rsi family for resistance analysis

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 0.2.0.9020
+Version: 0.2.0.9021
-Date: 2018-08-02
+Date: 2018-08-03
 Title: Antimicrobial Resistance Analysis
 Authors@R: c(
     person(

NAMESPACE

@@ -31,12 +31,8 @@ export("%like%")
 export(BRMO)
 export(EUCAST_exceptional_phenotypes)
 export(EUCAST_rules)
-export(IR)
 export(MDRO)
 export(MRGN)
-export(R)
-export(S)
-export(SI)
 export(abname)
 export(anti_join_microorganisms)
 export(as.bactid)
@@ -55,6 +51,7 @@ export(g.test)
 export(guess_atc)
 export(guess_bactid)
 export(inner_join_microorganisms)
+export(intermediate)
 export(interpretive_reading)
 export(is.bactid)
 export(is.mic)
@@ -72,6 +69,12 @@ export(resistance)
 export(resistance_predict)
 export(right_join_microorganisms)
 export(rsi)
+export(rsi_I)
+export(rsi_IR)
+export(rsi_R)
+export(rsi_S)
+export(rsi_SI)
+export(rsi_n)
 export(rsi_predict)
 export(semi_join_microorganisms)
 export(skewness)

NEWS.md

@@ -2,7 +2,7 @@
 **Published on CRAN: (unpublished)**
 
 #### New
-* **BREAKING**: `rsi_df` was removed in favour of new functions `R`, `IR`, `SI` and `S` to selectively calculate resistance or susceptibility. These functions use **hybrid evaluation**, which means that calculations are not done in R directly but rather in C++ using the `Rcpp` package, making them 20 to 30 times faster. The function `rsi` still works, but is deprecated.
+* **BREAKING**: `rsi_df` was removed in favour of new functions `rsi_R`, `rsi_IR`, `rsi_I`, `rsi_SI` and `rsi_S` to selectively calculate resistance or susceptibility. These functions use **hybrid evaluation**, which means that calculations are not done in R directly but rather in C++ using the `Rcpp` package, making them 20 to 30 times faster. The function `rsi` still works, but is deprecated. The function `n_rsi` is accompanied by `rsi_n`. 
 * **BREAKING**: the methodology for determining first weighted isolates was changed. The antibiotics that are compared between isolates (call *key antibiotics*) to include more first isolates (afterwards called first *weighted* isolates) are now as follows:
   * Universal: amoxicillin, amoxicillin/clavlanic acid, cefuroxime, piperacillin/tazobactam, ciprofloxacin,  trimethoprim/sulfamethoxazole
   * Gram-positive: vancomycin, teicoplanin, tetracycline, erythromycin, oxacillin, rifampicin

R/RcppExports.R

@@ -5,6 +5,10 @@ rsi_calc_S <- function(x, include_I) {
     .Call(`_AMR_rsi_calc_S`, x, include_I)
 }
 
+rsi_calc_I <- function(x) {
+    .Call(`_AMR_rsi_calc_I`, x)
+}
+
 rsi_calc_R <- function(x, include_I) {
     .Call(`_AMR_rsi_calc_R`, x, include_I)
 }

R/bactid.R

@@ -23,6 +23,7 @@
 #' @param Becker a logical to indicate whether \emph{Staphylococci} should be categorised into Coagulase Negative \emph{Staphylococci} ("CoNS") and Coagulase Positive \emph{Staphylococci} ("CoPS") instead of their own species, according to Karsten Becker \emph{et al.} [1]. This excludes \emph{Staphylococcus aureus} at default, use \code{Becker = "all"} to also categorise \emph{S. aureus} as "CoPS".
 #' @param Lancefield a logical to indicate whether beta-haemolytic \emph{Streptococci} should be categorised into Lancefield groups instead of their own species, according to Rebecca C. Lancefield [2]. These \emph{Streptococci} will be categorised in their first group, i.e. \emph{Streptococcus dysgalactiae} will be group C, although officially it was also categorised into groups G and L. Groups D and E will be ignored, since they are \emph{Enterococci}.
 #' @rdname as.bactid
+#' @keywords bactid Becker becker Lancefield lancefield guess
 #' @details \code{guess_bactid} is an alias of \code{as.bactid}.
 #'
 #' Some exceptions have been built in to get more logical results, based on prevalence of human pathogens. These are:

