Skip to contents

These functions determine which items in a vector can be considered (the start of) a new episode, based on the argument episode_days. This can be used to determine clinical episodes for any epidemiological analysis. The get_episode() function returns the index number of the episode per group, while the is_new_episode() function returns TRUE for every new get_episode() index, and is thus equal to !duplicated(get_episode(...)).

Usage

get_episode(x, episode_days, ...)

is_new_episode(x, episode_days, ...)

Arguments

x

vector of dates (class Date or POSIXt), will be sorted internally to determine episodes

episode_days

required episode length in days, can also be less than a day or Inf, see Details

...

ignored, only in place to allow future extensions

Value

  • get_episode(): a double vector

  • is_new_episode(): a logical vector

Details

Dates are first sorted from old to new. The oldest date will mark the start of the first episode. After this date, the next date will be marked that is at least episode_days days later than the start of the first episode. From that second marked date on, the next date will be marked that is at least episode_days days later than the start of the second episode which will be the start of the third episode, and so on. Before the vector is being returned, the original order will be restored.

The first_isolate() function is a wrapper around the is_new_episode() function, but is more efficient for data sets containing microorganism codes or names and allows for different isolate selection methods.

The dplyr package is not required for these functions to work, but these episode functions do support variable grouping and work conveniently inside dplyr verbs such as filter(), mutate() and summarise().

See also

Examples

# `example_isolates` is a data set available in the AMR package.
# See ?example_isolates
df <- example_isolates[sample(seq_len(2000), size = 100), ]

get_episode(df$date, episode_days = 60) # indices
#>   [1] 50 29 35 51  8 52 19 48  6 36  1 49 12  9 10  4 29 46 32 37 33 30  6 35 32
#>  [26]  9 34  8  1 44 51  4 40 16 12 14 47 16 27 29 14 25 11  7 32 39 15 48 50  4
#>  [51] 43 23 25 31 22 28 29 16 34  2  5  9 48 24 43 20 34 40 13 17 38 31 11 34  7
#>  [76] 35 53 28 21 41 51 16  4 42 23 47 49 53 48  3 45 18 46  9 18 26 14 10 28  7
is_new_episode(df$date, episode_days = 60) # TRUE/FALSE
#>   [1]  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
#>  [13]  TRUE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE FALSE
#>  [25] FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE
#>  [37]  TRUE FALSE  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE FALSE
#>  [49] FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE  TRUE
#>  [61]  TRUE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE
#>  [73] FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE
#>  [85] FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE  TRUE
#>  [97] FALSE FALSE FALSE FALSE

# filter on results from the third 60-day episode only, using base R
df[which(get_episode(df$date, 60) == 3), ]
#> # A tibble: 1 × 46
#>   date       patient   age gender ward     mo           PEN   OXA   FLC   AMX  
#>   <date>     <chr>   <dbl> <chr>  <chr>    <mo>         <sir> <sir> <sir> <sir>
#> 1 2002-11-18 956065     89 F      Clinical B_ESCHR_COLI R     NA    NA    NA   
#> # … with 36 more variables: AMC <sir>, AMP <sir>, TZP <sir>, CZO <sir>,
#> #   FEP <sir>, CXM <sir>, FOX <sir>, CTX <sir>, CAZ <sir>, CRO <sir>,
#> #   GEN <sir>, TOB <sir>, AMK <sir>, KAN <sir>, TMP <sir>, SXT <sir>,
#> #   NIT <sir>, FOS <sir>, LNZ <sir>, CIP <sir>, MFX <sir>, VAN <sir>,
#> #   TEC <sir>, TCY <sir>, TGC <sir>, DOX <sir>, ERY <sir>, CLI <sir>,
#> #   AZM <sir>, IPM <sir>, MEM <sir>, MTR <sir>, CHL <sir>, COL <sir>,
#> #   MUP <sir>, RIF <sir>

# the functions also work for less than a day, e.g. to include one per hour:
get_episode(c(Sys.time(),
              Sys.time() + 60 * 60),
            episode_days = 1 / 24)
#> [1] 1 2

