Add bundle_gas: Group A Strep across Epic Cosmos, NNDSS, and ABCs

data/abcs_gas/README.md

@@ -0,0 +1,15 @@
+# abcs_gas
+
+This is a dcf data source project, initialized with `dcf::dcf_add_source`.
+
+You can us the `dcf` package to check the project:
+
+```R
+dcf_check_source("abcs_gas", "..")
+```
+
+And process it:
+
+```R
+dcf_process("abcs_gas", "..")
+```

data/abcs_gas/ingest.R

@@ -0,0 +1,193 @@
+# =============================================================================
+# ABCs Group A Streptococcus Data Ingestion
+# Source: https://data.cdc.gov/Public-Health-Surveillance/Active-Bacterial-Core-surveillance-ABCs-Group-A-St/9y49-tura/about_data
+# =============================================================================
+
+library(dplyr)
+
+process <- dcf::dcf_process_record()
+
+raw_state <- dcf::dcf_download_cdc(
+  "9y49-tura",
+  "raw",
+  process$raw_state
+)
+
+if (!identical(process$raw_state, raw_state)) {
+
+  data_raw <- vroom::vroom("raw/9y49-tura.csv.xz", show_col_types = FALSE) %>%
+    rename(
+      year    = Year,
+      value   = Value,
+      units   = Units,
+      bacteria = Bacteria,
+      topic   = Topic,
+      viewby  = ViewBy,
+      viewby2 = ViewBy2
+    ) %>%
+    mutate(
+      # Normalize casing inconsistencies across years
+      topic = case_when(
+        tolower(trimws(topic)) == "case rates"                    ~ "Case rates",
+        tolower(trimws(topic)) == "death rates"                   ~ "Death rates",
+        tolower(trimws(topic)) == "number of cases and deaths"    ~ "Number of cases and deaths",
+        tolower(trimws(topic)) == "syndromes"                     ~ "Syndromes",
+        tolower(trimws(topic)) == "antibiotic resistance"         ~ "Antibiotic resistance",
+        tolower(trimws(topic)) %in% c("emm types", "emm types")  ~ "Emm types",
+        TRUE ~ topic
+      ),
+      time      = as.Date(paste0(year, "-12-31")),
+      geography = "00"
+    )
+
+  # ---------------------------------------------------------------------------
+  # 1. Case rates and death rates (by age, sex, race, and overall)
+  # ---------------------------------------------------------------------------
+  rate_topics <- c("Case rates", "Death rates")
+
+  make_measure <- function(df) {
+    df %>% mutate(measure = if_else(topic == "Case rates", "case_rate", "death_rate"))
+  }
+
+  # Overall (one row per year/measure)
+  rates_overall <- data_raw %>%
+    filter(topic %in% rate_topics, viewby == "Overall") %>%
+    make_measure() %>%
+    mutate(age = "Overall", sex = "Overall", race_ethnicity = "Overall")
+
+  # Age-stratified (exclude the Overall row within Age viewby)
+  age_map <- c(
+    "<1 year old"     = "<1 years",
+    "1 year old"      = "1 year old",
+    "1 years old"     = "1 year old",
+    "2-4 years old"   = "2-4 years old",
+    "5-17 years old"  = "5-17 years old",
+    "18-34 years old" = "18-34 years old",
+    "35-49 years old" = "35-49 years old",
+    "50-64 years old" = "50-64 years old",
+    "\u226565 years old" = "65+ years olds"
+  )
+  rates_age <- data_raw %>%
+    filter(topic %in% rate_topics, viewby == "Age", viewby2 %in% names(age_map)) %>%
+    make_measure() %>%
+    mutate(age = age_map[viewby2], sex = "Overall", race_ethnicity = "Overall")
+
+  # Sex-stratified (Male/Female only — Overall already covered above)
+  rates_sex <- data_raw %>%
+    filter(topic %in% rate_topics, viewby == "Sex", viewby2 %in% c("Male", "Female")) %>%
+    make_measure() %>%
+    mutate(age = "Overall", sex = viewby2, race_ethnicity = "Overall")
+
+  # Race-stratified (non-Overall values only)
+  race_map <- c("Black" = "Black", "White" = "White", "Other races" = "Other")
+  rates_race <- data_raw %>%
+    filter(topic %in% rate_topics, viewby == "Race", viewby2 %in% names(race_map)) %>%
+    make_measure() %>%
+    mutate(age = "Overall", sex = "Overall", race_ethnicity = race_map[viewby2])
+
+  data_rates <- bind_rows(rates_overall, rates_age, rates_sex, rates_race) %>%
