\t\t\t\"CONCEPT_CODE\" : \"3355\",\n\t\t\t\t\t\t\t\"DOMAIN_ID\" : \"Drug\",\n\t\t\t\t\t\t\t\"VOCABULARY_ID\" : \"RxNorm\",\n\t\t\t\t\t\t\t\"CONCEPT_CLASS_ID\" : \"Ingredient\"\n\t\t\t\t\t\t},\n\t\t\t\t\t\t\"isExcluded\" : false,\n\t\t\t\t\t\t\"includeDescendants\" : false,\n\t\t\t\t\t\t\"includeMapped\" : false\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t}\n\t],\n\t\"QualifiedLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"ExpressionLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"InclusionRules\" : [],\n\t\"EndStrategy\" : {\n\t\t\"CustomEra\" : {\n\t\t\t\"DrugCodesetId\" : 0,\n\t\t\t\"GapDays\" : 30,\n\t\t\t\"Offset\" : 0\n\t\t}\n\t},\n\t\"CensoringCriteria\" : [],\n\t\"CollapseSettings\" : {\n\t\t\"CollapseType\" : \"ERA\",\n\t\t\"EraPad\" : 0\n\t},\n\t\"CensorWindow\" : {}\n}"
        },
        {
          "cohortId": 3,
          "cohortName": "GI bleed",
          "cohortDefinition": "{\n\t\"cdmVersionRange\" : \">=5.0.0\",\n\t\"PrimaryCriteria\" : {\n\t\t\"CriteriaList\" : [\n\t\t\t{\n\t\t\t\t\"ConditionOccurrence\" : {\n\t\t\t\t\t\"CodesetId\" : 0,\n\t\t\t\t\t\"ConditionTypeExclude\" : false\n\t\t\t\t}\n\t\t\t}\n\t\t],\n\t\t\"ObservationWindow\" : {\n\t\t\t\"PriorDays\" : 0,\n\t\t\t\"PostDays\" : 0\n\t\t},\n\t\t\"PrimaryCriteriaLimit\" : {\n\t\t\t\"Type\" : \"All\"\n\t\t}\n\t},\n\t\"ConceptSets\" : [\n\t\t{\n\t\t\t\"id\" : 0,\n\t\t\t\"name\" : \"GI bleed\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"items\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"concept\" : {\n\t\t\t\t\t\t\t\"CONCEPT_ID\" : 192671,\n\t\t\t\t\t\t\t\"CONCEPT_NAME\" : \"Gastrointestinal hemorrhage\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT\" : \"S\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT_CAPTION\" : \"Standard\",\n\t\t\t\t\t\t\t\"INVALID_REASON\" : \"V\",\n\t\t\t\t\t\t\t\"INVALID_REASON_CAPTION\" : \"Valid\",\n\t\t\t\t\t\t\t\"CONCEPT_CODE\" : \"74474003\",\n\t\t\t\t\t\t\t\"DOMAIN_ID\" : \"Condition\",\n\t\t\t\t\t\t\t\"VOCABULARY_ID\" : \"SNOMED\",\n\t\t\t\t\t\t\t\"CONCEPT_CLASS_ID\" : \"Clinical Finding\"\n\t\t\t\t\t\t},\n\t\t\t\t\t\t\"isExcluded\" : false,\n\t\t\t\t\t\t\"includeDescendants\" : true,\n\t\t\t\t\t\t\"includeMapped\" : false\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t}\n\t],\n\t\"QualifiedLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"ExpressionLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"InclusionRules\" : [],\n\t\"EndStrategy\" : {\n\t\t\"DateOffset\" : {\n\t\t\t\"DateField\" : \"StartDate\",\n\t\t\t\"Offset\" : 0\n\t\t}\n\t},\n\t\"CensoringCriteria\" : [],\n\t\"CollapseSettings\" : {\n\t\t\"CollapseType\" : \"ERA\",\n\t\t\"EraPad\" : 0\n\t},\n\t\"CensorWindow\" : {}\n}"
        },
        {
          "cohortId": 4,
          "cohortName": "Celecoxib age 30 or older",
          "cohortDefinition": "{\n\t\"cdmVersionRange\" : \">=5.0.0\",\n\t\"PrimaryCriteria\" : {\n\t\t\"CriteriaList\" : [\n\t\t\t{\n\t\t\t\t\"DrugEra\" : {\n\t\t\t\t\t\"CodesetId\" : 0\n\t\t\t\t}\n\t\t\t}\n\t\t],\n\t\t\"ObservationWindow\" : {\n\t\t\t\"PriorDays\" : 0,\n\t\t\t\"PostDays\" : 0\n\t\t},\n\t\t\"PrimaryCriteriaLimit\" : {\n\t\t\t\"Type\" : \"First\"\n\t\t}\n\t},\n\t\"ConceptSets\" : [\n\t\t{\n\t\t\t\"id\" : 0,\n\t\t\t\"name\" : \"Celecoxib\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"items\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"concept\" : {\n\t\t\t\t\t\t\t\"CONCEPT_ID\" : 