mirror of
https://github.com/msberends/AMR.git
synced 2025-09-06 06:49:41 +02:00
dplyr 0.8.0 support, fixes #7
This commit is contained in:
@@ -2,6 +2,8 @@
|
||||
% Please edit documentation in R/first_isolate.R
|
||||
\name{first_isolate}
|
||||
\alias{first_isolate}
|
||||
\alias{filter_first_isolate}
|
||||
\alias{filter_first_weighted_isolate}
|
||||
\title{Determine first (weighted) isolates}
|
||||
\source{
|
||||
Methodology of this function is based on: \strong{M39 Analysis and Presentation of Cumulative Antimicrobial Susceptibility Test Data, 4th Edition}, 2014, \emph{Clinical and Laboratory Standards Institute (CLSI)}. \url{https://clsi.org/standards/products/microbiology/documents/m39/}.
|
||||
@@ -11,10 +13,15 @@ first_isolate(tbl, col_date = NULL, col_patient_id = NULL,
|
||||
col_mo = NULL, col_testcode = NULL, col_specimen = NULL,
|
||||
col_icu = NULL, col_keyantibiotics = NULL, episode_days = 365,
|
||||
testcodes_exclude = NULL, icu_exclude = FALSE,
|
||||
filter_specimen = NULL, output_logical = TRUE,
|
||||
type = "keyantibiotics", ignore_I = TRUE, points_threshold = 2,
|
||||
info = TRUE, col_bactid = NULL, col_genus = NULL,
|
||||
col_species = NULL)
|
||||
specimen_group = NULL, type = "keyantibiotics", ignore_I = TRUE,
|
||||
points_threshold = 2, info = TRUE, ...)
|
||||
|
||||
filter_first_isolate(tbl, col_date = NULL, col_patient_id = NULL,
|
||||
col_mo = NULL, ...)
|
||||
|
||||
filter_first_weighted_isolate(tbl, col_date = NULL,
|
||||
col_patient_id = NULL, col_mo = NULL, col_keyantibiotics = NULL,
|
||||
...)
|
||||
}
|
||||
\arguments{
|
||||
\item{tbl}{a \code{data.frame} containing isolates.}
|
||||
@@ -37,11 +44,9 @@ first_isolate(tbl, col_date = NULL, col_patient_id = NULL,
|
||||
|
||||
\item{testcodes_exclude}{character vector with test codes that should be excluded (case-insensitive)}
|
||||
|
||||
\item{icu_exclude}{logical whether ICU isolates should be excluded}
|
||||
\item{icu_exclude}{logical whether ICU isolates should be excluded (rows with value \code{TRUE} in column \code{col_icu})}
|
||||
|
||||
\item{filter_specimen}{specimen group or type that should be excluded}
|
||||
|
||||
\item{output_logical}{return output as \code{logical} (will else be the values \code{0} or \code{1})}
|
||||
\item{specimen_group}{value in column \code{col_specimen} to filter on}
|
||||
|
||||
\item{type}{type to determine weighed isolates; can be \code{"keyantibiotics"} or \code{"points"}, see Details}
|
||||
|
||||
@@ -51,21 +56,34 @@ first_isolate(tbl, col_date = NULL, col_patient_id = NULL,
|
||||
|
||||
\item{info}{print progress}
|
||||
|
||||
\item{col_bactid}{(deprecated, use \code{col_mo} instead)}
|
||||
|
||||
\item{col_genus}{(deprecated, use \code{col_mo} instead) column name of the genus of the microorganisms}
|
||||
|
||||
\item{col_species}{(deprecated, use \code{col_mo} instead) column name of the species of the microorganisms}
|
||||
\item{...}{parameters passed on to the \code{first_isolate} function}
|
||||
}
|
||||
\value{
|
||||
A vector to add to table, see Examples.
|
||||
Logical vector
|
||||
}
|
||||
\description{
|
||||
Determine first (weighted) isolates of all microorganisms of every patient per episode and (if needed) per specimen type.
|
||||
}
|
||||
\details{
|
||||
\strong{WHY THIS IS SO IMPORTANT} \cr
|
||||
To conduct an analysis of antimicrobial resistance, you should only include the first isolate of every patient per episode \href{https://www.ncbi.nlm.nih.gov/pubmed/17304462}{[1]}. If you would not do this, you could easily get an overestimate or underestimate of the resistance of an antibiotic. Imagine that a patient was admitted with an MRSA and that it was found in 5 different blood cultures the following week. The resistance percentage of oxacillin of all \emph{S. aureus} isolates would be overestimated, because you included this MRSA more than once. It would be \href{https://en.wikipedia.org/wiki/Selection_bias}{selection bias}.