+    mutate(measure = if_else(measure == "case_rate", "abcs_gas_rate_cases", "abcs_gas_rate_deaths")) %>%
+    select(geography, time, age, sex, race_ethnicity, measure, value)
+
+  # ---------------------------------------------------------------------------
+  # 2. Total case counts and deaths (national aggregate)
+  # ---------------------------------------------------------------------------
+  data_counts <- data_raw %>%
+    filter(
+      topic == "Number of cases and deaths",
+      viewby == "ALL"
+    ) %>%
+    mutate(
+      measure = case_when(
+        viewby2 == "Total cases"      ~ "abcs_gas_N_cases",
+        viewby2 == "Number of deaths" ~ "abcs_gas_N_deaths",
+        TRUE ~ NA_character_
+      ),
+      age            = "Overall",
+      sex            = "Overall",
+      race_ethnicity = "Overall"
+    ) %>%
+    filter(!is.na(measure)) %>%
+    # Source has duplicate 2023 "Total cases" entries; keep the larger (national estimate)
+    group_by(geography, time, measure) %>%
+    slice_max(value, n = 1, with_ties = FALSE) %>%
+    ungroup() %>%
+    select(geography, time, age, sex, race_ethnicity, measure, value)
+
+  data_main <- bind_rows(data_rates, data_counts) %>%
+    tidyr::pivot_wider(
+      id_cols     = c(geography, time, age, sex, race_ethnicity),
+      names_from  = measure,
+      values_from = value
+    )
+
+  vroom::vroom_write(data_main, "standard/data.csv.gz", delim = ",")
+
+  # ---------------------------------------------------------------------------
+  # 3. Syndromes (percent of cases by clinical presentation)
+  # ---------------------------------------------------------------------------
+  syndrome_name_map <- c(
+    "Cellulitis"                = "cellulitis",
+    "Bacteremia without focus"  = "bacteremia_without_focus",
+    "Pneumonia"                 = "pneumonia",
+    "Necrotizing fasciitis"     = "necrotizing_fasciitis",
+    "Streptococcal toxic shock" = "strep_toxic_shock",
+    "Other"                     = "other"
+  )
+
+  data_syndromes <- data_raw %>%
+    filter(topic == "Syndromes", viewby %in% names(syndrome_name_map)) %>%
+    mutate(
+      measure = paste0("abcs_gas_pct_syndrome_", syndrome_name_map[viewby])
+    ) %>%
+    select(geography, time, measure, value) %>%
+    tidyr::pivot_wider(names_from = measure, values_from = value)
+
+  vroom::vroom_write(data_syndromes, "standard/data_syndromes.csv.gz", delim = ",")
+
+  # ---------------------------------------------------------------------------
+  # 4. Antibiotic resistance (percent resistant / number of isolates)
+  # ---------------------------------------------------------------------------
+  antibiotics <- c(
+    "Penicillin", "Erythromycin", "Clindamycin**",
+    "Cefotaxime", "Tetracycline", "Vancomycin", "Number of isolates"
+  )
+
+  data_resistance <- data_raw %>%
+    filter(topic == "Antibiotic resistance", viewby %in% antibiotics) %>%
+    mutate(
+      drug    = tolower(sub("\\*\\*$", "", viewby)),
+      measure = if_else(
+        viewby == "Number of isolates",
+        "abcs_gas_n_isolates",
+        paste0("abcs_gas_pct_resistant_", drug)
+      )
+    ) %>%
+    select(geography, time, measure, value) %>%
+    tidyr::pivot_wider(names_from = measure, values_from = value)
+
+  vroom::vroom_write(data_resistance, "standard/data_resistance.csv.gz", delim = ",")
+
+  # ---------------------------------------------------------------------------
+  # 5. emm types (percent and counts of isolates by emm type)
+  # ---------------------------------------------------------------------------
+  data_emm <- data_raw %>%
+    filter(topic == "Emm types") %>%
+    mutate(
+      emm_clean = tolower(gsub("[^a-zA-Z0-9]", "_", viewby)),
+      measure   = case_when(
+        units == "Percent" ~ paste0("abcs_gas_emm_pct_", emm_clean),
+        TRUE               ~ paste0("abcs_gas_emm_count_", emm_clean)
+      )
+    ) %>%
+    select(geography, time, measure, value) %>%
+    tidyr::pivot_wider(names_from = measure, values_from = value)