R/rsi_IR.R

@@ -18,20 +18,17 @@
 
 #' Calculate resistance of isolates
 #'
-#' These functions can be used to calculate the (co-)resistance of microbial isolates (i.e. percentage S, SI, IR or R). All functions can be used in \code{dplyr}s \code{\link[dplyr]{summarise}} and support grouped variables, see \emph{Examples}. \cr\cr
+#' These functions can be used to calculate the (co-)resistance of microbial isolates (i.e. percentage S, SI, I, IR or R). All functions can be used in \code{dplyr}s \code{\link[dplyr]{summarise}} and support grouped variables, see \emph{Examples}. \cr\cr
-#' \code{R} and \code{IR} can be used to calculate resistance, \code{S} and \code{SI} can be used to calculate susceptibility.\cr
+#' \code{rsi_R} and \code{rsi_IR} can be used to calculate resistance, \code{rsi_S} and \code{rsi_SI} can be used to calculate susceptibility.\cr
-#' \code{n_rsi} counts all cases where antimicrobial interpretations are available.
+#' \code{rsi_n} counts all cases where antimicrobial interpretations are available.
 #' @param ab1 vector of antibiotic interpretations, they will be transformed internally with \code{\link{as.rsi}}
 #' @param ab2 like \code{ab}, a vector of antibiotic interpretations. Use this to calculate (the lack of) co-resistance: the probability where one of two drugs have a susceptible result. See Examples.
 #' @param include_I logical to indicate whether antimicrobial interpretations of "I" should be included
 #' @param minimum minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA}. The default number of \code{30} isolates is advised by the CLSI as best practice, see Source.
 #' @param as_percent logical to indicate whether the output must be returned as percent (text), will else be a double
-#' @param interpretation antimicrobial interpretation
-#' @param info \emph{DEPRECATED} calculate the amount of available isolates and print it, like \code{n = 423}
-#' @param warning \emph{DEPRECATED} show a warning when the available amount of isolates is below \code{minimum}
 #' @details \strong{Remember that you should filter your table to let it contain only first isolates!} Use \code{\link{first_isolate}} to determine them in your data set.
 #'
-#' The functions \code{resistance} and \code{susceptibility} are wrappers around \code{IR} and \code{S}, respectively. All functions except \code{rsi} use hybrid evaluation (i.e. using C++), which makes these functions 20-30 times faster than the old \code{rsi} function. This latter function is still available for backwards compatibility but is deprecated.
+#' The functions \code{resistance} and \code{susceptibility} are wrappers around \code{rsi_IR} and \code{rsi_S}, respectively. All functions use hybrid evaluation (i.e. using C++), which makes these functions 20-30 times faster than the old \code{\link{rsi}} function. This latter function is still available for backwards compatibility but is deprecated.
 #' \if{html}{
 #'   \cr\cr
 #'   To calculate the probability (\emph{p}) of susceptibility of one antibiotic, we use this formula:
@@ -47,48 +44,57 @@
 #' @source \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/}.
 #' @keywords resistance susceptibility rsi_df rsi antibiotics isolate isolates
 #' @return Double or, when \code{as_percent = TRUE}, a character.
-#' @rdname resistance
+#' @rdname rsi_IR
+#' @name rsi_IR
 #' @export
 #' @examples
 #' # Calculate resistance
-#' R(septic_patients$amox)
+#' rsi_R(septic_patients$amox)
-#' IR(septic_patients$amox)
+#' rsi_IR(septic_patients$amox)
 #'
 #' # Or susceptibility
-#' S(septic_patients$amox)
+#' rsi_S(septic_patients$amox)
-#' SI(septic_patients$amox)
+#' rsi_SI(septic_patients$amox)
 #'
 #' # Since n_rsi counts available isolates (and is used as denominator),
 #' # you can calculate back to e.g. count resistant isolates:
-#' IR(septic_patients$amox) * n_rsi(septic_patients$amox)
+#' rsi_IR(septic_patients$amox) * n_rsi(septic_patients$amox)
 #'
 #' library(dplyr)
 #' septic_patients %>%
 #'   group_by(hospital_id) %>%
-#'   summarise(p = S(cipr),
+#'   summarise(p = rsi_S(cipr),
-#'             n = n_rsi(cipr)) # n_rsi works like n_distinct in dplyr
+#'             n = rsi_n(cipr)) # n_rsi works like n_distinct in dplyr
-#'
-#' # Calculate co-resistance between amoxicillin/clav acid and gentamicin,
-#' # so we can see that combination therapy does a lot more than mono therapy:
-#' S(septic_patients$amcl)     # p = 67.3%
-#' n_rsi(septic_patients$amcl) # n = 1570
-#'
-#' S(septic_patients$gent)     # p = 74.0%
-#' n_rsi(septic_patients$gent) # n = 1842
-#'
-#' with(septic_patients,
-#'      S(amcl, gent))         # p = 92.1%
-#' with(septic_patients,
-#'      n_rsi(amcl, gent))     # n = 1504
 #'
 #' septic_patients %>%
 #'   group_by(hospital_id) %>%
-#'   summarise(cipro_p = S(cipr, as_percent = TRUE),
+#'   summarise(R = rsi_R(cipr, as_percent = TRUE),
-#'             cipro_n = n_rsi(cipr),
+#'             I = rsi_I(cipr, as_percent = TRUE),
-#'             genta_p = S(gent, as_percent = TRUE),
+#'             S = rsi_S(cipr, as_percent = TRUE),
-#'             genta_n = n_rsi(gent),
+#'             n = rsi_n(cipr), # also: n_rsi, works like n_distinct in dplyr
-#'             combination_p = S(cipr, gent, as_percent = TRUE),
+#'             total = n()) # this is the length, NOT the amount of tested isolates
-#'             combination_n = n_rsi(cipr, gent))
+#'
+#' # Calculate co-resistance between amoxicillin/clav acid and gentamicin,
+#' # so we can see that combination therapy does a lot more than mono therapy:
+#' rsi_S(septic_patients$amcl) # S = 67.3%
+#' rsi_n(septic_patients$amcl) # n = 1570
+#'
+#' rsi_S(septic_patients$gent) # S = 74.0%
+#' rsi_n(septic_patients$gent) # n = 1842
+#'
+#' with(septic_patients,
+#'      rsi_S(amcl, gent))     # S = 92.1%
+#' with(septic_patients,       # n = 1504
+#'      rsi_n(amcl, gent))
+#'
+#' septic_patients %>%
+#'   group_by(hospital_id) %>%
+#'   summarise(cipro_p = rsi_S(cipr, as_percent = TRUE),
+#'             cipro_n = rsi_n(cipr),
+#'             genta_p = rsi_S(gent, as_percent = TRUE),
+#'             genta_n = rsi_n(gent),
+#'             combination_p = rsi_S(cipr, gent, as_percent = TRUE),
+#'             combination_n = rsi_n(cipr, gent))
 #'
 #' \dontrun{
 #'
@@ -96,28 +102,42 @@
 #' my_table %>%
 #'   filter(first_isolate == TRUE,
 #'          genus == "Helicobacter") %>%
-#'   summarise(p = S(amox, metr),     # amoxicillin with metronidazole
+#'   summarise(p = rsi_S(amox, metr),  # amoxicillin with metronidazole
-#'             n = n_rsi(amox, metr))
+#'             n = rsi_n(amox, metr))
 #' }
-#' @rdname resistance
+rsi_R <- function(ab1,
-#' @name resistance
-#' @export
-#' @rdname resistance
-#' @export
-S <- function(ab1,
-              ab2 = NULL,
                   minimum = 30,
                   as_percent = FALSE) {
-  susceptibility(ab1 = ab1,
+  resistance(ab1 = ab1,
-                 ab2 = ab2,
              include_I = FALSE,
              minimum = minimum,
              as_percent = as_percent)
 }
 
