Get the WHO TB Burden Data

Get the TB burden data, and multi-drug resistant TB (MDR-TB) data from the WHO, see here for details. This function will first attempt to load the data from the temporary directory (tempdir). If that fails, and download_data = TRUE, it will instead download the data. The MDR TB data is only available for the latest year of data.

get_tb_burden(
  url = NULL,
  download_data = TRUE,
  save = TRUE,
  burden_save_name = NULL,
  add_mdr_data = TRUE,
  additional_datasets = NULL,
  mdr_save_name = NULL,
  mdr_url = NULL,
  return = TRUE,
  verbose = FALSE,
  use_utils = FALSE,
  retry_download = TRUE
)

Arguments

url	Character string, indicating the url of the TB burden data. Default is current url. This argument is depreciated and will be removed from future releases. The TB burden URL is now supplied internally - see `available_datasets` for details.
download_data	Logical, defaults to `TRUE`. If not found locally should the data be downloaded from the specified URL?
save	Logical, should the data be saved for reuse during the current R session. Defaults to `TRUE`. If `TRUE` then the data is saved to the temporary directory specified by `tempdir`.
burden_save_name	Character string, name to save the data under. This argument is depreciated and will be removed from future releases. Dataset naming is now handled internally.
add_mdr_data	Logical, defaults to `TRUE`. Should MDR TB burden data be downloaded and joined to the TB burden data.
additional_datasets	A character vector specifying the names of the additional datasets to import. See `available_datasets` for available datasets. Use "all" to download all available datasets (experimental datasets such as incidence by age and sex are excluded from this list).
mdr_save_name	Character string, name to save the MDR data under. This argument is depreciated and will be removed from future releases. Dataset naming is now handled internally.
mdr_url	Character string, indicating the url of the MDR TB data. This argument is depreciated and will be removed from future releases. The MDR-TB burden URL is now supplied internally - see `available_datasets` for details.
return	Logical, should the data be returned as a dataframe. Defaults to `TRUE`.
verbose	Logical, defaults to `FALSE`. Should additional status and progress messages be displayed.
use_utils	Logical, defaults to `FALSE`. Used for testing alternative data download function. When `TRUE` data is downloaded using `read.csv`.
retry_download	Logical defaults to `TRUE`. When `TRUE`, if downloading fails, the function will try repeatedly to download the data within 3 seconds, up to 3 times.

Value

The WHO TB burden data as a tibble.

Examples



## Default datasets
tb_burden <- get_tb_burden(additional_datasets = available_datasets$dataset[3])
#> Incidence by age and sex data is experimental and may cause issues for other
#>         datasets. Use with caution!
#>         Open an issue here if you run into problems: https://github.com/seabbs/getTBinR/issues

head(tb_burden)
#> # A tibble: 6 x 79
#>   country iso2  iso3  iso_numeric g_whoregion  year e_pop_num e_inc_100k
#>   <chr>   <chr> <chr>       <int> <chr>       <int>     <int>      <dbl>
#> 1 Afghan… AF    AFG             4 Eastern Me…  2000  20779953        190
#> 2 Afghan… AF    AFG             4 Eastern Me…  2001  21606988        189
#> 3 Afghan… AF    AFG             4 Eastern Me…  2002  22600770        189
#> 4 Afghan… AF    AFG             4 Eastern Me…  2003  23680871        189
#> 5 Afghan… AF    AFG             4 Eastern Me…  2004  24726684        189
#> 6 Afghan… AF    AFG             4 Eastern Me…  2005  25654277        189
#> # … with 71 more variables: e_inc_100k_lo <dbl>, e_inc_100k_hi <dbl>,
#> #   e_inc_num <int>, e_inc_num_lo <int>, e_inc_num_hi <int>,
#> #   e_tbhiv_prct <dbl>, e_tbhiv_prct_lo <dbl>, e_tbhiv_prct_hi <dbl>,
#> #   e_inc_tbhiv_100k <dbl>, e_inc_tbhiv_100k_lo <dbl>,
#> #   e_inc_tbhiv_100k_hi <dbl>, e_inc_tbhiv_num <int>, e_inc_tbhiv_num_lo <int>,
#> #   e_inc_tbhiv_num_hi <int>, e_mort_exc_tbhiv_100k <dbl>,
#> #   e_mort_exc_tbhiv_100k_lo <dbl>, e_mort_exc_tbhiv_100k_hi <dbl>,
#> #   e_mort_exc_tbhiv_num <int>, e_mort_exc_tbhiv_num_lo <int>,
#> #   e_mort_exc_tbhiv_num_hi <int>, e_mort_tbhiv_100k <dbl>,
#> #   e_mort_tbhiv_100k_lo <dbl>, e_mort_tbhiv_100k_hi <dbl>,
#> #   e_mort_tbhiv_num <int>, e_mort_tbhiv_num_lo <int>,
#> #   e_mort_tbhiv_num_hi <int>, e_mort_100k <dbl>, e_mort_100k_lo <dbl>,
#> #   e_mort_100k_hi <dbl>, e_mort_num <int>, e_mort_num_lo <int>,
#> #   e_mort_num_hi <int>, cfr <dbl>, cfr_lo <dbl>, cfr_hi <dbl>, cfr_pct <int>,
#> #   cfr_pct_lo <int>, cfr_pct_hi <int>, c_newinc_100k <dbl>, c_cdr <dbl>,
#> #   c_cdr_lo <dbl>, c_cdr_hi <dbl>, source_rr_new <chr>,
#> #   source_drs_coverage_new <chr>, source_drs_year_new <int>,
#> #   e_rr_pct_new <dbl>, e_rr_pct_new_lo <dbl>, e_rr_pct_new_hi <dbl>,
#> #   e_mdr_pct_rr_new <int>, source_rr_ret <chr>, source_drs_coverage_ret <chr>,
#> #   source_drs_year_ret <int>, e_rr_pct_ret <dbl>, e_rr_pct_ret_lo <dbl>,
#> #   e_rr_pct_ret_hi <dbl>, e_mdr_pct_rr_ret <int>, e_inc_rr_num <int>,
#> #   e_inc_rr_num_lo <int>, e_inc_rr_num_hi <int>, e_mdr_pct_rr <dbl>,
#> #   e_rr_in_notified_labconf_pulm <int>,
#> #   e_rr_in_notified_labconf_pulm_lo <int>,
#> #   e_rr_in_notified_labconf_pulm_hi <int>, measure <chr>, unit <chr>,
#> #   age_group <chr>, sex <chr>, risk_factor <chr>, inc_age_sex <int>,
#> #   inc_age_sex_lo <int>, inc_age_sex_hi <int>