+
+  vroom::vroom_write(data_emm, "standard/data_emm.csv.gz", delim = ",")
+
+  # ---------------------------------------------------------------------------
+  # 6. Record processed state
+  # ---------------------------------------------------------------------------
+  process$raw_state <- raw_state
+  dcf::dcf_process_record(updated = process)
+}

data/abcs_gas/measure_info.json

@@ -0,0 +1,141 @@
+{
+  "case_rate": {
+    "id": "case_rate",
+    "short_name": "Invasive GAS case rate",
+    "long_name": "Invasive Group A Streptococcus case rate",
+    "category": "Bacterial diseases",
+    "short_description": "Incidence rate of invasive Group A Streptococcus disease per 100,000 population",
+    "long_description": "Annual incidence rate of invasive Group A Streptococcus (iGAS) disease per 100,000 population, from CDC Active Bacterial Core surveillance (ABCs). Rates are available by age group, sex, and race.",
+    "statement": "In {location}, the invasive GAS case rate was {value} per 100,000 population.",
+    "measure_type": "Rate",
+    "unit": "Per 100,000 population",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "death_rate": {
+    "id": "death_rate",
+    "short_name": "Invasive GAS death rate",
+    "long_name": "Invasive Group A Streptococcus death rate",
+    "category": "Bacterial diseases",
+    "short_description": "Mortality rate from invasive Group A Streptococcus disease per 100,000 population",
+    "long_description": "Annual mortality rate from invasive Group A Streptococcus (iGAS) disease per 100,000 population, from CDC Active Bacterial Core surveillance (ABCs). Rates are available by age group, sex, and race.",
+    "statement": "In {location}, the invasive GAS death rate was {value} per 100,000 population.",
+    "measure_type": "Rate",
+    "unit": "Per 100,000 population",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "n_cases": {
+    "id": "n_cases",
+    "short_name": "Invasive GAS case count",
+    "long_name": "Number of invasive Group A Streptococcus cases",
+    "category": "Bacterial diseases",
+    "short_description": "Total number of invasive Group A Streptococcus cases in the ABCs catchment area",
+    "long_description": "Annual count of invasive Group A Streptococcus (iGAS) disease cases in the CDC ABCs surveillance catchment area.",
+    "statement": "In {location}, {value} invasive GAS cases were reported.",
+    "measure_type": "Count",
+    "unit": "Count",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "n_deaths": {
+    "id": "n_deaths",
+    "short_name": "Invasive GAS death count",
+    "long_name": "Number of deaths from invasive Group A Streptococcus",
+    "category": "Bacterial diseases",
+    "short_description": "Total number of deaths from invasive Group A Streptococcus in the ABCs catchment area",
+    "long_description": "Annual count of deaths from invasive Group A Streptococcus (iGAS) disease in the CDC ABCs surveillance catchment area.",
+    "statement": "In {location}, {value} deaths from invasive GAS were reported.",
+    "measure_type": "Count",
+    "unit": "Count",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "n_survivals": {
+    "id": "n_survivals",
+    "short_name": "Invasive GAS survival count",
+    "long_name": "Number of survivors of invasive Group A Streptococcus",
+    "category": "Bacterial diseases",
+    "short_description": "Total number of survivors of invasive Group A Streptococcus in the ABCs catchment area",
+    "long_description": "Annual count of survivors of invasive Group A Streptococcus (iGAS) disease in the CDC ABCs surveillance catchment area.",
+    "statement": "In {location}, {value} people survived invasive GAS disease.",
+    "measure_type": "Count",
+    "unit": "Count",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "syndrome": {
+    "id": "syndrome",
+    "short_name": "Clinical syndrome",
+    "long_name": "Clinical syndrome of invasive GAS case",
+    "category": "Bacterial diseases",