-#' @rdname resistance
+#' @rdname rsi_IR
 #' @export
-SI <- function(ab1,
+rsi_IR <- function(ab1,
+                   minimum = 30,
+                   as_percent = FALSE) {
+  resistance(ab1 = ab1,
+             include_I = TRUE,
+             minimum = minimum,
+             as_percent = as_percent)
+}
+
+#' @rdname rsi_IR
+#' @export
+rsi_I <- function(ab1,
+                  minimum = 30,
+                  as_percent = FALSE) {
+  intermediate(ab1 = ab1,
+               minimum = minimum,
+               as_percent = as_percent)
+}
+
+#' @rdname rsi_IR
+#' @export
+rsi_SI <- function(ab1,
                    ab2 = NULL,
                    minimum = 30,
                    as_percent = FALSE) {
@@ -128,51 +148,20 @@ SI <- function(ab1,
                  as_percent = as_percent)
 }
 
-#' @rdname resistance
+#' @rdname rsi_IR
 #' @export
-IR <- function(ab1,
+rsi_S <- function(ab1,
+                  ab2 = NULL,
                   minimum = 30,
                   as_percent = FALSE) {
-  resistance(ab1 = ab1,
+  susceptibility(ab1 = ab1,
-             include_I = TRUE,
+                 ab2 = ab2,
-             minimum = minimum,
-             as_percent = as_percent)
-}
-
-#' @rdname resistance
-#' @export
-R <- function(ab1,
-              minimum = 30,
-              as_percent = FALSE) {
-  resistance(ab1 = ab1,
                  include_I = FALSE,
                  minimum = minimum,
                  as_percent = as_percent)
 }
 
-#' @rdname resistance
+#' @rdname rsi_IR
-#' @export
-n_rsi <- function(ab1, ab2 = NULL) {
-  if (NCOL(ab1) > 1) {
-    stop('`ab` must be a vector of antimicrobial interpretations', call. = FALSE)
-  }
-  if (!is.rsi(ab1)) {
-    ab1 <- as.rsi(ab1)
-  }
-  if (!is.null(ab2)) {
-    if (NCOL(ab2) > 1) {
-      stop('`ab2` must be a vector of antimicrobial interpretations', call. = FALSE)
-    }
-    if (!is.rsi(ab2)) {
-      ab2 <- as.rsi(ab2)
-    }
-    sum(!is.na(ab1) & !is.na(ab2))
-  } else {
-    sum(!is.na(ab1))
-  }
-}
-
-#' @rdname resistance
 #' @export
 resistance <- function(ab1,
                        include_I = TRUE,
@@ -214,7 +203,45 @@ resistance <- function(ab1,
   }
 }
 
-#' @rdname resistance
+#' @rdname rsi_IR
+#' @export
+intermediate <- function(ab1,
+                         minimum = 30,
+                         as_percent = FALSE) {
+
+  if (NCOL(ab1) > 1) {
+    stop('`ab1` must be a vector of antimicrobial interpretations', call. = FALSE)
+  }
+  if (!is.numeric(minimum)) {
+    stop('`minimum` must be numeric', call. = FALSE)
+  }
+  if (!is.logical(as_percent)) {
+    stop('`as_percent` must be logical', call. = FALSE)
+  }
+
+  # ab_name <- deparse(substitute(ab))
+
+  if (!is.rsi(ab1)) {
+    x <- as.rsi(ab1)
+    warning("Increase speed by transforming to class `rsi` on beforehand: df %>% mutate_at(vars(col10:col20), as.rsi)")
+  } else {
+    x <- ab1
+  }
+  total <- length(x) - sum(is.na(x)) # faster than C++
+  if (total < minimum) {
+    # warning("Too few isolates available for ", ab_name, ": ", total, " < ", minimum, "; returning NA.", call. = FALSE)
+    return(NA)
+  }
+  found <- .Call(`_AMR_rsi_calc_I`, x)
+
+  if (as_percent == TRUE) {
+    percent(found / total, force_zero = TRUE)
+  } else {
+    found / total
+  }
+}
+
+#' @rdname rsi_IR
 #' @export
 susceptibility <- function(ab1,
                            ab2 = NULL,
@@ -275,7 +302,37 @@ susceptibility <- function(ab1,
   }
 }
 