1118084,\n\t\t\t\t\t\t\t\"CONCEPT_NAME\" : \"celecoxib\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT\" : \"S\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT_CAPTION\" : \"Standard\",\n\t\t\t\t\t\t\t\"INVALID_REASON\" : \"V\",\n\t\t\t\t\t\t\t\"INVALID_REASON_CAPTION\" : \"Valid\",\n\t\t\t\t\t\t\t\"CONCEPT_CODE\" : \"140587\",\n\t\t\t\t\t\t\t\"DOMAIN_ID\" : \"Drug\",\n\t\t\t\t\t\t\t\"VOCABULARY_ID\" : \"RxNorm\",\n\t\t\t\t\t\t\t\"CONCEPT_CLASS_ID\" : \"Ingredient\"\n\t\t\t\t\t\t},\n\t\t\t\t\t\t\"isExcluded\" : false,\n\t\t\t\t\t\t\"includeDescendants\" : false,\n\t\t\t\t\t\t\"includeMapped\" : false\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t}\n\t],\n\t\"QualifiedLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"ExpressionLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"InclusionRules\" : [\n\t\t{\n\t\t\t\"name\" : \"Age >= 30\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"Type\" : \"ALL\",\n\t\t\t\t\"CriteriaList\" : [],\n\t\t\t\t\"DemographicCriteriaList\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"Age\" : {\n\t\t\t\t\t\t\t\"Value\" : 30,\n\t\t\t\t\t\t\t\"Op\" : \"gte\"\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t],\n\t\t\t\t\"Groups\" : []\n\t\t\t}\n\t\t}\n\t],\n\t\"EndStrategy\" : {\n\t\t\"CustomEra\" : {\n\t\t\t\"DrugCodesetId\" : 0,\n\t\t\t\"GapDays\" : 30,\n\t\t\t\"Offset\" : 0\n\t\t}\n\t},\n\t\"CensoringCriteria\" : [],\n\t\"CollapseSettings\" : {\n\t\t\"CollapseType\" : \"ERA\",\n\t\t\"EraPad\" : 0\n\t},\n\t\"CensorWindow\" : {}\n}"
        },
        {
          "cohortId": 5,
          "cohortName": "Diclofenac age 30 or older",
          "cohortDefinition": "{\n\t\"cdmVersionRange\" : \">=5.0.0\",\n\t\"PrimaryCriteria\" : {\n\t\t\"CriteriaList\" : [\n\t\t\t{\n\t\t\t\t\"DrugEra\" : {\n\t\t\t\t\t\"CodesetId\" : 0\n\t\t\t\t}\n\t\t\t}\n\t\t],\n\t\t\"ObservationWindow\" : {\n\t\t\t\"PriorDays\" : 0,\n\t\t\t\"PostDays\" : 0\n\t\t},\n\t\t\"PrimaryCriteriaLimit\" : {\n\t\t\t\"Type\" : \"First\"\n\t\t}\n\t},\n\t\"ConceptSets\" : [\n\t\t{\n\t\t\t\"id\" : 0,\n\t\t\t\"name\" : \"Diclofenac\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"items\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"concept\" : {\n\t\t\t\t\t\t\t\"CONCEPT_ID\" : 1124300,\n\t\t\t\t\t\t\t\"CONCEPT_NAME\" : \"diclofenac\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT\" : \"S\",\n\t\t\t\t\t\t\t\"STANDARD_CONCEPT_CAPTION\" : \"Standard\",\n\t\t\t\t\t\t\t\"INVALID_REASON\" : \"V\",\n\t\t\t\t\t\t\t\"INVALID_REASON_CAPTION\" : \"Valid\",\n\t\t\t\t\t\t\t\"CONCEPT_CODE\" : \"3355\",\n\t\t\t\t\t\t\t\"DOMAIN_ID\" : \"Drug\",\n\t\t\t\t\t\t\t\"VOCABULARY_ID\" : \"RxNorm\",\n\t\t\t\t\t\t\t\"CONCEPT_CLASS_ID\" : \"Ingredient\"\n\t\t\t\t\t\t},\n\t\t\t\t\t\t\"isExcluded\" : false,\n\t\t\t\t\t\t\"includeDescendants\" : false,\n\t\t\t\t\t\t\"includeMapped\" : false\n\t\t\t\t\t}\n\t\t\t\t]\n\t\t\t}\n\t\t}\n\t],\n\t\"QualifiedLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"ExpressionLimit\" : {\n\t\t\"Type\" : \"First\"\n\t},\n\t\"InclusionRules\" : [\n\t\t{\n\t\t\t\"name\" : \"Age >= 30\",\n\t\t\t\"expression\" : {\n\t\t\t\t\"Type\" : \"ALL\",\n\t\t\t\t\"CriteriaList\" : [],\n\t\t\t\t\"DemographicCriteriaList\" : [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"Age\" : {\n\t\t\t\t\t\t\t\"Value\" : 30,\n\t\t\t\t\t\t\t\"Op\" : \"gte\"\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t],\n\t\t\t\t\"Groups\" : []\n\t\t\t}\n\t\t}\n\t],\n\t\"EndStrategy\" : {\n\t\t\"CustomEra\" : {\n\t\t\t\"DrugCodesetId\" : 0,\n\t\t\t\"GapDays\" : 30,\n\t\t\t\"Offset\" : 0\n\t\t}\n\t},\n\t\"CensoringCriteria\" : [],\n\t\"CollapseSettings\" : {\n\t\t\"CollapseType\" : \"ERA\",\n\t\t\"EraPad\" : 0\n\t},\n\t\"CensorWindow\" : {}\n}"
