P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-24 18:46:14 +01:00
Code Releases Activity

(v1.4.0.9025) is_new_episode()

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2020-11-23 21:50:27 +01:00
parent 363218da7e
commit b045b571a6
29 changed files with 706 additions and 366 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
DESCRIPTION
View File

@ -1,6 +1,6 @@
Package: AMR
Version: 1.4.0.9024
Date: 2020-11-17
Version: 1.4.0.9025
Date: 2020-11-23
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(role = c("aut", "cre"),

2
NAMESPACE
View File

@ -65,8 +65,6 @@ S3method(unique,mo)
S3method(unique,rsi)
export("%like%")
export("%like_case%")
export("%not_like%")
export("%not_like_case%")
export(ab_atc)
export(ab_atc_group1)
export(ab_atc_group2)

16
NEWS.md
View File

@ -1,14 +1,12 @@
# AMR 1.4.0.9024
## <small>Last updated: 17 November 2020</small>
# AMR 1.4.0.9025
## <small>Last updated: 23 November 2020</small>
### New
* Function `is_new_episode()` to determine patient episodes which are not necessarily based on microorganisms. It also supports grouped variables with e.g. `mutate()` and `summarise()` of the `dplyr` package:
* Function `is_new_episode()` to determine patient episodes which are not necessarily based on microorganisms. It also supports grouped variables with e.g. `mutate()`, `filter()` and `summarise()` of the `dplyr` package:
```r
example_isolates %>%
group_by(hospital_id) %>%
summarise(patients = n_distinct(patient_id),
n_episodes_365 = sum(is_new_episode(episode_days = 365)),
n_episodes_60 = sum(is_new_episode(episode_days = 60)))
example_isolates %>%
group_by(patient_id, hospital_id) %>%
filter(is_new_episode(date, episode_days = 60))
```
* Functions `mo_is_gram_negative()` and `mo_is_gram_positive()` as wrappers around `mo_gramstain()`. They always return `TRUE` or `FALSE` (except when the input is `NA` or the MO code is `UNKNOWN`), thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria. If you have the `dplyr` package installed, they can even determine the column with microorganisms themselves when used inside `dplyr` verbs:
```r
@ -22,7 +20,6 @@
filter(mo_is_intrinsic_resistant(ab = "Vancomycin"))
#> NOTE: Using column `mo` as input for mo_is_intrinsic_resistant()
```
* Functions `%not_like%` and `%not_like_case%` as wrappers around `%like%` and `%like_case%`. The RStudio addin to insert the text " %like% " as provided in this package now iterates over all like variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert ` %like% ` and by pressing it again it will be replaced with ` %not_like% `, etc.
### Changed
* Reference data used for `as.rsi()` can now be set by the user, using the `reference_data` parameter. This allows for using own interpretation guidelines.
@ -32,6 +29,7 @@
* Updated coagulase-negative staphylococci determination with Becker *et al.* 2020 (PMID 32056452), meaning that the species *S. argensis*, *S. caeli*, *S. debuckii*, *S. edaphicus* and *S. pseudoxylosus* are now all considered CoNS
* Fix for using parameter `reference_df` in `as.mo()` and `mo_*()` functions that contain old microbial codes (from previous package versions)
* Fix for using `as.rsi()` on a data.frame in older R versions
* `as.rsi()` on a data.frame will not print a message anymore if the values are already clean R/SI values
### Other
* All messages and warnings thrown by this package now break sentences on whole words

36
R/aa_helper_functions.R
View File

@ -71,41 +71,7 @@ addin_insert_in <- function() {
# No export, no Rd
addin_insert_like <- function() {
stop_ifnot_installed("rstudioapi")
# we want Ctrl/Cmd + L to iterate over %like%, %not_like% and %like_case%, so determine context first
getSourceEditorContext <- import_fn("getSourceEditorContext", "rstudioapi")
insertText <- import_fn("insertText", "rstudioapi")
modifyRange <- import_fn("insertText", "rstudioapi")
document_range <- import_fn("document_range", "rstudioapi")
document_position <- import_fn("document_position", "rstudioapi")
context <- getSourceEditorContext()
current_row <- context$selection[[1]]$range$end[1]
current_col <- context$selection[[1]]$range$end[2]
current_row_txt <- context$contents[current_row]
pos_preceded_by <- function(txt) {
substr(current_row_txt, current_col - nchar(txt), current_col) %like% paste0("^", txt)
}
replace_pos <- function(old, with) {
modifyRange(document_range(document_position(current_row, current_col - nchar(old)),
document_position(current_row, current_col)),
text = with,
id = context$id)
}
if (pos_preceded_by(" %like% ")) {
replace_pos(" %like% ", with = " %not_like% ")
} else if (pos_preceded_by(" %not_like% ")) {
replace_pos(" %not_like% ", with = " %like_case% ")
} else if (pos_preceded_by(" %like_case% ")) {
replace_pos(" %like_case% ", with = " %not_like_case% ")
} else if (pos_preceded_by(" %not_like_case% ")) {
replace_pos(" %not_like_case% ", with = " %like% ")
} else {
insertText(" %like% ")
}
import_fn("insertText", "rstudioapi")(" %like% ")
}
check_dataset_integrity <- function() {