-#' @rdname resistance
+#' @rdname rsi_IR
+#' @export
+rsi_n <- function(ab1, ab2 = NULL) {
+  if (NCOL(ab1) > 1) {
+    stop('`ab` must be a vector of antimicrobial interpretations', call. = FALSE)
+  }
+  if (!is.rsi(ab1)) {
+    ab1 <- as.rsi(ab1)
+  }
+  if (!is.null(ab2)) {
+    if (NCOL(ab2) > 1) {
+      stop('`ab2` must be a vector of antimicrobial interpretations', call. = FALSE)
+    }
+    if (!is.rsi(ab2)) {
+      ab2 <- as.rsi(ab2)
+    }
+    sum(!is.na(ab1) & !is.na(ab2))
+  } else {
+    sum(!is.na(ab1))
+  }
+}
+
+#' @rdname rsi_IR
+#' @export
+n_rsi <- rsi_n
+
+#' @inherit resistance
+#' @description This function is deprecated. Use \code{\link{rsi_IR}} instead.
+#' @param info calculate the amount of available isolates and print it, like \code{n = 423}
+#' @param warning show a warning when the available amount of isolates is below \code{minimum}
+#' @param interpretation antimicrobial interpretation
 #' @export
 rsi <- function(ab1,
                 ab2 = NA,

README.md

@@ -28,7 +28,7 @@ Erwin E.A. Hassing<sup>2</sup>,
 This R package contains functions to make **microbiological, epidemiological data analysis easier**. It allows the use of some new classes to work with MIC values and antimicrobial interpretations (i.e. values S, I and R).
 