# \donttest{
if (require("dplyr")) {
  # is_new_episode() can also be used in dplyr verbs to determine patient
  # episodes based on any (combination of) grouping variables:
  df %>%
    mutate(condition = sample(
      x = c("A", "B", "C"),
      size = 200,
      replace = TRUE
    )) %>%
    group_by(condition) %>%
    mutate(new_episode = is_new_episode(date, 365)) %>%
    select(patient, date, condition, new_episode)
}
#> Error in mutate(., condition = sample(x = c("A", "B", "C"), size = 200,     replace = TRUE)):  In argument: `condition = sample(x = c("A", "B", "C"), size = 200,
#>   replace = TRUE)`.
#> Caused by error:
#> ! `condition` must be size 100 or 1, not 200.

if (require("dplyr")) {
  df %>%
    group_by(ward, patient) %>%
    transmute(date,
      patient,
      new_index = get_episode(date, 60),
      new_logical = is_new_episode(date, 60)
    ) %>% 
    arrange(patient, ward, date)
}
#> # A tibble: 100 × 5
#> # Groups:   ward, patient [96]
#>    ward     date       patient new_index new_logical
#>    <chr>    <date>     <chr>       <dbl> <lgl>      
#>  1 Clinical 2013-12-02 004531          1 TRUE       
#>  2 Clinical 2007-08-22 005088          1 TRUE       
#>  3 Clinical 2011-09-20 011307          1 TRUE       
#>  4 Clinical 2011-04-25 023456          1 TRUE       
#>  5 ICU      2015-09-21 062027          1 TRUE       
#>  6 ICU      2003-05-26 065187          1 TRUE       
#>  7 Clinical 2009-08-24 077922          1 TRUE       
#>  8 Clinical 2007-10-26 080086          2 TRUE       
#>  9 Clinical 2010-08-08 080086          1 TRUE       
#> 10 Clinical 2016-08-07 092034          1 TRUE       
#> # … with 90 more rows

if (require("dplyr")) {
  df %>%
    group_by(ward) %>%
    summarise(
      n_patients = n_distinct(patient),
      n_episodes_365 = sum(is_new_episode(date, episode_days = 365)),
      n_episodes_60 = sum(is_new_episode(date, episode_days = 60)),
      n_episodes_30 = sum(is_new_episode(date, episode_days = 30))
    )
}
#> # A tibble: 3 × 5
#>   ward       n_patients n_episodes_365 n_episodes_60 n_episodes_30
#>   <chr>           <int>          <int>         <int>         <int>
#> 1 Clinical           57             13            39            47
#> 2 ICU                31              9            20            25
#> 3 Outpatient          8              5             7             7

# grouping on patients and microorganisms leads to the same
# results as first_isolate() when using 'episode-based':
if (require("dplyr")) {
  x <- df %>%
    filter_first_isolate(
      include_unknown = TRUE,
      method = "episode-based"
    )

  y <- df %>%
    group_by(patient, mo) %>%
    filter(is_new_episode(date, 365)) %>%
    ungroup()

  identical(x, y)
}
#> [1] FALSE

# but is_new_episode() has a lot more flexibility than first_isolate(),
# since you can now group on anything that seems relevant:
if (require("dplyr")) {
  
  df %>%
    group_by(patient, mo, ward) %>%
    mutate(flag_episode = is_new_episode(date, 365)) %>%
    select(group_vars(.), flag_episode)
}
#> # A tibble: 100 × 4
#> # Groups:   patient, mo, ward [97]
#>    patient mo           ward       flag_episode
#>    <chr>   <mo>         <chr>      <lgl>       
#>  1 D08278  B_ESCHR_COLI ICU        TRUE        
#>  2 807228  B_KLBSL_PNMN ICU        TRUE        
#>  3 C25552  B_STPHY_CONS Outpatient TRUE        
#>  4 423709  B_ESCHR_COLI Clinical   TRUE        
#>  5 304508  B_STRPT_PNMN Clinical   TRUE        
#>  6 BF4515  B_ESCHR_COLI ICU        TRUE        
#>  7 005088  B_SLMNL_ENTR Clinical   TRUE        
#>  8 A79917  B_PSDMN_AERG Clinical   TRUE        
#>  9 2FC253  B_ESCHR_COLI ICU        TRUE        
#> 10 D29354  B_STRPT_PNMN ICU        TRUE        
#> # … with 90 more rows
# }