Summarise patient characteristics

library(CDMConnector)
library(CodelistGenerator)
library(CohortCharacteristics)
library(dplyr)
library(ggplot2)

con <- DBI::dbConnect(duckdb::duckdb(),
  dbdir = CDMConnector::eunomia_dir()
)
cdm <- CDMConnector::cdm_from_con(con,
  cdm_schem = "main",
  write_schema = "main",
  cdm_name = "Eunomia"
)

cdm <- generateConceptCohortSet(
  cdm = cdm,
  name = "injuries",
  conceptSet = list(
    "ankle_sprain" = 81151,
    "ankle_fracture" = 4059173,
    "forearm_fracture" = 4278672,
    "hip_fracture" = 4230399
  ),
  end = "event_end_date",
  limit = "all"
)
settings(cdm$injuries)
#> # A tibble: 4 × 6
#>   cohort_definition_id cohort_name    limit prior_observation future_observation
#>                  <int> <chr>          <chr>             <dbl>              <dbl>
#> 1                    1 ankle_sprain   all                   0                  0
#> 2                    2 ankle_fracture all                   0                  0
#> 3                    3 forearm_fract… all                   0                  0
#> 4                    4 hip_fracture   all                   0                  0
#> # ℹ 1 more variable: end <chr>
cohortCount(cdm$injuries)
#> # A tibble: 4 × 3
#>   cohort_definition_id number_records number_subjects
#>                  <int>          <int>           <int>
#> 1                    1           1915            1357
#> 2                    2            464             427
#> 3                    3            569             510
#> 4                    4            138             132

chars <- cdm$injuries |>
  summariseCharacteristics(ageGroup = list(c(0, 49), c(50, Inf)))
chars |>
  glimpse()
#> Rows: 164
#> Columns: 13
#> $ result_id        <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name         <chr> "Eunomia", "Eunomia", "Eunomia", "Eunomia", "Eunomia"…
#> $ group_name       <chr> "cohort_name", "cohort_name", "cohort_name", "cohort_…
#> $ group_level      <chr> "ankle_sprain", "ankle_fracture", "forearm_fracture",…
#> $ strata_name      <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level     <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name    <chr> "Number records", "Number records", "Number records",…
#> $ variable_level   <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
#> $ estimate_name    <chr> "count", "count", "count", "count", "count", "count",…
#> $ estimate_type    <chr> "integer", "integer", "integer", "integer", "integer"…
#> $ estimate_value   <chr> "1915", "464", "569", "138", "1357", "427", "510", "1…
#> $ additional_name  <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ additional_level <chr> "overall", "overall", "overall", "overall", "overall"…

tableCharacteristics(chars)

chars |>
  filter(variable_name == "Age") |>
  plotCharacteristics(
    plotStyle = "boxplot",
    colour = "group_level",
    x = "group_level",
    facet = c("cdm_name")
  )

chars <- cdm$injuries |>
  PatientProfiles::addAge(ageGroup = list(
    c(0, 49),
    c(50, Inf)
  )) |>
  summariseCharacteristics(strata = list("age_group"))

tableCharacteristics(chars,
  groupColumn = "age_group"
)

chars |>
  filter(variable_name == "Prior observation") |>
  plotCharacteristics(
    plotStyle = "boxplot",
    colour = "group_level",
    x = "group_level",
    facet = c("strata_level")
  ) +
  coord_flip()

meds_cs <- getDrugIngredientCodes(
  cdm = cdm,
  name = c(
    "acetaminophen",
    "morphine",
    "warfarin"
  )
)
cdm <- generateConceptCohortSet(
  cdm = cdm,
  name = "meds",
  conceptSet = meds_cs,
  end = "event_end_date",
  limit = "all",
  overwrite = TRUE
)

chars <- cdm$injuries |>
  summariseCharacteristics(cohortIntersectFlag = list(
    "Medications prior to index date" = list(
      targetCohortTable = "meds",
      window = c(-Inf, -1)
    ),
    "Medications on index date" = list(
      targetCohortTable = "meds",
      window = c(0, 0)
    )
  ))

tableCharacteristics(chars)

plot_data <- chars |>
  filter(
    variable_name == "Medications prior to index date",
    estimate_name == "percentage"
  )

plot_data |>
  plotCharacteristics(
    plotStyle = "barplot",
    colour = "variable_level",
    x = "variable_level",
    facet = c(
      "cdm_name",
      "group_level"
    )
  ) +
  scale_x_discrete(limits = rev(sort(unique(plot_data$variable_level)))) +
  coord_flip() +
  ggtitle("Medication use prior to index date")

chars <- cdm$injuries |>
  summariseCharacteristics(conceptIntersectFlag = list(
    "Medications prior to index date" = list(
      conceptSet = meds_cs,
      window = c(-Inf, -1)
    ),
    "Medications on index date" = list(
      conceptSet = meds_cs,
      window = c(0, 0)
    )
  ))

tableCharacteristics(chars)

chars <- cdm$injuries |>
  summariseCharacteristics(
    tableIntersectCount = list(
      "Visits in the year prior" = list(
        tableName = "visit_occurrence",
        window = c(-365, -1)
      )
    ),
    tableIntersectFlag = list(
      "Any drug exposure in the year prior" = list(
        tableName = "drug_exposure",
        window = c(-365, -1)
      ),
      "Any procedure in the year prior" = list(
        tableName = "procedure_occurrence",
        window = c(-365, -1)
      )
    )
  )

tableCharacteristics(chars)