 With `AMR` you can:
-* Calculate the resistance (and even co-resistance) of microbial isolates with the `R`, `IR`, `SI` and `S` functions, that can also be used with the `dplyr` package (e.g. in conjunction with `summarise`)
+* Calculate the resistance (and even co-resistance) of microbial isolates with the `rsi_R`, `rsi_IR`, `rsi_I`, `rsi_SI` and `rsi_S` functions, that can also be used with the `dplyr` package (e.g. in conjunction with `summarise`)
 * Predict antimicrobial resistance for the nextcoming years with the `resistance_predict` function
 * Apply [EUCAST rules to isolates](http://www.eucast.org/expert_rules_and_intrinsic_resistance/) with the `EUCAST_rules` function
 * Identify first isolates of every patient [using guidelines from the CLSI](https://clsi.org/standards/products/microbiology/documents/m39/) (Clinical and Laboratory Standards Institute) with the `first_isolate` function
@@ -121,17 +121,17 @@ after
 # 5 PSEAER    R    R    -    -    R
 ```
 
-Bacteria ID's can be retrieved with the `as.bactid` function. It uses any type of info about a microorganism as input. For example, all these will return value `STAAUR`, the ID of *S. aureus*:
+Bacteria ID's can be retrieved with the `guess_bactid` function. It uses any type of info about a microorganism as input. For example, all these will return value `STAAUR`, the ID of *S. aureus*:
 ```r
-as.bactid("stau")
+guess_bactid("stau")
-as.bactid("STAU")
+guess_bactid("STAU")
-as.bactid("staaur")
+guess_bactid("staaur")
-as.bactid("S. aureus")
+guess_bactid("S. aureus")
-as.bactid("S aureus")
+guess_bactid("S aureus")
-as.bactid("Staphylococcus aureus")
+guess_bactid("Staphylococcus aureus")
-as.bactid("MRSA") # Methicillin Resistant S. aureus
+guess_bactid("MRSA") # Methicillin Resistant S. aureus
-as.bactid("VISA") # Vancomycin Intermediate S. aureus
+guess_bactid("VISA") # Vancomycin Intermediate S. aureus
-as.bactid("VRSA") # Vancomycin Resistant S. aureus
+guess_bactid("VRSA") # Vancomycin Resistant S. aureus
 ```
 
 ### New classes

man/as.bactid.Rd

@@ -84,3 +84,9 @@ df <- df \%>\%
 \seealso{
 \code{\link{microorganisms}} for the dataframe that is being used to determine ID's.
 }
+\keyword{Becker}
+\keyword{Lancefield}
+\keyword{bactid}
+\keyword{becker}
+\keyword{guess}
+\keyword{lancefield}

man/microorganisms.Rd

@@ -4,7 +4,7 @@
 \name{microorganisms}
 \alias{microorganisms}
 \title{Dataset with ~2500 microorganisms}
-\format{A data.frame with 2456 observations and 12 variables:
+\format{A data.frame with 2464 observations and 12 variables:
 \describe{
   \item{\code{bactid}}{ID of microorganism}
   \item{\code{bactsys}}{Bactsyscode of microorganism}
@@ -23,7 +23,7 @@
 microorganisms
 }
 \description{
-A dataset containing 2456 microorganisms. MO codes of the UMCG can be looked up using \code{\link{microorganisms.umcg}}.
+A dataset containing 2464 microorganisms. MO codes of the UMCG can be looked up using \code{\link{microorganisms.umcg}}.
 }
 \seealso{
 \code{\link{guess_bactid}} \code{\link{antibiotics}} \code{\link{microorganisms.umcg}}

man/resistance_predict.Rd

@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/resistance.R
+% Please edit documentation in R/rsi_IR.R
 \name{resistance_predict}
 \alias{resistance_predict}
 \alias{rsi_predict}

man/rsi.Rd

@@ -0,0 +1,106 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/rsi_IR.R
+\name{rsi}
+\alias{rsi}
+\title{Calculate resistance of isolates}
+\usage{
+rsi(ab1, ab2 = NA, interpretation = "IR", minimum = 30,
+  as_percent = FALSE, info = FALSE, warning = TRUE)
+}
+\arguments{
+\item{ab1}{vector of antibiotic interpretations, they will be transformed internally with \code{\link{as.rsi}}}
+
+\item{ab2}{like \code{ab}, a vector of antibiotic interpretations. Use this to calculate (the lack of) co-resistance: the probability where one of two drugs have a susceptible result. See Examples.}
+
+\item{interpretation}{antimicrobial interpretation}
+
+\item{minimum}{minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA}. The default number of \code{30} isolates is advised by the CLSI as best practice, see Source.}
+
+\item{as_percent}{logical to indicate whether the output must be returned as percent (text), will else be a double}
+
+\item{info}{calculate the amount of available isolates and print it, like \code{n = 423}}
+
+\item{warning}{show a warning when the available amount of isolates is below \code{minimum}}
+}
+\value{
+Double or, when \code{as_percent = TRUE}, a character.
+}
+\description{
+This function is deprecated. Use \code{\link{rsi_IR}} instead.
+}
+\details{
+\strong{Remember that you should filter your table to let it contain only first isolates!} Use \code{\link{first_isolate}} to determine them in your data set.
+
+The functions \code{resistance} and \code{susceptibility} are wrappers around \code{rsi_IR} and \code{rsi_S}, respectively. All functions use hybrid evaluation (i.e. using C++), which makes these functions 20-30 times faster than the old \code{\link{rsi}} function. This latter function is still available for backwards compatibility but is deprecated.
+\if{html}{
+  \cr\cr
+  To calculate the probability (\emph{p}) of susceptibility of one antibiotic, we use this formula:
+  \out{<div style="text-align: center">}\figure{mono_therapy.png}\out{</div>}