|
||||
To conduct an analysis of antimicrobial resistance, you should only include the first isolate of every patient per episode \href{https://www.ncbi.nlm.nih.gov/pubmed/17304462}{[1]}. If you would not do this, you could easily get an overestimate or underestimate of the resistance of an antibiotic. Imagine that a patient was admitted with an MRSA and that it was found in 5 different blood cultures the following week. The resistance percentage of oxacillin of all \emph{S. aureus} isolates would be overestimated, because you included this MRSA more than once. It would be \href{https://en.wikipedia.org/wiki/Selection_bias}{selection bias}.
|
||||
|
||||
The function \code{filter_first_isolate} is essentially equal to:
|
||||
\preformatted{
|
||||
tbl \%>\%
|
||||
mutate(only_firsts = first_isolate(tbl, ...)) \%>\%
|
||||
filter(only_firsts == TRUE) \%>\%
|
||||
select(-only_firsts)
|
||||
}
|
||||
The function \code{filter_first_weighted_isolate} is essentially equal to:
|
||||
\preformatted{
|
||||
tbl \%>\%
|
||||
mutate(keyab = key_antibiotics(.)) \%>\%
|
||||
mutate(only_weighted_firsts = first_isolate(tbl,
|
||||
col_keyantibiotics = "keyab", ...)) \%>\%
|
||||
filter(only_weighted_firsts == TRUE) \%>\%
|
||||
select(-only_weighted_firsts)
|
||||
}
|
||||
}
|
||||
\section{Key antibiotics}{
|
||||
|
||||
@@ -83,20 +101,29 @@ Determine first (weighted) isolates of all microorganisms of every patient per e
|
||||
?septic_patients
|
||||
|
||||
library(dplyr)
|
||||
my_patients <- septic_patients \%>\%
|
||||
# Filter on first isolates:
|
||||
septic_patients \%>\%
|
||||
mutate(first_isolate = first_isolate(.,
|
||||
col_date = "date",
|
||||
col_patient_id = "patient_id",
|
||||
col_mo = "mo"))
|
||||
col_mo = "mo")) \%>\%
|
||||
filter(first_isolate == TRUE)
|
||||
|
||||
# Which can be shortened to:
|
||||
septic_patients \%>\%
|
||||
filter_first_isolate()
|
||||
# or for first weighted isolates:
|
||||
septic_patients \%>\%
|
||||
filter_first_weighted_isolate()
|
||||
|
||||
# Now let's see if first isolates matter:
|
||||
A <- my_patients \%>\%
|
||||
A <- septic_patients \%>\%
|
||||
group_by(hospital_id) \%>\%
|
||||
summarise(count = n_rsi(gent), # gentamicin availability
|
||||
resistance = portion_IR(gent)) # gentamicin resistance
|
||||
|
||||
B <- my_patients \%>\%
|
||||
filter(first_isolate == TRUE) \%>\% # the 1st isolate filter
|
||||
B <- septic_patients \%>\%
|
||||
filter_first_weighted_isolate() \%>\% # the 1st isolate filter
|
||||
group_by(hospital_id) \%>\%
|
||||
summarise(count = n_rsi(gent), # gentamicin availability
|
||||
resistance = portion_IR(gent)) # gentamicin resistance
|
||||
@@ -106,6 +133,7 @@ B <- my_patients \%>\%
|
||||
# Gentamicin resitance in hospital D appears to be 5.4\% higher than
|
||||
# when you (erroneously) would have used all isolates!
|
||||
|
||||
|
||||
## OTHER EXAMPLES:
|
||||
|
||||
\dontrun{
|
||||
@@ -122,29 +150,29 @@ tbl$first_isolate_weighed <-
|
||||
|
||||
tbl$first_blood_isolate <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Blood')
|
||||
specimen_group = 'Blood')
|
||||
|
||||
tbl$first_blood_isolate_weighed <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Blood',
|
||||
specimen_group = 'Blood',
|
||||
col_keyantibiotics = 'keyab')
|
||||
|
||||
tbl$first_urine_isolate <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Urine')
|
||||
specimen_group = 'Urine')
|
||||
|
||||
tbl$first_urine_isolate_weighed <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Urine',
|
||||
specimen_group = 'Urine',
|
||||
col_keyantibiotics = 'keyab')
|
||||
|
||||
tbl$first_resp_isolate <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Respiratory')
|
||||
specimen_group = 'Respiratory')
|
||||
|
||||
tbl$first_resp_isolate_weighed <-
|
||||
first_isolate(tbl,
|
||||
filter_specimen = 'Respiratory',
|
||||
specimen_group = 'Respiratory',
|
||||
col_keyantibiotics = 'keyab')
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user