## Add in the latent TB dataset as an additional dataset (see getTBinR::avaiable_datasets)
tb_with_latents <- get_tb_burden(additional_datasets = available_datasets$dataset[3])
#> Incidence by age and sex data is experimental and may cause issues for other
#>         datasets. Use with caution!
#>         Open an issue here if you run into problems: https://github.com/seabbs/getTBinR/issues

head(tb_with_latents)
#> # A tibble: 6 x 79
#>   country iso2  iso3  iso_numeric g_whoregion  year e_pop_num e_inc_100k
#>   <chr>   <chr> <chr>       <int> <chr>       <int>     <int>      <dbl>
#> 1 Afghan… AF    AFG             4 Eastern Me…  2000  20779953        190
#> 2 Afghan… AF    AFG             4 Eastern Me…  2001  21606988        189
#> 3 Afghan… AF    AFG             4 Eastern Me…  2002  22600770        189
#> 4 Afghan… AF    AFG             4 Eastern Me…  2003  23680871        189
#> 5 Afghan… AF    AFG             4 Eastern Me…  2004  24726684        189
#> 6 Afghan… AF    AFG             4 Eastern Me…  2005  25654277        189
#> # … with 71 more variables: e_inc_100k_lo <dbl>, e_inc_100k_hi <dbl>,
#> #   e_inc_num <int>, e_inc_num_lo <int>, e_inc_num_hi <int>,
#> #   e_tbhiv_prct <dbl>, e_tbhiv_prct_lo <dbl>, e_tbhiv_prct_hi <dbl>,
#> #   e_inc_tbhiv_100k <dbl>, e_inc_tbhiv_100k_lo <dbl>,
#> #   e_inc_tbhiv_100k_hi <dbl>, e_inc_tbhiv_num <int>, e_inc_tbhiv_num_lo <int>,
#> #   e_inc_tbhiv_num_hi <int>, e_mort_exc_tbhiv_100k <dbl>,
#> #   e_mort_exc_tbhiv_100k_lo <dbl>, e_mort_exc_tbhiv_100k_hi <dbl>,
#> #   e_mort_exc_tbhiv_num <int>, e_mort_exc_tbhiv_num_lo <int>,
#> #   e_mort_exc_tbhiv_num_hi <int>, e_mort_tbhiv_100k <dbl>,
#> #   e_mort_tbhiv_100k_lo <dbl>, e_mort_tbhiv_100k_hi <dbl>,
#> #   e_mort_tbhiv_num <int>, e_mort_tbhiv_num_lo <int>,
#> #   e_mort_tbhiv_num_hi <int>, e_mort_100k <dbl>, e_mort_100k_lo <dbl>,
#> #   e_mort_100k_hi <dbl>, e_mort_num <int>, e_mort_num_lo <int>,
#> #   e_mort_num_hi <int>, cfr <dbl>, cfr_lo <dbl>, cfr_hi <dbl>, cfr_pct <int>,
#> #   cfr_pct_lo <int>, cfr_pct_hi <int>, c_newinc_100k <dbl>, c_cdr <dbl>,
#> #   c_cdr_lo <dbl>, c_cdr_hi <dbl>, source_rr_new <chr>,
#> #   source_drs_coverage_new <chr>, source_drs_year_new <int>,
#> #   e_rr_pct_new <dbl>, e_rr_pct_new_lo <dbl>, e_rr_pct_new_hi <dbl>,
#> #   e_mdr_pct_rr_new <int>, source_rr_ret <chr>, source_drs_coverage_ret <chr>,
#> #   source_drs_year_ret <int>, e_rr_pct_ret <dbl>, e_rr_pct_ret_lo <dbl>,
#> #   e_rr_pct_ret_hi <dbl>, e_mdr_pct_rr_ret <int>, e_inc_rr_num <int>,
#> #   e_inc_rr_num_lo <int>, e_inc_rr_num_hi <int>, e_mdr_pct_rr <dbl>,
#> #   e_rr_in_notified_labconf_pulm <int>,
#> #   e_rr_in_notified_labconf_pulm_lo <int>,
#> #   e_rr_in_notified_labconf_pulm_hi <int>, measure <chr>, unit <chr>,
#> #   age_group <chr>, sex <chr>, risk_factor <chr>, inc_age_sex <int>,
#> #   inc_age_sex_lo <int>, inc_age_sex_hi <int>

Arguments

Value

See also

Examples