Get Portfolio configuration from a dataframe aggregated on patient level with max_ae and max_visit. Will filter studies with only a few sites and patients and will anonymize IDs. Portfolio configuration can be used by sim_test_data_portfolio to generate data for an artificial portfolio.

get_config(
  df_site,
  min_pat_per_study = 100,
  min_sites_per_study = 10,
  anonymize = TRUE,
  pad_width = 4
)

Arguments

df_site

dataframe aggregated on patient level with max_ae and max_visit

min_pat_per_study

minimum number of patients per study, Default: 100

min_sites_per_study

minimum number of sites per study, Default: 10

anonymize

logical, Default: TRUE

pad_width

padding width for newly created IDs, Default: 4

Value

dataframe with the following columns:

study_id

study identification

ae_per_visit_mean

mean AE per visit per study

site_number

site

max_visit_sd

standard deviation of maximum patient visits per site

max_visit_mean

mean of maximum patient visits per site

n_pat

number of patients

Examples

# \donttest{
df_visit1 <- sim_test_data_study(n_pat = 100, n_sites = 10,
                                 frac_site_with_ur = 0.4, ur_rate = 0.6)

df_visit1$study_id <- "A"

df_visit2 <- sim_test_data_study(n_pat = 100, n_sites = 10,
                                 frac_site_with_ur = 0.2, ur_rate = 0.1)

df_visit2$study_id <- "B"

df_visit <- dplyr::bind_rows(df_visit1, df_visit2)

df_site_max <- df_visit %>%
  dplyr::group_by(study_id, site_number, patnum) %>%
  dplyr::summarise(max_visit = max(visit),
            max_ae = max(n_ae),
            .groups = "drop")

df_config <- get_config(df_site_max)

df_config
#> # A tibble: 20 × 6
#>    study_id ae_per_visit_mean site_number max_visit_sd max_visit_mean n_pat
#>    <chr>                <dbl> <chr>              <dbl>          <dbl> <int>
#>  1 0001                 0.401 0001                3.41           20.1    10
#>  2 0001                 0.401 0002                2.33           21.1    10
#>  3 0001                 0.401 0003                3.97           20.2    10
#>  4 0001                 0.401 0004                3.30           21.3    10
#>  5 0001                 0.401 0005                4.25           20.9    10
#>  6 0001                 0.401 0006                4.50           19.5    10
#>  7 0001                 0.401 0007                3.92           17.3    10
#>  8 0001                 0.401 0008                4.76           19.7    10
#>  9 0001                 0.401 0009                4.40           19.3    10
#> 10 0001                 0.401 0010                4.27           19.3    10
#> 11 0002                 0.487 0001                2.99           20.4    10
#> 12 0002                 0.487 0002                4.30           19.7    10
#> 13 0002                 0.487 0003                2.49           19.8    10
#> 14 0002                 0.487 0004                5.32           19.4    10
#> 15 0002                 0.487 0005                3.77           19.3    10
#> 16 0002                 0.487 0006                5.44           19.7    10
#> 17 0002                 0.487 0007                4.72           19.5    10
#> 18 0002                 0.487 0008                4.10           20.8    10
#> 19 0002                 0.487 0009                3.88           17.8    10
#> 20 0002                 0.487 0010                3.89           18.3    10

df_portf <- sim_test_data_portfolio(df_config)

df_portf
#> # A tibble: 3,829 × 8
#>    study_id ae_per_visit_mean site_number max_visit…¹ max_v…² patnum visit  n_ae
#>    <chr>                <dbl> <chr>             <dbl>   <dbl> <chr>  <int> <int>
#>  1 0001                 0.401 0001               3.41    20.1 0001       1     0
#>  2 0001                 0.401 0001               3.41    20.1 0001       2     0
#>  3 0001                 0.401 0001               3.41    20.1 0001       3     2
#>  4 0001                 0.401 0001               3.41    20.1 0001       4     2
#>  5 0001                 0.401 0001               3.41    20.1 0001       5     2
#>  6 0001                 0.401 0001               3.41    20.1 0001       6     2
#>  7 0001                 0.401 0001               3.41    20.1 0001       7     2
#>  8 0001                 0.401 0001               3.41    20.1 0001       8     3
#>  9 0001                 0.401 0001               3.41    20.1 0001       9     3
#> 10 0001                 0.401 0001               3.41    20.1 0001      10     3
#> # … with 3,819 more rows, and abbreviated variable names ¹​max_visit_sd,
#> #   ²​max_visit_mean

df_scen <- sim_ur_scenarios(df_portf,
                            extra_ur_sites = 2,
                            ur_rate = c(0.5, 1))
#> aggregating site level
#> prepping for simulation
#> generating scenarios
#> getting under-reporting stats
#> evaluating stats


df_scen
#> # A tibble: 140 × 14
#>    study…¹ site_…² n_pat n_pat…³ visit…⁴ mean_…⁵ mean_…⁶ n_pat…⁷ extra…⁸ frac_…⁹
#>    <chr>   <chr>   <int>   <int>   <dbl>   <dbl>   <dbl>   <int>   <dbl>   <dbl>
#>  1 0001    0001       10      10      15    5.8     5.87      78       0   0    
#>  2 0001    0001       10      10      15    2.9     5.87      78       0   0.114
#>  3 0001    0001       10      10      15    0       5.87      78       0   0.114
#>  4 0001    0001       10      10      15    2.9     5.53      78       1   0.214
#>  5 0001    0001       10      10      15    0       5.18      78       1   0.214
#>  6 0001    0001       10      10      15    2.9     5.25      78       2   0.314
#>  7 0001    0001       10      10      15    0       4.63      78       2   0.314
#>  8 0001    0002       10      10      17    7.1     6.46      65       0   0    
#>  9 0001    0002       10      10      17    3.55    6.46      65       0   0.133
#> 10 0001    0002       10      10      17    0       6.46      65       0   0.133
#> # … with 130 more rows, 4 more variables: ur_rate <dbl>, prob_low <dbl>,
#> #   prob_low_adj <dbl>, prob_low_prob_ur <dbl>, and abbreviated variable names
#> #   ¹​study_id, ²​site_number, ³​n_pat_with_med75, ⁴​visit_med75,
#> #   ⁵​mean_ae_site_med75, ⁶​mean_ae_study_med75, ⁷​n_pat_with_med75_study,
#> #   ⁸​extra_ur_sites, ⁹​frac_pat_with_ur

df_perf <- get_portf_perf(df_scen)

df_perf
#> # A tibble: 27 × 5
#>      fpr thresh extra_ur_sites ur_rate   tpr
#>    <dbl>  <dbl>          <dbl>   <dbl> <dbl>
#>  1 0.001  0.922              0     0    0.05
#>  2 0.001  0.922              1     0    0.05
#>  3 0.001  0.922              2     0    0.05
#>  4 0.001  0.922              0     0.5  1   
#>  5 0.001  0.922              1     0.5  1   
#>  6 0.001  0.922              2     0.5  1   
#>  7 0.001  0.922              0     1    1   
#>  8 0.001  0.922              1     1    1   
#>  9 0.001  0.922              2     1    1   
#> 10 0.01   0.909              0     0    0.05
#> # … with 17 more rows
# }