+  To calculate the probability (\emph{p}) of susceptibility of more antibiotics (i.e. combination therapy), we need to check whether one of them has a susceptible result (as numerator) and count all cases where all antibiotics were tested (as denominator). \cr
+  \cr
+  For two antibiotics:
+  \out{<div style="text-align: center">}\figure{combi_therapy_2.png}\out{</div>}
+  \cr
+  Theoretically for three antibiotics:
+  \out{<div style="text-align: center">}\figure{combi_therapy_3.png}\out{</div>}
+}
+}
+\examples{
+# Calculate resistance
+rsi_R(septic_patients$amox)
+rsi_IR(septic_patients$amox)
+
+# Or susceptibility
+rsi_S(septic_patients$amox)
+rsi_SI(septic_patients$amox)
+
+# Since n_rsi counts available isolates (and is used as denominator),
+# you can calculate back to e.g. count resistant isolates:
+rsi_IR(septic_patients$amox) * n_rsi(septic_patients$amox)
+
+library(dplyr)
+septic_patients \%>\%
+  group_by(hospital_id) \%>\%
+  summarise(p = rsi_S(cipr),
+            n = rsi_n(cipr)) # n_rsi works like n_distinct in dplyr
+
+septic_patients \%>\%
+  group_by(hospital_id) \%>\%
+  summarise(R = rsi_R(cipr, as_percent = TRUE),
+            I = rsi_I(cipr, as_percent = TRUE),
+            S = rsi_S(cipr, as_percent = TRUE),
+            n = rsi_n(cipr), # also: n_rsi, works like n_distinct in dplyr
+            total = n()) # this is the length, NOT the amount of tested isolates
+
+# Calculate co-resistance between amoxicillin/clav acid and gentamicin,
+# so we can see that combination therapy does a lot more than mono therapy:
+rsi_S(septic_patients$amcl) # S = 67.3\%
+rsi_n(septic_patients$amcl) # n = 1570
+
+rsi_S(septic_patients$gent) # S = 74.0\%
+rsi_n(septic_patients$gent) # n = 1842
+
+with(septic_patients,
+     rsi_S(amcl, gent))     # S = 92.1\%
+with(septic_patients,       # n = 1504
+     rsi_n(amcl, gent))
+
+septic_patients \%>\%
+  group_by(hospital_id) \%>\%
+  summarise(cipro_p = rsi_S(cipr, as_percent = TRUE),
+            cipro_n = rsi_n(cipr),
+            genta_p = rsi_S(gent, as_percent = TRUE),
+            genta_n = rsi_n(gent),
+            combination_p = rsi_S(cipr, gent, as_percent = TRUE),
+            combination_n = rsi_n(cipr, gent))
+
+\dontrun{
+
+# calculate current empiric combination therapy of Helicobacter gastritis:
+my_table \%>\%
+  filter(first_isolate == TRUE,
+         genus == "Helicobacter") \%>\%
+  summarise(p = rsi_S(amox, metr),  # amoxicillin with metronidazole
+            n = rsi_n(amox, metr))
+}
+}

man/rsi_IR.Rd

@@ -1,66 +1,65 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/resistance.R
+% Please edit documentation in R/rsi_IR.R
-\name{resistance}
+\name{rsi_IR}
+\alias{rsi_IR}
+\alias{rsi_R}
+\alias{rsi_I}
+\alias{rsi_SI}
+\alias{rsi_S}
 \alias{resistance}
-\alias{S}
+\alias{intermediate}
-\alias{SI}
-\alias{IR}
-\alias{R}
-\alias{n_rsi}
 \alias{susceptibility}
-\alias{rsi}
+\alias{rsi_n}
+\alias{n_rsi}
 \title{Calculate resistance of isolates}
 \source{
 \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/}.
 }
 \usage{
-S(ab1, ab2 = NULL, minimum = 30, as_percent = FALSE)
+rsi_R(ab1, minimum = 30, as_percent = FALSE)
 
-SI(ab1, ab2 = NULL, minimum = 30, as_percent = FALSE)
+rsi_IR(ab1, minimum = 30, as_percent = FALSE)
 
-IR(ab1, minimum = 30, as_percent = FALSE)
+rsi_I(ab1, minimum = 30, as_percent = FALSE)
 
-R(ab1, minimum = 30, as_percent = FALSE)
+rsi_SI(ab1, ab2 = NULL, minimum = 30, as_percent = FALSE)
 
-n_rsi(ab1, ab2 = NULL)
+rsi_S(ab1, ab2 = NULL, minimum = 30, as_percent = FALSE)
 
 resistance(ab1, include_I = TRUE, minimum = 30, as_percent = FALSE)
 
+intermediate(ab1, minimum = 30, as_percent = FALSE)
+
 susceptibility(ab1, ab2 = NULL, include_I = FALSE, minimum = 30,
   as_percent = FALSE)
 
-rsi(ab1, ab2 = NA, interpretation = "IR", minimum = 30,
+rsi_n(ab1, ab2 = NULL)
-  as_percent = FALSE, info = FALSE, warning = TRUE)
+
+n_rsi(ab1, ab2 = NULL)
 }
 \arguments{
 \item{ab1}{vector of antibiotic interpretations, they will be transformed internally with \code{\link{as.rsi}}}
 
-\item{ab2}{like \code{ab}, a vector of antibiotic interpretations. Use this to calculate (the lack of) co-resistance: the probability where one of two drugs have a susceptible result. See Examples.}
-
 \item{minimum}{minimal amount of available isolates. Any number lower than \code{minimum} will return \code{NA}. The default number of \code{30} isolates is advised by the CLSI as best practice, see Source.}
 
 \item{as_percent}{logical to indicate whether the output must be returned as percent (text), will else be a double}
 
+\item{ab2}{like \code{ab}, a vector of antibiotic interpretations. Use this to calculate (the lack of) co-resistance: the probability where one of two drugs have a susceptible result. See Examples.}
+
 \item{include_I}{logical to indicate whether antimicrobial interpretations of "I" should be included}
-
-\item{interpretation}{antimicrobial interpretation}
-
-\item{info}{\emph{DEPRECATED} calculate the amount of available isolates and print it, like \code{n = 423}}
-
-\item{warning}{\emph{DEPRECATED} show a warning when the available amount of isolates is below \code{minimum}}
 }
 \value{
 Double or, when \code{as_percent = TRUE}, a character.
 }
 \description{
-These functions can be used to calculate the (co-)resistance of microbial isolates (i.e. percentage S, SI, IR or R). All functions can be used in \code{dplyr}s \code{\link[dplyr]{summarise}} and support grouped variables, see \emph{Examples}. \cr\cr