130
R/first_isolate.R
View File

@ -25,7 +25,7 @@
#' Determine first (weighted) isolates
#'
#' Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use [is_new_episode()] that also supports grouping with the `dplyr` package, see *Examples*.
#' Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use [is_new_episode()] that also supports grouping with the `dplyr` package.
#' @inheritSection lifecycle Stable lifecycle
#' @param x,.data a [data.frame] containing isolates.
#' @param col_date column name of the result date (or date that is was received on the lab), defaults to the first column with a date class
@ -45,7 +45,7 @@
#' @param info print progress
#' @param include_unknown logical to determine whether 'unknown' microorganisms should be included too, i.e. microbial code `"UNKNOWN"`, which defaults to `FALSE`. For WHONET users, this means that all records with organism code `"con"` (*contamination*) will be excluded at default. Isolates with a microbial ID of `NA` will always be excluded as first isolate.
#' @param ... parameters passed on to the [first_isolate()] function
#' @details The [is_new_episode()] function is a wrapper around the [first_isolate()] function and can be used for data sets without isolates to just determine patient episodes based on any combination of grouping variables (using `dplyr`), please see *Examples*. Since it runs [first_isolate()] for every group, it is quite slow.
#' @details The [first_isolate()] function is a wrapper around the [is_new_episode()] function, but more efficient for data sets containing microorganism codes or names.
#'
#' All isolates with a microbial ID of `NA` will be excluded as first isolate.
#'
@ -130,42 +130,6 @@
#' # Gentamicin resistance in hospital D appears to be 3.7% higher than
#' # when you (erroneously) would have used all isolates for analysis.
#' }
#'
#' # filtering based on any other condition -----------------------------------
#'
#' if (require("dplyr")) {
#' # is_new_episode() can be used in dplyr verbs to determine patient
#' # episodes based on any (combination of) grouping variables:
#' example_isolates %>%
#' mutate(condition = sample(x = c("A", "B", "C"),
#' size = 2000,
#' replace = TRUE)) %>%
#' group_by(condition) %>%
#' mutate(new_episode = is_new_episode())
#'
#' example_isolates %>%
#' group_by(hospital_id) %>%
#' summarise(patients = n_distinct(patient_id),
#' n_episodes_365 = sum(is_new_episode(episode_days = 365)),
#' n_episodes_60 = sum(is_new_episode(episode_days = 60)),
#' n_episodes_30 = sum(is_new_episode(episode_days = 30)))
#'
#'
#' # grouping on microorganisms leads to the same results as first_isolate():
#' x <- example_isolates %>%
#' filter_first_isolate(include_unknown = TRUE)
#'
#' y <- example_isolates %>%
#' group_by(mo) %>%
#' filter(is_new_episode())
#'
#' identical(x$patient_id, y$patient_id)
#'
#' # but now you can group on isolates and many more:
#' example_isolates %>%
#' group_by(mo, hospital_id, ward_icu) %>%
#' mutate(flag_episode = is_new_episode())
#' }
#' }
first_isolate <- function(x,
col_date = NULL,
@ -375,28 +339,6 @@ first_isolate <- function(x,
scope.size <- nrow(x[which(x$newvar_row_index_sorted %in% c(row.start + 1:row.end) &
!is.na(x$newvar_mo)), , drop = FALSE])
identify_new_year <- function(x, episode_days) {
# I asked on StackOverflow:
# https://stackoverflow.com/questions/42122245/filter-one-row-every-year
if (length(x) == 1) {
return(TRUE)
}
indices <- integer(0)
start <- x[1]
ind <- 1
indices[ind] <- ind
for (i in 2:length(x)) {
if (isTRUE(as.numeric(x[i] - start) >= episode_days)) {
ind <- ind + 1
indices[ind] <- i
start <- x[i]
}
}
result <- rep(FALSE, length(x))
result[indices] <- TRUE
return(result)
}
# Analysis of first isolate ----
x$other_pat_or_mo <- ifelse(x$newvar_patient_id == pm_lag(x$newvar_patient_id) &
x$newvar_genus_species == pm_lag(x$newvar_genus_species),
@ -407,8 +349,8 @@ first_isolate <- function(x,
function(g,
df = x,
days = episode_days) {
identify_new_year(x = df[which(df$episode_group == g), "newvar_date", drop = TRUE],
episode_days = days)
is_new_episode(x = df[which(df$episode_group == g), ]$newvar_date,
episode_days = days)
}))
weighted.notice <- ""
@ -572,67 +514,5 @@ filter_first_weighted_isolate <- function(x,
subset(x, first_isolate(x = y,
col_date = col_date,
col_patient_id = col_patient_id,
...))
}
#' @rdname first_isolate
#' @export
is_new_episode <- function(.data,
episode_days = 365,
col_date = NULL,
col_patient_id = NULL) {
if (missing(.data)) {
# look it up - this also supports grouping variables
cur_data <- import_fn("cur_data", "dplyr", error_on_fail = FALSE)
if (is.null(cur_data)) {
stop_("parameter '.data' not set.")
}
.data <- cur_data()
}
meet_criteria(.data, allow_class = "data.frame") # also checks dimensions to be >0
meet_criteria(col_date, allow_class = "character", has_length = 1, allow_NULL = TRUE, is_in = colnames(x))
meet_criteria(col_patient_id, allow_class = "character", has_length = 1, allow_NULL = TRUE, is_in = colnames(x))
meet_criteria(episode_days, allow_class = c("numeric", "integer"), has_length = 1)
# get i'th ID of group, so notices will only be thrown once
cur_group_id <- import_fn("cur_group_id", "dplyr", error_on_fail = FALSE)
first_group <- tryCatch(is.null(cur_group_id) || cur_group_id() == 1,
error = function(e) TRUE)
# try to find columns based on type
# -- date
if (is.null(col_date)) {
col_date <- search_type_in_df(x = .data,
type = "date",
info = first_group)
stop_if(is.null(col_date), "`col_date` must be set")
}
# -- patient id
if (is.null(col_patient_id)) {
if (all(c("First name", "Last name", "Sex") %in% colnames(.data))) {
# WHONET support
.data$patient_id <- paste(.data$`First name`, .data$`Last name`, .data$Sex)
col_patient_id <- "patient_id"
if (is.null(cur_group_id) || cur_group_id() == 1) {
message_("Using combined columns `", font_bold("First name"), "`, `", font_bold("Last name"), "` and `", font_bold("Sex"), "` as input for `col_patient_id`")
}
} else {
col_patient_id <- search_type_in_df(x = .data,
type = "patient_id",
info = first_group)
}
stop_if(is.null(col_patient_id), "`col_patient_id` must be set")
}
# create any random mo, so first isolates can be calculated
.data$a94a8fe5 <- as.mo("Escherichia coli")
first_isolate(.data,
col_date = col_date,
col_patient_id = col_patient_id,
episode_days = episode_days,
col_mo = "a94a8fe5",
info = FALSE)
col_patient_id = col_patient_id))
}

129
R/is_new_episode.R Normal file
View File

@ -0,0 +1,129 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis for R #
# #
# SOURCE #
# https://github.com/msberends/AMR #
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
#' Determine (new) episodes for patients
#'
#' This function determines which items in a vector can be considered (the start of) a new episode, based on the parameter `episode_days`. This can be used to determine clinical episodes for any epidemiological analysis.
#' @inheritSection lifecycle Experimental lifecycle
#' @param x vector of dates (class `Date` or `POSIXt`)
#' @param episode_days length of the required episode in days, defaults to 365. Every element in the input will return `TRUE` after this number of days has passed since the last included date, independent of calendar years. Please see *Details*.
#' @param ... arguments passed on to [as.Date()]
#' @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 `dplyr` package is not required for this function to work, but this function works conveniently inside `dplyr` verbs such as [filter()], [mutate()] and [summarise()].
#' @return a [logical] vector
#' @export
#' @inheritSection AMR Read more on our website!
#' @examples
#' # `example_isolates` is a dataset available in the AMR package.
#' # See ?example_isolates.
#'
#' is_new_episode(example_isolates$date)
#' is_new_episode(example_isolates$date, episode_days = 60)
#'
#' if (require("dplyr")) {
#' # is_new_episode() can also be used in dplyr verbs to determine patient
#' # episodes based on any (combination of) grouping variables:
#' example_isolates %>%
#' mutate(condition = sample(x = c("A", "B", "C"),
#' size = 2000,
#' replace = TRUE)) %>%
#' group_by(condition) %>%
#' mutate(new_episode = is_new_episode(date))
#'
#' example_isolates %>%
#' group_by(hospital_id) %>%
#' summarise(patients = n_distinct(patient_id),
#' 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)))
#'
#'
#' # grouping on patients and microorganisms leads to the same results
#' # as first_isolate():
#' x <- example_isolates %>%
#' filter(first_isolate(., include_unknown = TRUE))
#'
#' y <- example_isolates %>%
#' group_by(patient_id, mo) %>%
#' filter(is_new_episode(date))
#'
#' identical(x$patient_id, y$patient_id)
#'
#' # but is_new_episode() has a lot more flexibility than first_isolate(),
#' # since you can now group on anything that seems relevant:
#' example_isolates %>%
#' group_by(patient_id, mo, hospital_id, ward_icu) %>%
#' mutate(flag_episode = is_new_episode(date))
#' }
is_new_episode <- function(x, episode_days = 365, ...) {
meet_criteria(x, allow_class = c("Date", "POSIXt"))
meet_criteria(episode_days, allow_class = c("numeric", "double", "integer"), has_length = 1)
x <- as.double(as.Date(x, ...)) # as.Date() for POSIX classes
if (length(x) == 1) {
return(TRUE)
}
if (length(x) == 2 && max(x) - min(x) >= episode_days) {
return(rep(TRUE, 2))
}
# I asked on StackOverflow:
# https://stackoverflow.com/questions/42122245/filter-one-row-every-year
exec <- function(x, episode_days) {
if (length(x) == 1) {
return(TRUE)
} else if (length(x) == 2) {
if (max(x) - min(x) >= episode_days) {
return(c(TRUE, TRUE))
} else {
return(c(TRUE, FALSE))
}
}
indices <- integer()
start <- x[1]
ind <- 1
indices[1] <- 1
for (i in 2:length(x)) {
if (isTRUE((x[i] - start) >= episode_days)) {
ind <- ind + 1
indices[ind] <- i
start <- x[i]
}
}
result <- rep(FALSE, length(x))
result[indices] <- TRUE
result
}
df <- data.frame(x = x,
y = seq_len(length(x))) %pm>%
pm_arrange(x)
df$new <- exec(df$x, episode_days)
df %pm>%
pm_arrange(y) %pm>%
pm_pull(new)
}

