Create a prediction model to predict antimicrobial resistance for the next years on statistical solid ground. Standard errors (SE) will be returned as columns se_min and se_max. See Examples for a real live example.

resistance_predict(x, col_ab, col_date = NULL, year_min = NULL,
  year_max = NULL, year_every = 1, minimum = 30, model = NULL,
  I_as_S = TRUE, preserve_measurements = TRUE, info = TRUE, ...)

rsi_predict(x, col_ab, col_date = NULL, year_min = NULL,
  year_max = NULL, year_every = 1, minimum = 30, model = NULL,
  I_as_S = TRUE, preserve_measurements = TRUE, info = TRUE, ...)

# S3 method for resistance_predict
plot(x,
  main = paste("Resistance Prediction of", x_name), ...)

ggplot_rsi_predict(x, main = paste("Resistance Prediction of", x_name),
  ribbon = TRUE, ...)

Arguments

x

a data.frame containing isolates.

col_ab

column name of x with antimicrobial interpretations (R, I and S)

col_date

column name of the date, will be used to calculate years if this column doesn't consist of years already, defaults to the first column of with a date class

year_min

lowest year to use in the prediction model, dafaults to the lowest year in col_date

year_max

highest year to use in the prediction model, defaults to 10 years after today

year_every

unit of sequence between lowest year found in the data and year_max

minimum

minimal amount of available isolates per year to include. Years containing less observations will be estimated by the model.

model

the statistical model of choice. This could be a generalised linear regression model with binomial distribution (i.e. using glm(..., family = binomial)), assuming that a period of zero resistance was followed by a period of increasing resistance leading slowly to more and more resistance. See Details for all valid options.

I_as_S

a logical to indicate whether values I should be treated as S (will otherwise be treated as R)

preserve_measurements

a logical to indicate whether predictions of years that are actually available in the data should be overwritten by the original data. The standard errors of those years will be NA.

info

a logical to indicate whether textual analysis should be printed with the name and summary of the statistical model.

...

parameters passed on to functions

main

title of the plot

ribbon

a logical to indicate whether a ribbon should be shown (default) or error bars

Value

data.frame with extra class "resistance_predict" with columns:

  • year

  • value, the same as estimated when preserve_measurements = FALSE, and a combination of observed and estimated otherwise

  • se_min, the lower bound of the standard error with a minimum of 0 (so the standard error will never go below 0%)

  • se_max the upper bound of the standard error with a maximum of 1 (so the standard error will never go above 100%)

  • observations, the total number of available observations in that year, i.e. S + I + R

  • observed, the original observed resistant percentages

  • estimated, the estimated resistant percentages, calculated by the model

Furthermore, the model itself is available as an attribute: attributes(x)$model, see Examples.

Details

Valid options for the statistical model are:

  • "binomial" or "binom" or "logit": a generalised linear regression model with binomial distribution

  • "loglin" or "poisson": a generalised log-linear regression model with poisson distribution

  • "lin" or "linear": a linear regression model

Read more on our website!

On our website https://msberends.gitlab.io/AMR you can find a tutorial about how to conduct AMR analysis, the complete documentation of all functions (which reads a lot easier than here in R) and an example analysis using WHONET data.

See also

The portion function to calculate resistance,
lm glm

Examples

# NOT RUN {
x <- resistance_predict(septic_patients, col_ab = "AMX", year_min = 2010)
plot(x)
ggplot_rsi_predict(x)

# use dplyr so you can actually read it:
library(dplyr)
x <- septic_patients %>%
  filter_first_isolate() %>%
  filter(mo_genus(mo) == "Staphylococcus") %>%
  resistance_predict("PEN")
plot(x)


# get the model from the object
mymodel <- attributes(x)$model
summary(mymodel)


# create nice plots with ggplot2 yourself
if (!require(ggplot2)) {

  data <- septic_patients %>%
    filter(mo == as.mo("E. coli")) %>%
    resistance_predict(col_ab = "AMX",
                       col_date = "date",
                       info = FALSE,
                       minimum = 15)

  ggplot(data,
         aes(x = year)) +
    geom_col(aes(y = value),
             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)
}
# }