+These functions can be used to calculate the (co-)resistance of microbial isolates (i.e. percentage S, SI, I, IR or R). All functions can be used in \code{dplyr}s \code{\link[dplyr]{summarise}} and support grouped variables, see \emph{Examples}. \cr\cr
-\code{R} and \code{IR} can be used to calculate resistance, \code{S} and \code{SI} can be used to calculate susceptibility.\cr
+\code{rsi_R} and \code{rsi_IR} can be used to calculate resistance, \code{rsi_S} and \code{rsi_SI} can be used to calculate susceptibility.\cr
-\code{n_rsi} counts all cases where antimicrobial interpretations are available.
+\code{rsi_n} counts all cases where antimicrobial interpretations are available.
 }
 \details{
 \strong{Remember that you should filter your table to let it contain only first isolates!} Use \code{\link{first_isolate}} to determine them in your data set.
 
-The functions \code{resistance} and \code{susceptibility} are wrappers around \code{IR} and \code{S}, respectively. All functions except \code{rsi} use hybrid evaluation (i.e. using C++), which makes these functions 20-30 times faster than the old \code{rsi} function. This latter function is still available for backwards compatibility but is deprecated.
+The functions \code{resistance} and \code{susceptibility} are wrappers around \code{rsi_IR} and \code{rsi_S}, respectively. All functions use hybrid evaluation (i.e. using C++), which makes these functions 20-30 times faster than the old \code{\link{rsi}} function. This latter function is still available for backwards compatibility but is deprecated.
 \if{html}{
   \cr\cr
   To calculate the probability (\emph{p}) of susceptibility of one antibiotic, we use this formula:
@@ -76,44 +75,52 @@ The functions \code{resistance} and \code{susceptibility} are wrappers around \c
 }
 \examples{
 # Calculate resistance
-R(septic_patients$amox)
+rsi_R(septic_patients$amox)
-IR(septic_patients$amox)
+rsi_IR(septic_patients$amox)
 
 # Or susceptibility
-S(septic_patients$amox)
+rsi_S(septic_patients$amox)
-SI(septic_patients$amox)
+rsi_SI(septic_patients$amox)
 
 # Since n_rsi counts available isolates (and is used as denominator),
 # you can calculate back to e.g. count resistant isolates:
-IR(septic_patients$amox) * n_rsi(septic_patients$amox)
+rsi_IR(septic_patients$amox) * n_rsi(septic_patients$amox)
 
 library(dplyr)
 septic_patients \%>\%
   group_by(hospital_id) \%>\%
-  summarise(p = S(cipr),
+  summarise(p = rsi_S(cipr),
-            n = n_rsi(cipr)) # n_rsi works like n_distinct in dplyr
+            n = rsi_n(cipr)) # n_rsi works like n_distinct in dplyr
-
-# Calculate co-resistance between amoxicillin/clav acid and gentamicin,
-# so we can see that combination therapy does a lot more than mono therapy:
-S(septic_patients$amcl)     # p = 67.3\%
-n_rsi(septic_patients$amcl) # n = 1570
-
-S(septic_patients$gent)     # p = 74.0\%
-n_rsi(septic_patients$gent) # n = 1842
-
-with(septic_patients,
-     S(amcl, gent))         # p = 92.1\%
-with(septic_patients,
-     n_rsi(amcl, gent))     # n = 1504
 
 septic_patients \%>\%
   group_by(hospital_id) \%>\%
-  summarise(cipro_p = S(cipr, as_percent = TRUE),
+  summarise(R = rsi_R(cipr, as_percent = TRUE),
-            cipro_n = n_rsi(cipr),
+            I = rsi_I(cipr, as_percent = TRUE),
-            genta_p = S(gent, as_percent = TRUE),
+            S = rsi_S(cipr, as_percent = TRUE),
-            genta_n = n_rsi(gent),
+            n = rsi_n(cipr), # also: n_rsi, works like n_distinct in dplyr
-            combination_p = S(cipr, gent, as_percent = TRUE),
+            total = n()) # this is the length, NOT the amount of tested isolates
-            combination_n = n_rsi(cipr, gent))
+
+# Calculate co-resistance between amoxicillin/clav acid and gentamicin,
+# so we can see that combination therapy does a lot more than mono therapy:
+rsi_S(septic_patients$amcl) # S = 67.3\%
+rsi_n(septic_patients$amcl) # n = 1570
+
+rsi_S(septic_patients$gent) # S = 74.0\%
+rsi_n(septic_patients$gent) # n = 1842
+
+with(septic_patients,
+     rsi_S(amcl, gent))     # S = 92.1\%
+with(septic_patients,       # n = 1504
+     rsi_n(amcl, gent))
+
+septic_patients \%>\%
+  group_by(hospital_id) \%>\%
+  summarise(cipro_p = rsi_S(cipr, as_percent = TRUE),
+            cipro_n = rsi_n(cipr),
+            genta_p = rsi_S(gent, as_percent = TRUE),
+            genta_n = rsi_n(gent),
+            combination_p = rsi_S(cipr, gent, as_percent = TRUE),
+            combination_n = rsi_n(cipr, gent))
 
 \dontrun{
 
@@ -121,8 +128,8 @@ septic_patients \%>\%
 my_table \%>\%
   filter(first_isolate == TRUE,
          genus == "Helicobacter") \%>\%
-  summarise(p = S(amox, metr),     # amoxicillin with metronidazole
+  summarise(p = rsi_S(amox, metr),  # amoxicillin with metronidazole
-            n = n_rsi(amox, metr))
+            n = rsi_n(amox, metr))
 }
 }
 \keyword{antibiotics}

src/RcppExports.cpp

@@ -17,6 +17,17 @@ BEGIN_RCPP
     return rcpp_result_gen;
 END_RCPP
 }
+// rsi_calc_I
+int rsi_calc_I(DoubleVector x);
+RcppExport SEXP _AMR_rsi_calc_I(SEXP xSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject rcpp_result_gen;
+    Rcpp::RNGScope rcpp_rngScope_gen;
+    Rcpp::traits::input_parameter< DoubleVector >::type x(xSEXP);
+    rcpp_result_gen = Rcpp::wrap(rsi_calc_I(x));
+    return rcpp_result_gen;
+END_RCPP
+}
 // rsi_calc_R
 int rsi_calc_R(DoubleVector x, bool include_I);
 RcppExport SEXP _AMR_rsi_calc_R(SEXP xSEXP, SEXP include_ISEXP) {
@@ -32,6 +43,7 @@ END_RCPP
 