        }
      ],
      "attr_class": ["CohortDefinitionSharedResources", "SharedResources"]
    }
  ],
  "moduleSpecifications": [
    {
      "module": "CohortGeneratorModule",
      "settings": {
        "generateStats": true
      },
      "attr_class": ["ModuleSpecifications", "CohortGeneratorModuleSpecifications"]
    },
    {
      "module": "CohortDiagnosticsModule",
      "settings": {
        "runInclusionStatistics": true,
        "runIncludedSourceConcepts": true,
        "runOrphanConcepts": true,
        "runTimeSeries": false,
        "runVisitContext": true,
        "runBreakdownIndexEvents": true,
        "runIncidenceRate": true,
        "runCohortRelationship": true,
        "runTemporalCohortCharacterization": true,
        "temporalCovariateSettings": {
          "temporal": true,
          "temporalSequence": false,
          "DemographicsGender": true,
          "DemographicsAge": true,
          "DemographicsAgeGroup": true,
          "DemographicsRace": true,
          "DemographicsEthnicity": true,
          "DemographicsIndexYear": true,
          "DemographicsIndexMonth": true,
          "DemographicsPriorObservationTime": true,
          "DemographicsPostObservationTime": true,
          "DemographicsTimeInCohort": true,
          "DemographicsIndexYearMonth": true,
          "ConditionOccurrence": true,
          "ConditionEraStart": true,
          "ConditionEraOverlap": true,
          "ConditionEraGroupOverlap": true,
          "DrugEraStart": true,
          "DrugEraGroupOverlap": true,
          "ProcedureOccurrence": true,
          "DeviceExposure": true,
          "Measurement": true,
          "Observation": true,
          "CharlsonIndex": true,
          "Dcsi": true,
          "Chads2": true,
          "Chads2Vasc": true,
          "temporalStartDays": [-9999, -365, -180, -30, -365, -30, 0, 1, 31, -9999],
          "temporalEndDays": [0, 0, 0, 0, -31, -1, 0, 30, 365, 9999],
          "includedCovariateConceptIds": [],
          "addDescendantsToInclude": false,
          "excludedCovariateConceptIds": [],
          "addDescendantsToExclude": false,
          "includedCovariateIds": [],
          "attr_class": "covariateSettings",
          "attr_fun": "getDbDefaultCovariateData"
        },
        "minCharacterizationMean": 0.01,
        "irWashoutPeriod": 0
      },
      "attr_class": ["ModuleSpecifications", "CohortDiagnosticsModuleSpecifications"]
    }
  ],
  "attr_class": "AnalysisSpecifications"
}

Then I uploaded this json file to https://testnodestandalone.arachnenetwork.com/
image

image

Do we need a docker image with Strategus installed?
tagging @anthonysena, @konstjar

konstjar commented

@ablack3 Thank you for this example and details. Yes, we do not have yet ready R environment image for Strategus v1.0
We have this ticket opened #84 and targeted for November release.

  • 👍1
anthonysena commented

@konstjar @ablack3 I'd recommend that for the next R environment for Strategus that you look at the new repository template that is now available on https://github.com/ohdsi-studies/StrategusStudyRepoTemplate. This is using the latest HADES-wide lock file and will work best with R 4.4.1. The renv.lock file contains the dependencies, including those needed for PLP via Python.

The documentation is here: https://github.com/ohdsi-studies/StrategusStudyRepoTemplate/blob/main/template_docs/UsingThisTemplate.md. Feel free to reach out with any questions/concerns.

  • 👍1