+    "short_description": "Percent of invasive GAS cases by clinical syndrome (cellulitis, STSS, necrotizing fasciitis, etc.)",
+    "long_description": "Annual distribution of clinical syndromes among invasive Group A Streptococcus cases. Syndromes include cellulitis, bacteremia without focus, pneumonia, necrotizing fasciitis, streptococcal toxic shock syndrome (STSS), and other.",
+    "statement": "",
+    "measure_type": "Percent",
+    "unit": "Percent",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "pct_resistant": {
+    "id": "pct_resistant",
+    "short_name": "Antibiotic resistance (%)",
+    "long_name": "Percent of GAS isolates resistant to antibiotic",
+    "category": "Bacterial diseases",
+    "short_description": "Percent of invasive GAS isolates showing resistance to a given antibiotic",
+    "long_description": "Annual percent of invasive Group A Streptococcus isolates demonstrating non-susceptibility to antibiotics including penicillin, erythromycin, clindamycin, cefotaxime, tetracycline, and vancomycin. Data from CDC ABCs.",
+    "statement": "",
+    "measure_type": "Percent",
+    "unit": "Percent",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "n_isolates": {
+    "id": "n_isolates",
+    "short_name": "Number of GAS isolates tested",
+    "long_name": "Number of invasive GAS isolates tested for antibiotic susceptibility",
+    "category": "Bacterial diseases",
+    "short_description": "Total number of invasive GAS isolates tested for antibiotic susceptibility",
+    "long_description": "Annual count of invasive Group A Streptococcus isolates submitted for antibiotic susceptibility testing in the CDC ABCs catchment area.",
+    "statement": "",
+    "measure_type": "Count",
+    "unit": "Count",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "emm_type": {
+    "id": "emm_type",
+    "short_name": "emm type",
+    "long_name": "GAS emm type",
+    "category": "Bacterial diseases",
+    "short_description": "Distribution of GAS emm types among invasive isolates",
+    "long_description": "Annual distribution of emm types (surface protein gene sequence types) among invasive Group A Streptococcus isolates from the CDC ABCs catchment area. emm typing is used to track GAS strain diversity and vaccine coverage.",
+    "statement": "",
+    "measure_type": "Percent",
+    "unit": "Percent",
+    "time_resolution": "Year",
+    "sources": [{ "id": "abcs_gas" }],
+    "citations": []
+  },
+  "_sources": {
+    "abcs_gas": {
+      "name": "Active Bacterial Core surveillance (ABCs) - Group A Streptococcus",
+      "url": "https://data.cdc.gov/Public-Health-Surveillance/Active-Bacterial-Core-surveillance-ABCs-Group-A-St/9y49-tura/about_data",
+      "organization": "Centers for Disease Control and Prevention",
+      "organization_url": "https://www.cdc.gov",
+      "location": "Active Bacterial Core surveillance (ABCs) Group A Streptococcus data on data.cdc.gov",
+      "location_url": "https://data.cdc.gov/resource/9y49-tura/",
+      "date_accessed": 2025,
+      "description": "CDC monitors invasive bacterial infections through Active Bacterial Core surveillance (ABCs), a population-based surveillance program for invasive bacterial diseases in selected geographic areas of the United States. This dataset reports annual data on invasive Group A Streptococcus (iGAS) disease from 1997 onwards, including case and death rates by age group, sex, and race; clinical syndrome distribution (cellulitis, bacteremia without focus, pneumonia, necrotizing fasciitis, streptococcal toxic shock syndrome); antibiotic resistance patterns; and emm type distribution among isolates. ABCs catchment areas include California, Colorado, Connecticut, Georgia, Maryland, Minnesota, New York, Oregon, and Tennessee, representing approximately 10% of the US population. Incidence rates are calculated using U.S. Census Bureau population estimates for the respective catchment areas.",
+      "restrictions": "Public domain. CDC data is generally not subject to copyright restrictions."