 static const R_CallMethodDef CallEntries[] = {
     {"_AMR_rsi_calc_S", (DL_FUNC) &_AMR_rsi_calc_S, 2},
+    {"_AMR_rsi_calc_I", (DL_FUNC) &_AMR_rsi_calc_I, 1},
     {"_AMR_rsi_calc_R", (DL_FUNC) &_AMR_rsi_calc_R, 2},
     {NULL, NULL, 0}
 };

src/rsi_calc.cpp

@@ -1,6 +1,4 @@
 #include <Rcpp.h>
-// #include <functional> // for std::less_equal and std::greater_equal
-// #include <algorithm>  // for count_if
 
 using namespace Rcpp;
 
@@ -12,6 +10,14 @@ int rsi_calc_S(DoubleVector x, bool include_I) {
                           1 + include_I));
 }
 
+// [[Rcpp::export]]
+int rsi_calc_I(DoubleVector x) {
+  return count_if(x.begin(),
+                  x.end(),
+                  bind2nd(std::equal_to<double>(),
+                          2));
+}
+
 // [[Rcpp::export]]
 int rsi_calc_R(DoubleVector x, bool include_I) {
   return count_if(x.begin(),

tests/testthat/test-rsi_IR.R

@@ -1,19 +1,23 @@
-context("resistance.R")
+context("rsi_IR.R")
 
 test_that("resistance works", {
   # check shortcuts
   expect_equal(resistance(septic_patients$amox, include_I = TRUE),
-               IR(septic_patients$amox))
+               rsi_IR(septic_patients$amox))
   expect_equal(resistance(septic_patients$amox, include_I = FALSE),
-               R(septic_patients$amox))
+               rsi_R(septic_patients$amox))
+  expect_equal(intermediate(septic_patients$amox),
+               rsi_I(septic_patients$amox))
   expect_equal(susceptibility(septic_patients$amox, include_I = TRUE),
-               SI(septic_patients$amox))
+               rsi_SI(septic_patients$amox))
   expect_equal(susceptibility(septic_patients$amox, include_I = FALSE),
-               S(septic_patients$amox))
+               rsi_S(septic_patients$amox))
 
-  # amox resistance in `septic_patients` should be around 66.33%
+  # amox resistance in `septic_patients`
-  expect_equal(resistance(septic_patients$amox, include_I = TRUE), 0.6633, tolerance = 0.0001)
+  expect_equal(rsi_R(septic_patients$amox), 0.6603, tolerance = 0.0001)
-  expect_equal(susceptibility(septic_patients$amox, include_I = FALSE), 1 - 0.6633, tolerance = 0.0001)
+  expect_equal(rsi_I(septic_patients$amox), 0.0030, tolerance = 0.0001)
+  expect_equal(1 - rsi_R(septic_patients$amox) - rsi_I(septic_patients$amox),
+               rsi_S(septic_patients$amox))
 
   # pita+genta susceptibility around 98.09%
   expect_equal(susceptibility(septic_patients$pita,
@@ -26,6 +30,18 @@ test_that("resistance works", {
                0.9535,
                tolerance = 0.0001)
 
+  # percentages
+  expect_equal(septic_patients %>%
+                 group_by(hospital_id) %>%
+                 summarise(R = rsi_R(cipr, as_percent = TRUE),
+                           I = rsi_I(cipr, as_percent = TRUE),
+                           S = rsi_S(cipr, as_percent = TRUE),
+                           n = rsi_n(cipr),
+                           total = n()) %>%
+                 pull(n) %>%
+                 sum(),
+               1404)
+
   # count of cases
   expect_equal(septic_patients %>%
                  group_by(hospital_id) %>%
@@ -34,7 +50,7 @@ test_that("resistance works", {
                            genta_p = susceptibility(gent, as_percent = TRUE),
                            genta_n = n_rsi(gent),
                            combination_p = susceptibility(cipr, gent, as_percent = TRUE),
-                           combination_n = n_rsi(cipr, gent)) %>%
+                           combination_n = rsi_n(cipr, gent)) %>%
                  pull(combination_n),
                c(202, 482, 201, 499))
 
@@ -45,22 +61,29 @@ test_that("resistance works", {
 
 
   # check for errors
-  expect_error(IR(septic_patients %>% select(amox, amcl)))
+  expect_error(rsi_IR(septic_patients %>% select(amox, amcl)))
-  expect_error(IR("test", minimum = "test"))
+  expect_error(rsi_IR("test", minimum = "test"))
-  expect_error(IR("test", as_percent = "test"))
+  expect_error(rsi_IR("test", as_percent = "test"))
-  expect_error(S("test", minimum = "test"))
+  expect_error(rsi_I(septic_patients %>% select(amox, amcl)))
-  expect_error(S("test", as_percent = "test"))
+  expect_error(rsi_I("test", minimum = "test"))
-  expect_error(S(septic_patients %>% select(amox, amcl)))
+  expect_error(rsi_I("test", as_percent = "test"))
-  expect_error(S("R", septic_patients %>% select(amox, amcl)))
+  expect_error(rsi_S("test", minimum = "test"))
+  expect_error(rsi_S("test", as_percent = "test"))
+  expect_error(rsi_S(septic_patients %>% select(amox, amcl)))
+  expect_error(rsi_S("R", septic_patients %>% select(amox, amcl)))
 
   # check too low amount of isolates
-  expect_identical(IR(septic_patients$amox, minimum = nrow(septic_patients) + 1),
+  expect_identical(rsi_R(septic_patients$amox, minimum = nrow(septic_patients) + 1),
                    NA)
-  expect_identical(S(septic_patients$amox, minimum = nrow(septic_patients) + 1),
+  expect_identical(rsi_I(septic_patients$amox, minimum = nrow(septic_patients) + 1),
+                   NA)
+  expect_identical(rsi_S(septic_patients$amox, minimum = nrow(septic_patients) + 1),
                    NA)
 
   # warning for speed loss
-  expect_warning(S(septic_patients$amcl, as.character(septic_patients$gent)))
+  expect_warning(rsi_R(as.character(septic_patients$gent)))
+  expect_warning(rsi_I(as.character(septic_patients$gent)))
+  expect_warning(rsi_S(septic_patients$amcl, as.character(septic_patients$gent)))
 
 })