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.
Arguments
- x
vector of dates (class
DateorPOSIXt), 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
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().
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$date, episode_days = 60) # indices
#> [1] 3 60 40 53 59 20 23 5 19 39 19 12 16 54 9 20 31 7 12 2 46 44 4 44 56
#> [26] 15 58 25 39 43 9 12 35 8 18 37 58 5 46 4 17 47 10 26 11 7 34 31 11 2
#> [51] 23 49 8 46 26 55 25 54 26 55 28 29 35 27 38 36 3 54 41 60 13 48 52 59 24
#> [76] 6 6 14 15 15 1 26 19 10 62 51 10 24 16 49 22 2 25 58 12 48 19 59 34 16
#> [101] 59 51 49 61 36 53 52 23 38 10 57 49 51 58 58 45 50 59 30 52 6 51 20 1 3
#> [126] 33 38 6 14 45 42 16 54 47 4 50 22 37 59 28 40 9 43 19 61 17 51 32 54 24
#> [151] 59 23 42 50 12 43 44 59 8 60 10 12 7 43 3 11 30 3 39 56 8 28 5 3 47
#> [176] 54 3 16 16 9 5 43 33 58 61 21 12 10 23 59 43 29 56 59 26 10 29 15 12 32
is_new_episode(df$date, episode_days = 60) # TRUE/FALSE
#> [1] FALSE FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE
#> [13] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE
#> [25] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE
#> [37] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE TRUE
#> [49] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE
#> [61] TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE
#> [73] FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE
#> [85] TRUE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE TRUE
#> [97] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
#> [109] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE
#> [121] FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE
#> [133] FALSE TRUE FALSE FALSE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE
#> [145] TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE
#> [157] TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE
#> [169] FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
#> [181] FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE FALSE FALSE
#> [193] FALSE 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: 7 × 46
#> date patient age gender ward mo PEN OXA FLC AMX
#> <date> <chr> <dbl> <chr> <chr> <mo> <rsi> <rsi> <rsi> <rsi>
#> 1 2002-07-30 218912 76 F ICU B_ESCHR_COLI R NA NA NA
#> 2 2002-09-08 B8CB09 60 F Outpatie… B_STPHY_CONS S NA S NA
#> 3 2002-08-19 A49852 70 M Clinical B_ESCHR_COLI R NA NA NA
#> 4 2002-07-23 F35553 51 M ICU B_STPHY_AURS R NA S R
#> 5 2002-07-15 426426 67 F ICU B_ESCHR_COLI R NA NA NA
#> 6 2002-08-31 149442 80 F ICU B_STPHY_AURS R NA S R
#> 7 2002-07-21 955940 82 F Clinical B_PSDMN_AERG R NA NA R
#> # … 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 218912 2002-07-30 B FALSE
#> 2 C72224 2017-08-09 B FALSE
#> 3 207804 2012-10-04 A FALSE
#> 4 329C35 2016-04-03 A FALSE
#> 5 647993 2017-05-16 A FALSE
#> 6 E19253 2006-08-22 C FALSE
#> 7 F37316 2007-07-07 A TRUE
#> 8 151041 2003-01-31 B FALSE
#> 9 C34072 2006-07-05 A FALSE
#> 10 C2846C 2012-06-29 B 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 [184]
#> ward date patient new_index new_logical
#> <chr> <date> <chr> <dbl> <lgl>
#> 1 ICU 2002-07-30 218912 1 TRUE
#> 2 Clinical 2017-08-09 C72224 1 TRUE
#> 3 Clinical 2012-10-04 207804 1 TRUE
#> 4 Clinical 2016-04-03 329C35 1 TRUE
#> 5 Clinical 2017-05-16 647993 1 TRUE
#> 6 Clinical 2006-08-22 E19253 1 TRUE
#> 7 ICU 2007-07-07 F37316 1 TRUE
#> 8 Clinical 2003-01-31 151041 1 TRUE
#> 9 Clinical 2006-07-05 C34072 1 TRUE
#> 10 ICU 2012-06-29 C2846C 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 112 14 54 72
#> 2 ICU 62 14 34 43
#> 3 Outpatient 10 6 9 10
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 [189]
#> patient mo ward flag_episode
#> <chr> <mo> <chr> <lgl>
#> 1 218912 B_ESCHR_COLI ICU TRUE
#> 2 C72224 B_STRPT_AGLC Clinical TRUE
#> 3 207804 B_STRPT_PNMN Clinical TRUE
#> 4 329C35 B_ESCHR_COLI Clinical TRUE
#> 5 647993 B_STPHY_AURS Clinical TRUE
#> 6 E19253 B_STPHY_CONS Clinical TRUE
#> 7 F37316 B_STRPT_PNMN ICU TRUE
#> 8 151041 B_ESCHR_COLI Clinical TRUE
#> 9 C34072 B_STPHY_CONS Clinical TRUE
#> 10 C2846C B_ESCHR_COLI ICU TRUE
#> # … with 190 more rows
# }