25
R/like.R
View File

@ -41,9 +41,7 @@
#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed
#' * Tries again with `perl = TRUE` if regex fails
#'
#' Using RStudio? This function can also be inserted in your code from the Addins menu and can have its own Keyboard Shortcut like `Ctrl+Shift+L` or `Cmd+Shift+L` (see `Tools` > `Modify Keyboard Shortcuts...`). This addin iterates over all 'like' variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert ` %like% ` and by pressing it again it will be replaced with ` %not_like% `, then ` %like_case% `, then ` %not_like_case% ` and then back to ` %like% `.
#'
#' The `"%not_like%"` and `"%not_like_case%"` functions are wrappers around `"%like%"` and `"%like_case%"`.
#' Using RStudio? The text `%like%` can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like `Ctrl+Shift+L` or `Cmd+Shift+L` (see `Tools` > `Modify Keyboard Shortcuts...`).
#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/master/R/like.R)
#' @seealso [grep()]
#' @inheritSection AMR Read more on our website!
@ -67,11 +65,6 @@
#' if (require("dplyr")) {
#' example_isolates %>%
#' filter(mo_name(mo) %like% "^ent")
#'
#' example_isolates %>%
#' mutate(group = case_when(hospital_id %like% "A|D" ~ "Group 1",
#' mo_name(mo) %not_like% "^Staph" ~ "Group 2a",
#' TRUE ~ "Group 2b"))
#' }
#' }
like <- function(x, pattern, ignore.case = TRUE) {
@ -157,14 +150,6 @@ like <- function(x, pattern, ignore.case = TRUE) {
like(x, pattern, ignore.case = TRUE)
}
#' @rdname like
#' @export
"%not_like%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
meet_criteria(pattern, allow_NA = FALSE)
!like(x, pattern, ignore.case = TRUE)
}
#' @rdname like
#' @export
"%like_case%" <- function(x, pattern) {
@ -173,14 +158,6 @@ like <- function(x, pattern, ignore.case = TRUE) {
like(x, pattern, ignore.case = FALSE)
}
#' @rdname like
#' @export
"%not_like_case%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
meet_criteria(pattern, allow_NA = FALSE)
!like(x, pattern, ignore.case = FALSE)
}
"%like_perl%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
meet_criteria(pattern, allow_NA = FALSE)

19
R/rsi.R
View File

@ -614,13 +614,18 @@ as.rsi.data.frame <- function(x,
} else if (types[i] == "rsi") {
ab <- ab_cols[i]
ab_coerced <- suppressWarnings(as.ab(ab))
message_("=> Cleaning values in column `", font_bold(ab), "` (",
ifelse(ab_coerced != ab, paste0(ab_coerced, ", "), ""),
ab_name(ab_coerced, tolower = TRUE), ")... ",
appendLF = FALSE,
as_note = FALSE)
x[, ab_cols[i]] <- as.rsi.default(x = x %pm>% pm_pull(ab_cols[i]))
message_(" OK.", add_fn = list(font_green, font_bold), as_note = FALSE)
if (!all(x[, ab_cols[i], drop = TRUE] %in% c("R", "S", "I"), na.rm = TRUE)) {
# only print message if values are not already clean
message_("=> Cleaning values in column `", font_bold(ab), "` (",
ifelse(ab_coerced != ab, paste0(ab_coerced, ", "), ""),
ab_name(ab_coerced, tolower = TRUE), ")... ",
appendLF = FALSE,
as_note = FALSE)
}
x[, ab_cols[i]] <- as.rsi.default(x = as.character(x[, ab_cols[i], drop = TRUE]))
if (!all(x[, ab_cols[i], drop = TRUE] %in% c("R", "S", "I"), na.rm = TRUE)) {
message_(" OK.", add_fn = list(font_green, font_bold), as_note = FALSE)
}
}
}

20
_pkgdown.yml
View File

@ -147,11 +147,12 @@ reference:
- title: "Analysing data: antimicrobial resistance"
desc: >
Use these function for the analysis part. You can use `susceptibility()` or `resistance()` on any antibiotic column.
Be sure to first select the isolates that are appropiate for analysis, by using `first_isolate()`.
Be sure to first select the isolates that are appropiate for analysis, by using `first_isolate()` or `is_new_episode()`.
You can also filter your data on certain resistance in certain antibiotic classes (`filter_ab_class()`), or determine multi-drug resistant microorganisms (MDRO, `mdro()`).
contents:
- "`proportion`"
- "`count`"
- "`is_new_episode`"
- "`first_isolate`"
- "`key_antibiotics`"
- "`mdro`"
@ -181,20 +182,19 @@ reference:
- title: "Other: statistical tests"
desc: >
Some statistical tests or methods are not part of base R and are added to this package for convenience.
Some statistical tests or methods are not part of base R and were added to this package for convenience.
contents:
- "`g.test`"
- "`kurtosis`"
- "`skewness`"
- "`p_symbol`"
# - title: "Other: deprecated functions"
# desc: >
# These functions are deprecated, meaning that they will still
# work but show a warning with every use and will be removed
# in a future version.
# contents:
# - "`AMR-deprecated`"
- title: "Other: deprecated functions"
desc: >
These functions are deprecated, meaning that they will still
work but show a warning with every use and will be removed
in a future version.
contents:
- "`AMR-deprecated`"
authors:
Matthijs S. Berends:

2
docs/404.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="https://msberends.github.io/AMR//index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

2
docs/LICENSE-text.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

2
docs/articles/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

2
docs/authors.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

2
docs/index.html
View File

@ -43,7 +43,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

17
docs/news/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>
@ -236,19 +236,19 @@
<small>Source: <a href='https://github.com/msberends/AMR/blob/master/NEWS.md'><code>NEWS.md</code></a></small>
</div>
<div id="amr-1409024" class="section level1">
<h1 class="page-header" data-toc-text="1.4.0.9024">
<a href="#amr-1409024" class="anchor"></a>AMR 1.4.0.9024<small> Unreleased </small>
<div id="amr-1409025" class="section level1">
<h1 class="page-header" data-toc-text="1.4.0.9025">
<a href="#amr-1409025" class="anchor"></a>AMR 1.4.0.9025<small> Unreleased </small>
</h1>
<div id="last-updated-17-november-2020" class="section level2">
<div id="last-updated-23-november-2020" class="section level2">
<h2 class="hasAnchor">
<a href="#last-updated-17-november-2020" class="anchor"></a><small>Last updated: 17 November 2020</small>
<a href="#last-updated-23-november-2020" class="anchor"></a><small>Last updated: 23 November 2020</small>
</h2>
<div id="new" class="section level3">
<h3 class="hasAnchor">
<a href="#new" class="anchor"></a>New</h3>
<ul>
<li><p>Function <code><a href="../reference/first_isolate.html">is_new_episode()</a></code> to determine patient episodes which are not necessarily based on microorganisms. It also supports grouped variables with e.g. <code><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate()</a></code> and <code><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarise()</a></code> of the <code>dplyr</code> package: <code>r example_isolates %&gt;% group_by(hospital_id) %&gt;% summarise(patients = n_distinct(patient_id), n_episodes_365 = sum(is_new_episode(episode_days = 365)), n_episodes_60 = sum(is_new_episode(episode_days = 60)))</code></p></li>
<li><p>Function <code><a href="../reference/is_new_episode.html">is_new_episode()</a></code> to determine patient episodes which are not necessarily based on microorganisms. It also supports grouped variables with e.g. <code><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate()</a></code>, <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> and <code><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarise()</a></code> of the <code>dplyr</code> package: <code>r example_isolates %&gt;% group_by(patient_id, hospital_id) %&gt;% filter(is_new_episode(date, episode_days = 60))</code></p></li>
<li>
<p>Functions <code><a href="../reference/mo_property.html">mo_is_gram_negative()</a></code> and <code><a href="../reference/mo_property.html">mo_is_gram_positive()</a></code> as wrappers around <code><a href="../reference/mo_property.html">mo_gramstain()</a></code>. They always return <code>TRUE</code> or <code>FALSE</code> (except when the input is <code>NA</code> or the MO code is <code>UNKNOWN</code>), thus always return <code>FALSE</code> for species outside the taxonomic kingdom of Bacteria. If you have the <code>dplyr</code> package installed, they can even determine the column with microorganisms themselves when used inside <code>dplyr</code> verbs:</p>
<div class="sourceCode" id="cb1"><pre class="downlit">
@ -263,7 +263,6 @@
<span class="fu"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span><span class="op">(</span><span class="fu"><a href="../reference/mo_property.html">mo_is_intrinsic_resistant</a></span><span class="op">(</span>ab <span class="op">=</span> <span class="st">"Vancomycin"</span><span class="op">)</span><span class="op">)</span>
<span class="co">#&gt; NOTE: Using column `mo` as input for mo_is_intrinsic_resistant()</span></pre></div>
</li>
<li><p>Functions <code><a href="../reference/like.html">%not_like%</a></code> and <code><a href="../reference/like.html">%not_like_case%</a></code> as wrappers around <code><a href="../reference/like.html">%like%</a></code> and <code><a href="../reference/like.html">%like_case%</a></code>. The RStudio addin to insert the text " %like% " as provided in this package now iterates over all like variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert <code><a href="../reference/like.html">%like%</a></code> and by pressing it again it will be replaced with <code><a href="../reference/like.html">%not_like%</a></code>, etc.</p></li>
</ul>
</div>
<div id="changed" class="section level3">
@ -277,6 +276,8 @@
<li>Updated coagulase-negative staphylococci determination with Becker <em>et al.</em> 2020 (PMID 32056452), meaning that the species <em>S. argensis</em>, <em>S. caeli</em>, <em>S. debuckii</em>, <em>S. edaphicus</em> and <em>S. pseudoxylosus</em> are now all considered CoNS</li>
<li>Fix for using parameter <code>reference_df</code> in <code><a href="../reference/as.mo.html">as.mo()</a></code> and <code>mo_*()</code> functions that contain old microbial codes (from previous package versions)</li>
<li>Fix for using <code><a href="../reference/as.rsi.html">as.rsi()</a></code> on a data.frame in older R versions</li>
<li>
<code><a href="../reference/as.rsi.html">as.rsi()</a></code> on a data.frame will not print a message anymore if the values are already clean R/SI values</li>
</ul>
</div>
<div id="other" class="section level3">