+    }
+  }
+}

data/abcs_gas/process.json

@@ -0,0 +1,33 @@
+{
+  "name": "abcs_gas",
+  "type": "source",
+  "scripts": [
+    {
+      "path": "ingest.R",
+      "manual": false,
+      "frequency": 0,
+      "last_run": "",
+      "run_time": "",
+      "last_status": {
+        "log": "",
+        "success": true
+      }
+    }
+  ],
+  "checked": "2026-08-05 15:59:49",
+  "check_results": {
+    "data/abcs_gas/standard/data.csv.gz": {
+      "measures": ["missing_info: age", "missing_info: sex", "missing_info: race_ethnicity", "missing_info: abcs_gas_rate_cases", "missing_info: abcs_gas_rate_deaths", "missing_info: abcs_gas_N_cases", "missing_info: abcs_gas_N_deaths"]
+    },
+    "data/abcs_gas/standard/data_emm.csv.gz": {
+      "measures": ["missing_info: abcs_gas_emm_count_number_of_isolates", "missing_info: abcs_gas_emm_pct_other", "missing_info: abcs_gas_emm_pct_emm_1", "missing_info: abcs_gas_emm_pct_emm_11", "missing_info: abcs_gas_emm_pct_emm_12", "missing_info: abcs_gas_emm_pct_emm_28", "missing_info: abcs_gas_emm_pct_emm_43", "missing_info: abcs_gas_emm_pct_emm_59", "missing_info: abcs_gas_emm_pct_emm_77", "missing_info: abcs_gas_emm_pct_emm_82", "missing_info: abcs_gas_emm_pct_emm_83", "missing_info: abcs_gas_emm_pct_emm_89", "missing_info: abcs_gas_emm_pct_emm_92", "missing_info: abcs_gas_emm_pct_emm_49", "missing_info: abcs_gas_emm_pct_emm_81", "missing_info: abcs_gas_emm_pct_emm_60", "missing_info: abcs_gas_emm_pct_emm_91"]
+    },
+    "data/abcs_gas/standard/data_resistance.csv.gz": {
+      "measures": ["missing_info: abcs_gas_pct_resistant_cefotaxime", "missing_info: abcs_gas_pct_resistant_clindamycin", "missing_info: abcs_gas_pct_resistant_erythromycin", "missing_info: abcs_gas_pct_resistant_penicillin", "missing_info: abcs_gas_pct_resistant_tetracycline", "missing_info: abcs_gas_pct_resistant_vancomycin", "missing_info: abcs_gas_n_isolates"]
+    },
+    "data/abcs_gas/standard/data_syndromes.csv.gz": {
+      "measures": ["missing_info: abcs_gas_pct_syndrome_cellulitis", "missing_info: abcs_gas_pct_syndrome_bacteremia_without_focus", "missing_info: abcs_gas_pct_syndrome_pneumonia", "missing_info: abcs_gas_pct_syndrome_necrotizing_fasciitis", "missing_info: abcs_gas_pct_syndrome_strep_toxic_shock"]
+    }
+  },
+  "raw_state": 1747769158
+}