AMR/man/resistance_predict.Rd

123 lines
4.7 KiB
Plaintext
Raw Normal View History

2018-02-21 11:52:31 +01:00
% Generated by roxygen2: do not edit by hand
2018-07-13 17:23:46 +02:00
% Please edit documentation in R/resistance.R
\name{resistance_predict}
\alias{resistance_predict}
2018-02-21 11:52:31 +01:00
\alias{rsi_predict}
\title{Predict antimicrobial resistance}
\usage{
2018-07-26 16:30:42 +02:00
resistance_predict(tbl, col_ab, col_date, year_min = NULL, year_max = NULL,
year_every = 1, minimum = 30, model = "binomial", I_as_R = TRUE,
2018-07-13 17:23:46 +02:00
preserve_measurements = TRUE, info = TRUE)
2018-07-26 16:30:42 +02:00
rsi_predict(tbl, col_ab, col_date, year_min = NULL, year_max = NULL,
year_every = 1, minimum = 30, model = "binomial", I_as_R = TRUE,
2018-02-21 11:52:31 +01:00
preserve_measurements = TRUE, info = TRUE)
}
\arguments{
2018-07-26 16:30:42 +02:00
\item{tbl}{a \code{data.frame} containing isolates.}
2018-02-21 11:52:31 +01:00
2018-07-26 16:30:42 +02:00
\item{col_ab}{column name of \code{tbl} with antimicrobial interpretations (\code{R}, \code{I} and \code{S})}
2018-02-21 11:52:31 +01:00
2018-07-26 16:30:42 +02:00
\item{col_date}{column name of the date, will be used to calculate years if this column doesn't consist of years already}
2018-02-21 11:52:31 +01:00
2018-07-26 16:30:42 +02:00
\item{year_min}{lowest year to use in the prediction model, dafaults the lowest year in \code{col_date}}
\item{year_max}{highest year to use in the prediction model, defaults to 15 years after today}
2018-02-21 11:52:31 +01:00
\item{year_every}{unit of sequence between lowest year found in the data and \code{year_max}}
2018-07-26 16:30:42 +02:00
\item{minimum}{minimal amount of available isolates per year to include. Years containing less observations will be estimated by the model.}
2018-02-21 11:52:31 +01:00
\item{model}{the statistical model of choice. Valid values are \code{"binomial"} (or \code{"binom"} or \code{"logit"}) or \code{"loglin"} or \code{"linear"} (or \code{"lin"}).}
\item{I_as_R}{treat \code{I} as \code{R}}
2018-07-26 16:30:42 +02:00
\item{preserve_measurements}{logical to indicate whether predictions of years that are actually available in the data should be overwritten with the original data. The standard errors of those years will be \code{NA}.}
2018-02-21 11:52:31 +01:00
\item{info}{print textual analysis with the name and \code{\link{summary}} of the model.}
}
\value{
2018-07-26 16:30:42 +02:00
\code{data.frame} with columns:
\itemize{
\item{\code{year}}
2018-07-28 09:34:03 +02:00
\item{\code{value}, the same as \code{estimated} when \code{preserve_measurements = FALSE}, and a combination of \code{observed} and \code{estimated} otherwise}
2018-07-26 16:30:42 +02:00
\item{\code{se_min}, the lower bound of the standard error with a minimum of \code{0}}
\item{\code{se_max} the upper bound of the standard error with a maximum of \code{1}}
\item{\code{observations}, the total number of observations, i.e. S + I + R}
\item{\code{observed}, the original observed values}
\item{\code{estimated}, the estimated values, calculated by the model}
}
2018-02-21 11:52:31 +01:00
}
\description{
2018-02-27 20:01:02 +01:00
Create a prediction model to predict antimicrobial resistance for the next years on statistical solid ground. Standard errors (SE) will be returned as columns \code{se_min} and \code{se_max}. See Examples for a real live example.
2018-02-21 11:52:31 +01:00
}
\examples{
\dontrun{
2018-07-26 16:30:42 +02:00
# use it with base R:
resistance_predict(tbl = tbl[which(first_isolate == TRUE & genus == "Haemophilus"),],
col_ab = "amcl", col_date = "date")
2018-04-02 16:05:09 +02:00
2018-07-26 16:30:42 +02:00
# or use dplyr so you can actually read it:
2018-02-22 20:48:48 +01:00
library(dplyr)
2018-02-21 11:52:31 +01:00
tbl \%>\%
filter(first_isolate == TRUE,
genus == "Haemophilus") \%>\%
2018-07-26 16:30:42 +02:00
resistance_predict(amcl, date)
2018-02-27 20:01:02 +01:00
}
2018-02-21 11:52:31 +01:00
2018-02-27 20:01:02 +01:00
# real live example:
library(dplyr)
septic_patients \%>\%
# get bacteria properties like genus and species
2018-04-02 16:05:09 +02:00
left_join_microorganisms("bactid") \%>\%
2018-02-27 20:01:02 +01:00
# calculate first isolates
2018-04-02 16:05:09 +02:00
mutate(first_isolate =
2018-02-27 20:01:02 +01:00
first_isolate(.,
"date",
"patient_id",
2018-03-27 17:43:42 +02:00
"bactid",
2018-02-27 20:01:02 +01:00
col_specimen = NA,
2018-04-02 16:05:09 +02:00
col_icu = NA)) \%>\%
2018-02-27 20:01:02 +01:00
# filter on first E. coli isolates
2018-04-02 16:05:09 +02:00
filter(genus == "Escherichia",
species == "coli",
2018-02-27 20:01:02 +01:00
first_isolate == TRUE) \%>\%
# predict resistance of cefotaxime for next years
2018-07-26 16:30:42 +02:00
resistance_predict(col_ab = "cfot",
col_date = "date",
year_max = 2025,
preserve_measurements = TRUE,
minimum = 0)
2018-02-27 20:01:02 +01:00
2018-07-26 16:30:42 +02:00
# create nice plots with ggplot
if (!require(ggplot2)) {
data <- septic_patients \%>\%
filter(bactid == "ESCCOL") \%>\%
resistance_predict(col_ab = "amox",
col_date = "date",
info = FALSE,
minimum = 15)
ggplot(data,
aes(x = year)) +
2018-07-28 09:34:03 +02:00
geom_col(aes(y = value),
2018-07-26 16:30:42 +02:00
fill = "grey75") +
geom_errorbar(aes(ymin = se_min,
ymax = se_max),
colour = "grey50") +
scale_y_continuous(limits = c(0, 1),
breaks = seq(0, 1, 0.1),
labels = paste0(seq(0, 100, 10), "\%")) +
labs(title = expression(paste("Forecast of amoxicillin resistance in ",
italic("E. coli"))),
y = "\%IR",
x = "Year") +
theme_minimal(base_size = 13)
}
2018-02-21 11:52:31 +01:00
}
\seealso{
2018-07-13 17:23:46 +02:00
\code{\link{resistance}} \cr \code{\link{lm}} \code{\link{glm}}
2018-02-21 11:52:31 +01:00
}