2
docs/pkgdown.yml
View File

@ -12,7 +12,7 @@ articles:
datasets: datasets.html
resistance_predict: resistance_predict.html
welcome_to_AMR: welcome_to_AMR.html
last_built: 2020-11-17T15:56Z
last_built: 2020-11-23T20:45Z
urls:
reference: https://msberends.github.io/AMR//reference
article: https://msberends.github.io/AMR//articles

51
docs/reference/first_isolate.html
View File

@ -49,7 +49,7 @@
<script src="../extra.js"></script>
<meta property="og:title" content="Determine first (weighted) isolates — first_isolate" />
<meta property="og:description" content="Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use is_new_episode() that also supports grouping with the dplyr package, see Examples." />
<meta property="og:description" content="Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use is_new_episode() that also supports grouping with the dplyr package." />
<meta property="og:image" content="https://msberends.github.io/AMR/logo.png" />
@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>
@ -239,7 +239,7 @@
</div>
<div class="ref-description">
<p>Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use <code>is_new_episode()</code> that also supports grouping with the <code>dplyr</code> package, see <em>Examples</em>.</p>
<p>Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use <code><a href='is_new_episode.html'>is_new_episode()</a></code> that also supports grouping with the <code>dplyr</code> package.</p>
</div>
<pre class="usage"><span class='fu'>first_isolate</span><span class='op'>(</span>
@ -278,13 +278,6 @@
col_mo <span class='op'>=</span> <span class='cn'>NULL</span>,
col_keyantibiotics <span class='op'>=</span> <span class='cn'>NULL</span>,
<span class='va'>...</span>
<span class='op'>)</span>
<span class='fu'>is_new_episode</span><span class='op'>(</span>
<span class='va'>.data</span>,
episode_days <span class='op'>=</span> <span class='fl'>365</span>,
col_date <span class='op'>=</span> <span class='cn'>NULL</span>,
col_patient_id <span class='op'>=</span> <span class='cn'>NULL</span>
<span class='op'>)</span></pre>
<h2 class="hasAnchor" id="arguments"><a class="anchor" href="#arguments"></a>Arguments</h2>
@ -373,7 +366,7 @@
<p>A <code><a href='https://rdrr.io/r/base/logical.html'>logical</a></code> vector</p>
<h2 class="hasAnchor" id="details"><a class="anchor" href="#details"></a>Details</h2>
<p>The <code>is_new_episode()</code> function is a wrapper around the <code>first_isolate()</code> function and can be used for data sets without isolates to just determine patient episodes based on any combination of grouping variables (using <code>dplyr</code>), please see <em>Examples</em>. Since it runs <code>first_isolate()</code> for every group, it is quite slow.</p>
<p>The <code>first_isolate()</code> function is a wrapper around the <code><a href='is_new_episode.html'>is_new_episode()</a></code> function, but more efficient for data sets containing microorganism codes or names.</p>
<p>All isolates with a microbial ID of <code>NA</code> will be excluded as first isolate.</p><h3 class='hasAnchor' id='arguments'><a class='anchor' href='#arguments'></a>Why this is so important</h3>
@ -462,42 +455,6 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
<span class='co'># Gentamicin resistance in hospital D appears to be 3.7% higher than</span>
<span class='co'># when you (erroneously) would have used all isolates for analysis.</span>
<span class='op'>}</span>
<span class='co'># filtering based on any other condition -----------------------------------</span>
<span class='kw'>if</span> <span class='op'>(</span><span class='kw'><a href='https://rdrr.io/r/base/library.html'>require</a></span><span class='op'>(</span><span class='st'><a href='https://dplyr.tidyverse.org'>"dplyr"</a></span><span class='op'>)</span><span class='op'>)</span> <span class='op'>{</span>
<span class='co'># is_new_episode() can be used in dplyr verbs to determine patient</span>
<span class='co'># episodes based on any (combination of) grouping variables:</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>condition <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sample.html'>sample</a></span><span class='op'>(</span>x <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/c.html'>c</a></span><span class='op'>(</span><span class='st'>"A"</span>, <span class='st'>"B"</span>, <span class='st'>"C"</span><span class='op'>)</span>,
size <span class='op'>=</span> <span class='fl'>2000</span>,
replace <span class='op'>=</span> <span class='cn'>TRUE</span><span class='op'>)</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>condition</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>new_episode <span class='op'>=</span> <span class='fu'>is_new_episode</span><span class='op'>(</span><span class='op'>)</span><span class='op'>)</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>hospital_id</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/summarise.html'>summarise</a></span><span class='op'>(</span>patients <span class='op'>=</span> <span class='fu'><a href='https://dplyr.tidyverse.org/reference/n_distinct.html'>n_distinct</a></span><span class='op'>(</span><span class='va'>patient_id</span><span class='op'>)</span>,
n_episodes_365 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span>episode_days <span class='op'>=</span> <span class='fl'>365</span><span class='op'>)</span><span class='op'>)</span>,
n_episodes_60 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span>episode_days <span class='op'>=</span> <span class='fl'>60</span><span class='op'>)</span><span class='op'>)</span>,
n_episodes_30 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span>episode_days <span class='op'>=</span> <span class='fl'>30</span><span class='op'>)</span><span class='op'>)</span><span class='op'>)</span>
<span class='co'># grouping on microorganisms leads to the same results as first_isolate():</span>
<span class='va'>x</span> <span class='op'>&lt;-</span> <span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'>filter_first_isolate</span><span class='op'>(</span>include_unknown <span class='op'>=</span> <span class='cn'>TRUE</span><span class='op'>)</span>
<span class='va'>y</span> <span class='op'>&lt;-</span> <span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>mo</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='op'>)</span><span class='op'>)</span>
<span class='fu'><a href='https://rdrr.io/r/base/identical.html'>identical</a></span><span class='op'>(</span><span class='va'>x</span><span class='op'>$</span><span class='va'>patient_id</span>, <span class='va'>y</span><span class='op'>$</span><span class='va'>patient_id</span><span class='op'>)</span>
<span class='co'># but now you can group on isolates and many more:</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>mo</span>, <span class='va'>hospital_id</span>, <span class='va'>ward_icu</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>flag_episode <span class='op'>=</span> <span class='fu'>is_new_episode</span><span class='op'>(</span><span class='op'>)</span><span class='op'>)</span>
<span class='op'>}</span>
<span class='co'># }</span>
</pre>
</div>

