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 values TRUE/FALSE to indicate whether an item in a vector is the start of a new 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 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 = 200), ]

get_episode(df$date, episode_days = 60) # indices
#>   [1] 56 61 60 30 16 51 17  7  8  2 14 22 30 19 38 31 30 47 27 23 10 58 41 64 15
#>  [26] 39  9 28 40 35 37 57  4 10 29 61 53  2 56 27 56 13 62 28 46  9 45 43  4 16
#>  [51] 53 52  6 18 35 57  8 48 10 18 11 26 31 40 34 17 19 18 32 17  1 39  9  5 25
#>  [76]  5 51 52 33 45 14  4 12  6 38 62  7  9  9 45 49 40 33 30 12 13  4 47 39 60
#> [101] 60 20  8  2 13 51 57 62 36 38 34 38 14 16  1 54 42 28 59 23 29  3 36 43  8
#> [126] 27  9 48  1 40  9 24 57 22 59 33  7 30  7 60 32 37 36 13 35 10 32 49 41 62
#> [151] 30  8 19 26 44 24 46 63 47 56 54 22 33 50 30 55 49 12 55 57 50 24  9 54 27
#> [176] 30 40 26 58 39  9 58 25 13 60 21 44 39 26 28 41 29 35 10 18  3 46 38 61 20
is_new_episode(df$date, episode_days = 60) # TRUE/FALSE
#>   [1] FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE
#>  [13] FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE
#>  [25]  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE
#>  [37]  TRUE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE
#>  [49]  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE
#>  [61]  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE
#>  [73] FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE
#>  [85]  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE
#>  [97] FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE
#> [109]  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE
#> [121]  TRUE  TRUE FALSE  TRUE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE
#> [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
#> [145] FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE
#> [157] FALSE  TRUE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE
#> [169] FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE
#> [181] FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE
#> [193]  TRUE FALSE FALSE FALSE 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: 2 × 46
#>   date       patient   age gender ward     mo           PEN   OXA   FLC   AMX  
#>   <date>     <chr>   <dbl> <chr>  <chr>    <mo>         <rsi> <rsi> <rsi> <rsi>
#> 1 2002-08-19 A49852     70 M      Clinical B_ESCHR_COLI R     NA    NA    NA   
#> 2 2002-10-14 FCC668     54 F      ICU      B_STRPT_PNMN S     NA    NA    S    
#> # … with 36 more variables: AMC <rsi>, AMP <rsi>, TZP <rsi>, CZO <rsi>,
#> #   FEP <rsi>, CXM <rsi>, FOX <rsi>, CTX <rsi>, CAZ <rsi>, CRO <rsi>,
#> #   GEN <rsi>, TOB <rsi>, AMK <rsi>, KAN <rsi>, TMP <rsi>, SXT <rsi>,
#> #   NIT <rsi>, FOS <rsi>, LNZ <rsi>, CIP <rsi>, MFX <rsi>, VAN <rsi>,
#> #   TEC <rsi>, TCY <rsi>, TGC <rsi>, DOX <rsi>, ERY <rsi>, CLI <rsi>,
#> #   AZM <rsi>, IPM <rsi>, MEM <rsi>, MTR <rsi>, CHL <rsi>, COL <rsi>,
#> #   MUP <rsi>, RIF <rsi>

# 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)
}
#> # A tibble: 200 × 4
#> # Groups:   condition [3]
#>    patient date       condition new_episode
#>    <chr>   <date>     <chr>     <lgl>      
#>  1 329C35  2016-04-02 C         TRUE       
#>  2 694764  2017-03-30 A         FALSE      
#>  3 4B1971  2017-01-13 A         TRUE       
#>  4 B65162  2008-12-29 C         FALSE      
#>  5 B338BC  2005-07-02 B         FALSE      
#>  6 F67089  2014-10-24 B         FALSE      
#>  7 969581  2005-10-18 B         TRUE       
#>  8 F35553  2003-08-13 C         FALSE      
#>  9 82C90B  2003-09-19 C         FALSE      
#> 10 D10443  2002-04-26 C         FALSE      
#> # … with 190 more rows
if (require("dplyr")) {
  df %>%
    group_by(ward, patient) %>%
    transmute(date,
      patient,
      new_index = get_episode(date, 60),
      new_logical = is_new_episode(date, 60)
    )
}
#> # A tibble: 200 × 5
#> # Groups:   ward, patient [189]
#>    ward     date       patient new_index new_logical
#>    <chr>    <date>     <chr>       <dbl> <lgl>      
#>  1 Clinical 2016-04-02 329C35          1 TRUE       
#>  2 ICU      2017-03-30 694764          1 TRUE       
#>  3 ICU      2017-01-13 4B1971          1 TRUE       
#>  4 Clinical 2008-12-29 B65162          1 TRUE       
#>  5 Clinical 2005-07-02 B338BC          1 TRUE       
#>  6 Clinical 2014-10-24 F67089          1 TRUE       
#>  7 Clinical 2005-10-18 969581          1 TRUE       
#>  8 ICU      2003-08-13 F35553          2 TRUE       
#>  9 Clinical 2003-09-19 82C90B          1 TRUE       
#> 10 Clinical 2002-04-26 D10443          1 TRUE       
#> # … with 190 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          117             14            52            63
#> 2 ICU                59             14            39            50
#> 3 Outpatient         13              8            12            13
if (require("dplyr")) {

  # grouping on patients and microorganisms leads to the same
  # results as first_isolate() when using 'episode-based':
  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)
}
#> Including isolates from ICU.
#> [1] FALSE
if (require("dplyr")) {

  # but is_new_episode() has a lot more flexibility than first_isolate(),
  # since you can now group on anything that seems relevant:
  df %>%
    group_by(patient, mo, ward) %>%
    mutate(flag_episode = is_new_episode(date, 365)) %>%
    select(group_vars(.), flag_episode)
}
#> # A tibble: 200 × 4
#> # Groups:   patient, mo, ward [191]
#>    patient mo           ward     flag_episode
#>    <chr>   <mo>         <chr>    <lgl>       
#>  1 329C35  B_ESCHR_COLI Clinical TRUE        
#>  2 694764  B_STPHY_HMNS ICU      TRUE        
#>  3 4B1971  B_ESCHR_COLI ICU      TRUE        
#>  4 B65162  B_STRPT_PNMN Clinical TRUE        
#>  5 B338BC  B_ENTRC      Clinical TRUE        
#>  6 F67089  B_STPHY_AURS Clinical TRUE        
#>  7 969581  B_STPHY_CONS Clinical TRUE        
#>  8 F35553  B_ENTRC_FCLS ICU      TRUE        
#>  9 82C90B  B_STPHY_EPDR Clinical TRUE        
#> 10 D10443  B_KLBSL_PNMN Clinical TRUE        
#> # … with 190 more rows
# }