31
docs/reference/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>
@ -455,7 +455,7 @@
<tr>
<th colspan="2">
<h2 id="section-analysing-data-antimicrobial-resistance" class="hasAnchor"><a href="#section-analysing-data-antimicrobial-resistance" class="anchor"></a>Analysing data: antimicrobial resistance</h2>
<p class="section-desc"><p>Use these function for the analysis part. You can use <code><a href="../reference/proportion.html">susceptibility()</a></code> or <code><a href="../reference/proportion.html">resistance()</a></code> on any antibiotic column. Be sure to first select the isolates that are appropiate for analysis, by using <code><a href="../reference/first_isolate.html">first_isolate()</a></code>. You can also filter your data on certain resistance in certain antibiotic classes (<code><a href="../reference/filter_ab_class.html">filter_ab_class()</a></code>), or determine multi-drug resistant microorganisms (MDRO, <code><a href="../reference/mdro.html">mdro()</a></code>).</p></p>
<p class="section-desc"><p>Use these function for the analysis part. You can use <code><a href="../reference/proportion.html">susceptibility()</a></code> or <code><a href="../reference/proportion.html">resistance()</a></code> on any antibiotic column. Be sure to first select the isolates that are appropiate for analysis, by using <code><a href="../reference/first_isolate.html">first_isolate()</a></code> or <code><a href="../reference/is_new_episode.html">is_new_episode()</a></code>. You can also filter your data on certain resistance in certain antibiotic classes (<code><a href="../reference/filter_ab_class.html">filter_ab_class()</a></code>), or determine multi-drug resistant microorganisms (MDRO, <code><a href="../reference/mdro.html">mdro()</a></code>).</p></p>
</th>
</tr>
@ -478,7 +478,13 @@
</tr><tr>
<td>
<p><code><a href="first_isolate.html">first_isolate()</a></code> <code><a href="first_isolate.html">filter_first_isolate()</a></code> <code><a href="first_isolate.html">filter_first_weighted_isolate()</a></code> <code><a href="first_isolate.html">is_new_episode()</a></code> </p>
<p><code><a href="is_new_episode.html">is_new_episode()</a></code> </p>
</td>
<td><p>Determine (new) episodes for patients</p></td>
</tr><tr>
<td>
<p><code><a href="first_isolate.html">first_isolate()</a></code> <code><a href="first_isolate.html">filter_first_isolate()</a></code> <code><a href="first_isolate.html">filter_first_weighted_isolate()</a></code> </p>
</td>
<td><p>Determine first (weighted) isolates</p></td>
</tr><tr>
@ -581,7 +587,7 @@
</tr><tr>
<td>
<p><code><a href="like.html">like()</a></code> <code><a href="like.html">`%like%`</a></code> <code><a href="like.html">`%not_like%`</a></code> <code><a href="like.html">`%like_case%`</a></code> <code><a href="like.html">`%not_like_case%`</a></code> </p>
<p><code><a href="like.html">like()</a></code> <code><a href="like.html">`%like%`</a></code> <code><a href="like.html">`%like_case%`</a></code> </p>
</td>
<td><p>Pattern matching with keyboard shortcut</p></td>
</tr><tr>
@ -601,7 +607,7 @@
<tr>
<th colspan="2">
<h2 id="section-other-statistical-tests" class="hasAnchor"><a href="#section-other-statistical-tests" class="anchor"></a>Other: statistical tests</h2>
<p class="section-desc"><p>Some statistical tests or methods are not part of base R and are added to this package for convenience.</p></p>
<p class="section-desc"><p>Some statistical tests or methods are not part of base R and were added to this package for convenience.</p></p>
</th>
</tr>
@ -627,7 +633,20 @@
<p><code><a href="skewness.html">skewness()</a></code> </p>
</td>
<td><p>Skewness of the sample</p></td>
</tr><tr>
</tr>
</tbody><tbody>
<tr>
<th colspan="2">
<h2 id="section-other-deprecated-functions" class="hasAnchor"><a href="#section-other-deprecated-functions" class="anchor"></a>Other: deprecated functions</h2>
<p class="section-desc"><p>These functions are deprecated, meaning that they will still work but show a warning with every use and will be removed in a future version.</p></p>
</th>
</tr>
</tbody><tbody>
<tr>
<td>
<p><code><a href="AMR-deprecated.html">p_symbol()</a></code> </p>

348
docs/reference/is_new_episode.html Normal file
View File

@ -0,0 +1,348 @@
<!-- Generated by pkgdown: do not edit by hand -->
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Determine (new) episodes for patients — is_new_episode • AMR (for R)</title>
<!-- favicons -->
<link rel="icon" type="image/png" sizes="16x16" href="../favicon-16x16.png">
<link rel="icon" type="image/png" sizes="32x32" href="../favicon-32x32.png">
<link rel="apple-touch-icon" type="image/png" sizes="180x180" href="../apple-touch-icon.png" />
<link rel="apple-touch-icon" type="image/png" sizes="120x120" href="../apple-touch-icon-120x120.png" />
<link rel="apple-touch-icon" type="image/png" sizes="76x76" href="../apple-touch-icon-76x76.png" />
<link rel="apple-touch-icon" type="image/png" sizes="60x60" href="../apple-touch-icon-60x60.png" />
<!-- jquery -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.4.1/jquery.min.js" integrity="sha256-CSXorXvZcTkaix6Yvo6HppcZGetbYMGWSFlBw8HfCJo=" crossorigin="anonymous"></script>
<!-- Bootstrap -->
<link href="https://cdnjs.cloudflare.com/ajax/libs/bootswatch/3.4.0/flatly/bootstrap.min.css" rel="stylesheet" crossorigin="anonymous" />
<script src="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/3.4.1/js/bootstrap.min.js" integrity="sha256-nuL8/2cJ5NDSSwnKD8VqreErSWHtnEP9E7AySL+1ev4=" crossorigin="anonymous"></script>
<!-- bootstrap-toc -->
<link rel="stylesheet" href="../bootstrap-toc.css">
<script src="../bootstrap-toc.js"></script>
<!-- Font Awesome icons -->
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.12.1/css/all.min.css" integrity="sha256-mmgLkCYLUQbXn0B1SRqzHar6dCnv9oZFPEC1g1cwlkk=" crossorigin="anonymous" />
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.12.1/css/v4-shims.min.css" integrity="sha256-wZjR52fzng1pJHwx4aV2AO3yyTOXrcDW7jBpJtTwVxw=" crossorigin="anonymous" />
<!-- clipboard.js -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/clipboard.js/2.0.6/clipboard.min.js" integrity="sha256-inc5kl9MA1hkeYUt+EC3BhlIgyp/2jDIyBLS6k3UxPI=" crossorigin="anonymous"></script>
<!-- headroom.js -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/headroom/0.11.0/headroom.min.js" integrity="sha256-AsUX4SJE1+yuDu5+mAVzJbuYNPHj/WroHuZ8Ir/CkE0=" crossorigin="anonymous"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/headroom/0.11.0/jQuery.headroom.min.js" integrity="sha256-ZX/yNShbjqsohH1k95liqY9Gd8uOiE1S4vZc+9KQ1K4=" crossorigin="anonymous"></script>
<!-- pkgdown -->
<link href="../pkgdown.css" rel="stylesheet">
<script src="../pkgdown.js"></script>
<link href="../extra.css" rel="stylesheet">
<script src="../extra.js"></script>
<meta property="og:title" content="Determine (new) episodes for patients — is_new_episode" />
<meta property="og:description" content="This function determines which items in a vector can be considered (the start of) a new episode, based on the parameter episode_days. This can be used to determine clinical episodes for any epidemiological analysis." />
<meta property="og:image" content="https://msberends.github.io/AMR/logo.png" />
<!-- mathjax -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js" integrity="sha256-nvJJv9wWKEm88qvoQl9ekL2J+k/RWIsaSScxxlsrv8k=" crossorigin="anonymous"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/config/TeX-AMS-MML_HTMLorMML.js" integrity="sha256-84DKXVJXs0/F8OTMzX4UR909+jtl4G7SPypPavF+GfA=" crossorigin="anonymous"></script>
<!--[if lt IE 9]>
<script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js"></script>
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
<![endif]-->
</head>
<body data-spy="scroll" data-target="#toc">
<div class="container template-reference-topic">
<header>
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar" aria-expanded="false">
<span class="sr-only">Toggle navigation</span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul class="nav navbar-nav">
<li>
<a href="../index.html">
<span class="fa fa-home"></span>
Home
</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<span class="fa fa-question-circle"></span>
How to
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="../articles/AMR.html">
<span class="fa fa-directions"></span>
Conduct AMR analysis
</a>
</li>
<li>
<a href="../articles/resistance_predict.html">
<span class="fa fa-dice"></span>
Predict antimicrobial resistance
</a>
</li>
<li>
<a href="../articles/datasets.html">
<span class="fa fa-database"></span>
Data sets for download / own use
</a>
</li>
<li>
<a href="../articles/PCA.html">
<span class="fa fa-compress"></span>
Conduct principal component analysis for AMR
</a>
</li>
<li>
<a href="../articles/MDR.html">
<span class="fa fa-skull-crossbones"></span>
Determine multi-drug resistance (MDR)
</a>
</li>
<li>
<a href="../articles/WHONET.html">
<span class="fa fa-globe-americas"></span>
Work with WHONET data
</a>
</li>
<li>
<a href="../articles/SPSS.html">
<span class="fa fa-file-upload"></span>
Import data from SPSS/SAS/Stata
</a>
</li>
<li>
<a href="../articles/EUCAST.html">
<span class="fa fa-exchange-alt"></span>
Apply EUCAST rules
</a>
</li>
<li>
<a href="../reference/mo_property.html">
<span class="fa fa-bug"></span>
Get properties of a microorganism
</a>
</li>
<li>
<a href="../reference/ab_property.html">
<span class="fa fa-capsules"></span>
Get properties of an antibiotic
</a>
</li>
<li>
<a href="../articles/benchmarks.html">
<span class="fa fa-shipping-fast"></span>
Other: benchmarks
</a>
</li>
</ul>
</li>
<li>
<a href="../reference/index.html">
<span class="fa fa-book-open"></span>
Manual
</a>
</li>
<li>
<a href="../authors.html">
<span class="fa fa-users"></span>
Authors
</a>
</li>
<li>
<a href="../news/index.html">
<span class="far fa far fa-newspaper"></span>
Changelog
</a>
</li>
</ul>
<ul class="nav navbar-nav navbar-right">
<li>
<a href="https://github.com/msberends/AMR">
<span class="fab fa fab fa-github"></span>
Source Code
</a>
</li>
<li>
<a href="../survey.html">
<span class="fa fa-clipboard-list"></span>
Survey
</a>
</li>
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
</header>
<div class="row">
<div class="col-md-9 contents">
<div class="page-header">
<h1>Determine (new) episodes for patients</h1>
<small class="dont-index">Source: <a href='https://github.com/msberends/AMR/blob/master/R/is_new_episode.R'><code>R/is_new_episode.R</code></a></small>
<div class="hidden name"><code>is_new_episode.Rd</code></div>
</div>
<div class="ref-description">
<p>This function determines which items in a vector can be considered (the start of) a new episode, based on the parameter <code>episode_days</code>. This can be used to determine clinical episodes for any epidemiological analysis.</p>
</div>
<pre class="usage"><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>x</span>, episode_days <span class='op'>=</span> <span class='fl'>365</span>, <span class='va'>...</span><span class='op'>)</span></pre>
<h2 class="hasAnchor" id="arguments"><a class="anchor" href="#arguments"></a>Arguments</h2>
<table class="ref-arguments">
<colgroup><col class="name" /><col class="desc" /></colgroup>
<tr>
<th>x</th>
<td><p>vector of dates (class <code>Date</code> or <code>POSIXt</code>)</p></td>
</tr>
<tr>
<th>episode_days</th>
<td><p>length of the required episode in days, defaults to 365. Every element in the input will return <code>TRUE</code> after this number of days has passed since the last included date, independent of calendar years. Please see <em>Details</em>.</p></td>
</tr>
<tr>
<th>...</th>
<td><p>arguments passed on to <code><a href='https://rdrr.io/r/base/as.Date.html'>as.Date()</a></code></p></td>
</tr>
</table>
<h2 class="hasAnchor" id="value"><a class="anchor" href="#value"></a>Value</h2>
<p>a <a href='https://rdrr.io/r/base/logical.html'>logical</a> vector</p>
<h2 class="hasAnchor" id="details"><a class="anchor" href="#details"></a>Details</h2>
<p>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 <code>episode_days</code> 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 <code>episode_days</code> 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.</p>
<p>The <code>dplyr</code> package is not required for this function to work, but this function works conveniently inside <code>dplyr</code> verbs such as <code><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter()</a></code>, <code><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate()</a></code> and <code><a href='https://dplyr.tidyverse.org/reference/summarise.html'>summarise()</a></code>.</p>
<h2 class="hasAnchor" id="experimental-lifecycle"><a class="anchor" href="#experimental-lifecycle"></a>Experimental lifecycle</h2>
<p><img src='figures/lifecycle_experimental.svg' style=margin-bottom:5px /> <br />
The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>experimental</strong>. An experimental function is in early stages of development. The unlying code might be changing frequently. Experimental functions might be removed without deprecation, so you are generally best off waiting until a function is more mature before you use it in production code. Experimental functions are only available in development versions of this <code>AMR</code> package and will thus not be included in releases that are submitted to CRAN, since such functions have not yet matured enough.</p>
<h2 class="hasAnchor" id="examples"><a class="anchor" href="#examples"></a>Examples</h2>
<pre class="examples"><span class='co'># `example_isolates` is a dataset available in the AMR package.</span>
<span class='co'># See ?example_isolates.</span>
<span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>example_isolates</span><span class='op'>$</span><span class='va'>date</span><span class='op'>)</span>
<span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>example_isolates</span><span class='op'>$</span><span class='va'>date</span>, episode_days <span class='op'>=</span> <span class='fl'>60</span><span class='op'>)</span>
<span class='kw'>if</span> <span class='op'>(</span><span class='kw'><a href='https://rdrr.io/r/base/library.html'>require</a></span><span class='op'>(</span><span class='st'><a href='https://dplyr.tidyverse.org'>"dplyr"</a></span><span class='op'>)</span><span class='op'>)</span> <span class='op'>{</span>
<span class='co'># is_new_episode() can also be used in dplyr verbs to determine patient</span>
<span class='co'># episodes based on any (combination of) grouping variables:</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>condition <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sample.html'>sample</a></span><span class='op'>(</span>x <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/c.html'>c</a></span><span class='op'>(</span><span class='st'>"A"</span>, <span class='st'>"B"</span>, <span class='st'>"C"</span><span class='op'>)</span>,
size <span class='op'>=</span> <span class='fl'>2000</span>,
replace <span class='op'>=</span> <span class='cn'>TRUE</span><span class='op'>)</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>condition</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>new_episode <span class='op'>=</span> <span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span><span class='op'>)</span><span class='op'>)</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>hospital_id</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/summarise.html'>summarise</a></span><span class='op'>(</span>patients <span class='op'>=</span> <span class='fu'><a href='https://dplyr.tidyverse.org/reference/n_distinct.html'>n_distinct</a></span><span class='op'>(</span><span class='va'>patient_id</span><span class='op'>)</span>,
n_episodes_365 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span>, episode_days <span class='op'>=</span> <span class='fl'>365</span><span class='op'>)</span><span class='op'>)</span>,
n_episodes_60 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span>, episode_days <span class='op'>=</span> <span class='fl'>60</span><span class='op'>)</span><span class='op'>)</span>,
n_episodes_30 <span class='op'>=</span> <span class='fu'><a href='https://rdrr.io/r/base/sum.html'>sum</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span>, episode_days <span class='op'>=</span> <span class='fl'>30</span><span class='op'>)</span><span class='op'>)</span><span class='op'>)</span>
<span class='co'># grouping on patients and microorganisms leads to the same results</span>
<span class='co'># as first_isolate():</span>
<span class='va'>x</span> <span class='op'>&lt;-</span> <span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter</a></span><span class='op'>(</span><span class='fu'><a href='first_isolate.html'>first_isolate</a></span><span class='op'>(</span><span class='va'>.</span>, include_unknown <span class='op'>=</span> <span class='cn'>TRUE</span><span class='op'>)</span><span class='op'>)</span>
<span class='va'>y</span> <span class='op'>&lt;-</span> <span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>patient_id</span>, <span class='va'>mo</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter</a></span><span class='op'>(</span><span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span><span class='op'>)</span><span class='op'>)</span>
<span class='fu'><a href='https://rdrr.io/r/base/identical.html'>identical</a></span><span class='op'>(</span><span class='va'>x</span><span class='op'>$</span><span class='va'>patient_id</span>, <span class='va'>y</span><span class='op'>$</span><span class='va'>patient_id</span><span class='op'>)</span>
<span class='co'># but is_new_episode() has a lot more flexibility than first_isolate(),</span>
<span class='co'># since you can now group on anything that seems relevant:</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span><span class='op'>(</span><span class='va'>patient_id</span>, <span class='va'>mo</span>, <span class='va'>hospital_id</span>, <span class='va'>ward_icu</span><span class='op'>)</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>flag_episode <span class='op'>=</span> <span class='fu'>is_new_episode</span><span class='op'>(</span><span class='va'>date</span><span class='op'>)</span><span class='op'>)</span>
<span class='op'>}</span>
</pre>
</div>
<div class="col-md-3 hidden-xs hidden-sm" id="pkgdown-sidebar">
<nav id="toc" data-toggle="toc" class="sticky-top">
<h2 data-toc-skip>Contents</h2>
</nav>
</div>
</div>
<footer>
<div class="copyright">
<p>Developed by <a href='https://www.rug.nl/staff/m.s.berends/'>Matthijs S. Berends</a>, <a href='https://www.rug.nl/staff/c.f.luz/'>Christian F. Luz</a>, <a href='https://www.rug.nl/staff/a.w.friedrich/'>Alexander W. Friedrich</a>, <a href='https://www.rug.nl/staff/b.sinha/'>Bhanu N. M. Sinha</a>, <a href='https://www.rug.nl/staff/c.j.albers/'>Casper J. Albers</a>, <a href='https://www.rug.nl/staff/c.glasner/'>Corinna Glasner</a>.</p>
</div>
<div class="pkgdown">
<p>Site built with <a href="https://pkgdown.r-lib.org/">pkgdown</a> 1.6.1.</p>
</div>
</footer>
</div>
</body>
</html>

16
docs/reference/like.html
View File

@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9019</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>
@ -246,11 +246,7 @@
<span class='va'>x</span> <span class='op'>%like%</span> <span class='va'>pattern</span>
<span class='va'>x</span> <span class='op'>%not_like%</span> <span class='va'>pattern</span>
<span class='va'>x</span> <span class='op'>%like_case%</span> <span class='va'>pattern</span>
<span class='va'>x</span> <span class='op'>%not_like_case%</span> <span class='va'>pattern</span></pre>
<span class='va'>x</span> <span class='op'>%like_case%</span> <span class='va'>pattern</span></pre>
<h2 class="hasAnchor" id="arguments"><a class="anchor" href="#arguments"></a>Arguments</h2>
<table class="ref-arguments">
@ -284,8 +280,7 @@
<li><p>Tries again with <code>perl = TRUE</code> if regex fails</p></li>
</ul>
<p>Using RStudio? This function can also be inserted in your code from the Addins menu and can have its own Keyboard Shortcut like <code>Ctrl+Shift+L</code> or <code>Cmd+Shift+L</code> (see <code>Tools</code> &gt; <code>Modify Keyboard Shortcuts...</code>). This addin iterates over all 'like' variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert <code>%like%</code> and by pressing it again it will be replaced with <code>%not_like%</code>, then <code>%like_case%</code>, then <code>%not_like_case%</code> and then back to <code>%like%</code>.</p>
<p>The <code>"%not_like%"</code> and <code>"%not_like_case%"</code> functions are wrappers around <code>"%like%"</code> and <code>"%like_case%"</code>.</p>
<p>Using RStudio? The text <code>%like%</code> can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like <code>Ctrl+Shift+L</code> or <code>Cmd+Shift+L</code> (see <code>Tools</code> &gt; <code>Modify Keyboard Shortcuts...</code>).</p>
<h2 class="hasAnchor" id="stable-lifecycle"><a class="anchor" href="#stable-lifecycle"></a>Stable lifecycle</h2>
@ -322,11 +317,6 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
<span class='kw'>if</span> <span class='op'>(</span><span class='kw'><a href='https://rdrr.io/r/base/library.html'>require</a></span><span class='op'>(</span><span class='st'><a href='https://dplyr.tidyverse.org'>"dplyr"</a></span><span class='op'>)</span><span class='op'>)</span> <span class='op'>{</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter</a></span><span class='op'>(</span><span class='fu'><a href='mo_property.html'>mo_name</a></span><span class='op'>(</span><span class='va'>mo</span><span class='op'>)</span> <span class='op'>%like%</span> <span class='st'>"^ent"</span><span class='op'>)</span>
<span class='va'>example_isolates</span> <span class='op'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/mutate.html'>mutate</a></span><span class='op'>(</span>group <span class='op'>=</span> <span class='fu'><a href='https://dplyr.tidyverse.org/reference/case_when.html'>case_when</a></span><span class='op'>(</span><span class='va'>hospital_id</span> <span class='op'>%like%</span> <span class='st'>"A|D"</span> <span class='op'>~</span> <span class='st'>"Group 1"</span>,
<span class='fu'><a href='mo_property.html'>mo_name</a></span><span class='op'>(</span><span class='va'>mo</span><span class='op'>)</span> <span class='op'>%not_like%</span> <span class='st'>"^Staph"</span> <span class='op'>~</span> <span class='st'>"Group 2a"</span>,
<span class='cn'>TRUE</span> <span class='op'>~</span> <span class='st'>"Group 2b"</span><span class='op'>)</span><span class='op'>)</span>
<span class='op'>}</span>
<span class='co'># }</span>
</pre>

3
docs/sitemap.xml
View File

@ -96,6 +96,9 @@
<url>
<loc>https://msberends.github.io/AMR//reference/intrinsic_resistant.html</loc>
</url>
<url>
<loc>https://msberends.github.io/AMR//reference/is_new_episode.html</loc>
</url>
<url>
<loc>https://msberends.github.io/AMR//reference/join.html</loc>
</url>

2
docs/survey.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9024</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.4.0.9025</span>
</span>
</div>

2
inst/rstudio/addins.dcf
View File

@ -2,6 +2,6 @@ Name: Insert %in%
Binding: addin_insert_in
Interactive: false
Name: Insert %like% / %not_like%
Name: Insert %like%
Binding: addin_insert_like
Interactive: false

48
man/first_isolate.Rd
View File

@ -4,7 +4,6 @@
\alias{first_isolate}
\alias{filter_first_isolate}
\alias{filter_first_weighted_isolate}
\alias{is_new_episode}
\title{Determine first (weighted) isolates}
\source{
Methodology of this function is strictly based on:
@ -49,13 +48,6 @@ filter_first_weighted_isolate(
col_keyantibiotics = NULL,
...
)
is_new_episode(
.data,
episode_days = 365,
col_date = NULL,
col_patient_id = NULL
)
}
\arguments{
\item{x, .data}{a \link{data.frame} containing isolates.}
@ -98,10 +90,10 @@ is_new_episode(
A \code{\link{logical}} vector
}
\description{
Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use \code{\link[=is_new_episode]{is_new_episode()}} that also supports grouping with the \code{dplyr} package, see \emph{Examples}.
Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type. To determine patient episodes not necessarily based on microorganisms, use \code{\link[=is_new_episode]{is_new_episode()}} that also supports grouping with the \code{dplyr} package.
}
\details{
The \code{\link[=is_new_episode]{is_new_episode()}} function is a wrapper around the \code{\link[=first_isolate]{first_isolate()}} function and can be used for data sets without isolates to just determine patient episodes based on any combination of grouping variables (using \code{dplyr}), please see \emph{Examples}. Since it runs \code{\link[=first_isolate]{first_isolate()}} for every group, it is quite slow.
The \code{\link[=first_isolate]{first_isolate()}} function is a wrapper around the \code{\link[=is_new_episode]{is_new_episode()}} function, but more efficient for data sets containing microorganism codes or names.
All isolates with a microbial ID of \code{NA} will be excluded as first isolate.
\subsection{Why this is so important}{
@ -191,42 +183,6 @@ if (require("dplyr")) {
# Gentamicin resistance in hospital D appears to be 3.7\% higher than
# when you (erroneously) would have used all isolates for analysis.
}
# filtering based on any other condition -----------------------------------
if (require("dplyr")) {
# is_new_episode() can be used in dplyr verbs to determine patient
# episodes based on any (combination of) grouping variables:
example_isolates \%>\%
mutate(condition = sample(x = c("A", "B", "C"),
size = 2000,
replace = TRUE)) \%>\%
group_by(condition) \%>\%
mutate(new_episode = is_new_episode())
example_isolates \%>\%
group_by(hospital_id) \%>\%
summarise(patients = n_distinct(patient_id),
n_episodes_365 = sum(is_new_episode(episode_days = 365)),
n_episodes_60 = sum(is_new_episode(episode_days = 60)),
n_episodes_30 = sum(is_new_episode(episode_days = 30)))
# grouping on microorganisms leads to the same results as first_isolate():
x <- example_isolates \%>\%
filter_first_isolate(include_unknown = TRUE)
y <- example_isolates \%>\%
group_by(mo) \%>\%
filter(is_new_episode())
identical(x$patient_id, y$patient_id)
# but now you can group on isolates and many more:
example_isolates \%>\%
group_by(mo, hospital_id, ward_icu) \%>\%
mutate(flag_episode = is_new_episode())
}
}
}
\seealso{

80
man/is_new_episode.Rd Normal file
View File

@ -0,0 +1,80 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/is_new_episode.R
\name{is_new_episode}
\alias{is_new_episode}
\title{Determine (new) episodes for patients}
\usage{
is_new_episode(x, episode_days = 365, ...)
}
\arguments{
\item{x}{vector of dates (class \code{Date} or \code{POSIXt})}
\item{episode_days}{length of the required episode in days, defaults to 365. Every element in the input will return \code{TRUE} after this number of days has passed since the last included date, independent of calendar years. Please see \emph{Details}.}
\item{...}{arguments passed on to \code{\link[=as.Date]{as.Date()}}}
}
\value{
a \link{logical} vector
}
\description{
This function determines which items in a vector can be considered (the start of) a new episode, based on the parameter \code{episode_days}. This can be used to determine clinical episodes for any epidemiological analysis.
}
\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 \code{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 \code{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 \code{dplyr} package is not required for this function to work, but this function works conveniently inside \code{dplyr} verbs such as \code{\link[=filter]{filter()}}, \code{\link[=mutate]{mutate()}} and \code{\link[=summarise]{summarise()}}.
}
\section{Experimental lifecycle}{
\if{html}{\figure{lifecycle_experimental.svg}{options: style=margin-bottom:5px} \cr}
The \link[=lifecycle]{lifecycle} of this function is \strong{experimental}. An experimental function is in early stages of development. The unlying code might be changing frequently. Experimental functions might be removed without deprecation, so you are generally best off waiting until a function is more mature before you use it in production code. Experimental functions are only available in development versions of this \code{AMR} package and will thus not be included in releases that are submitted to CRAN, since such functions have not yet matured enough.
}
\section{Read more on our website!}{
On our website \url{https://msberends.github.io/AMR/} you can find \href{https://msberends.github.io/AMR/articles/AMR.html}{a comprehensive tutorial} about how to conduct AMR analysis, the \href{https://msberends.github.io/AMR/reference/}{complete documentation of all functions} and \href{https://msberends.github.io/AMR/articles/WHONET.html}{an example analysis using WHONET data}. As we would like to better understand the backgrounds and needs of our users, please \href{https://msberends.github.io/AMR/survey.html}{participate in our survey}!
}
\examples{
# `example_isolates` is a dataset available in the AMR package.
# See ?example_isolates.
is_new_episode(example_isolates$date)
is_new_episode(example_isolates$date, episode_days = 60)
if (require("dplyr")) {
# is_new_episode() can also be used in dplyr verbs to determine patient
# episodes based on any (combination of) grouping variables:
example_isolates \%>\%
mutate(condition = sample(x = c("A", "B", "C"),
size = 2000,
replace = TRUE)) \%>\%
group_by(condition) \%>\%
mutate(new_episode = is_new_episode(date))
example_isolates \%>\%
group_by(hospital_id) \%>\%
summarise(patients = n_distinct(patient_id),
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)))
# grouping on patients and microorganisms leads to the same results
# as first_isolate():
x <- example_isolates \%>\%
filter(first_isolate(., include_unknown = TRUE))
y <- example_isolates \%>\%
group_by(patient_id, mo) \%>\%
filter(is_new_episode(date))
identical(x$patient_id, y$patient_id)
# but is_new_episode() has a lot more flexibility than first_isolate(),
# since you can now group on anything that seems relevant:
example_isolates \%>\%
group_by(patient_id, mo, hospital_id, ward_icu) \%>\%
mutate(flag_episode = is_new_episode(date))
}
}

15
man/like.Rd
View File

@ -3,9 +3,7 @@
\name{like}
\alias{like}
\alias{\%like\%}
\alias{\%not_like\%}
\alias{\%like_case\%}
\alias{\%not_like_case\%}
\title{Pattern matching with keyboard shortcut}
\source{
Idea from the \href{https://github.com/Rdatatable/data.table/blob/master/R/like.R}{\code{like} function from the \code{data.table} package}
@ -15,11 +13,7 @@ like(x, pattern, ignore.case = TRUE)
x \%like\% pattern
x \%not_like\% pattern
x \%like_case\% pattern
x \%not_like_case\% pattern
}
\arguments{
\item{x}{a character vector where matches are sought, or an object which can be coerced by \code{\link[=as.character]{as.character()}} to a character vector.}
@ -43,9 +37,7 @@ The \verb{\%like\%} function:
\item Tries again with \code{perl = TRUE} if regex fails
}
Using RStudio? This function can also be inserted in your code from the Addins menu and can have its own Keyboard Shortcut like \code{Ctrl+Shift+L} or \code{Cmd+Shift+L} (see \code{Tools} > \verb{Modify Keyboard Shortcuts...}). This addin iterates over all 'like' variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert \verb{\%like\%} and by pressing it again it will be replaced with \verb{\%not_like\%}, then \verb{\%like_case\%}, then \verb{\%not_like_case\%} and then back to \verb{\%like\%}.
The \code{"\%not_like\%"} and \code{"\%not_like_case\%"} functions are wrappers around \code{"\%like\%"} and \code{"\%like_case\%"}.
Using RStudio? The text \verb{\%like\%} can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like \code{Ctrl+Shift+L} or \code{Cmd+Shift+L} (see \code{Tools} > \verb{Modify Keyboard Shortcuts...}).
}
\section{Stable lifecycle}{
@ -80,11 +72,6 @@ a \%like\% b
if (require("dplyr")) {
example_isolates \%>\%
filter(mo_name(mo) \%like\% "^ent")
example_isolates \%>\%
mutate(group = case_when(hospital_id \%like\% "A|D" ~ "Group 1",
mo_name(mo) \%not_like\% "^Staph" ~ "Group 2a",
TRUE ~ "Group 2b"))
}
}
}

6
tests/testthat/test-first_isolate.R
View File

@ -204,11 +204,5 @@ test_that("first isolates work", {
expect_true(all(example_isolates %pm>%
pm_distinct(mo, .keep_all = TRUE) %pm>%
first_isolate() == TRUE))
library(dplyr)
# is_new_episode
old <- example_isolates %>% mutate(out = first_isolate(., include_unknown = TRUE))
new <- example_isolates %>% group_by(mo) %>% mutate(out = is_new_episode())
expect_identical(which(old$out), which(new$out))
})

55
tests/testthat/test-is_new_episode.R Normal file
View File

@ -0,0 +1,55 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis for R #
# #
# SOURCE #
# https://github.com/msberends/AMR #
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
context("is_new_episode.R")
test_that("new episodes work", {
skip_on_cran()
test_df <- rbind(
data.frame(
date = as.Date(c("2015-01-01", "2015-10-01", "2016-02-04", "2016-12-31", "2017-01-01", "2017-02-01", "2017-02-05", "2020-01-01")),
patient_id = "A"
),
data.frame(
date = as.Date(c("2015-01-01", "2016-02-01", "2016-12-31", "2017-01-01", "2017-02-03")),
patient_id = "B"
))
library(dplyr)
expect_identical(test_df %>% group_by(patient_id) %>% mutate(f = is_new_episode(date)) %>% pull(f),
c(TRUE, FALSE, TRUE, FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, FALSE, FALSE, TRUE))
suppressMessages(
x <- example_isolates %>%
mutate(out = first_isolate(., include_unknown = TRUE, info = FALSE))
)
y <- example_isolates %>%
group_by(patient_id, mo) %>%
mutate(out = is_new_episode(date))
expect_identical(which(x$out), which(y$out))
})

5
tests/testthat/test-like.R
View File

@ -31,10 +31,7 @@ test_that("`like` works", {
expect_true("test" %like% "test")
expect_false("test" %like_case% "TEST")
expect_false("test" %not_like% "test")
expect_true("test" %not_like_case% "TEST")
expect_true(as.factor("test") %like% "TEST")
expect_identical(factor(c("Test case", "Something different", "Yet another thing")) %like% c("case", "diff", "yet"),
c(TRUE, TRUE, TRUE))