diff --git a/R/get_expected_total_infections.R b/R/get_expected_total_infections.R
index fd2197780e72d9c4415149a0400d7ad838ef69ce..a2fb431bbf66b39bbea7d3a107b88779ac77fe88 100644
--- a/R/get_expected_total_infections.R
+++ b/R/get_expected_total_infections.R
@@ -1,87 +1,55 @@
#' Expected number of total symptomatic infections
#'
-#' Calculates the expected total number of symptomatic infections,
-#' based on the size of the group, the age group and the setting of the event.
+#' Calculates the expected total number of symptomatic infections after a group event,
+#' based on the observed infections so far.
#'
-#' The values of age-specific symptomatic and susceptibility rates are from
-#' Davies et al. (2020).
+#' meanlog and sdlog are the log-normal distribution parameters derived from
+#' the incubation period characteristics described in Xin et al. (2021).
+#' Note that the function often clearly overestimates the number of symptomatic infections
+#' if last_day_reported_infections is less than 3.
#'
#' @param group_size integer, size of the group.
-#' @param age_group character, the age group of the group, default is "mixed",
-#' possible other entries are "children", "adults" or "elderly".
-#' @param setting character, the setting of the event, default is "neutral",
-#' possible entries are "high risk" or "low risk".
-#' @return The number of expected symptomatic infections.
-#'
-#' @references Davies NG, Klepac P, Liu Y et al. (2020) "Age-dependent effects
-#' in the transmission and control of COVID-19 epidemics". \emph{Nature Medicine},
-#' 26: 1205-1211.
+#' @param last_day_reported_infection Number of days the last infection was reported after the event (0 = event day).
+#' @param total_reported_infections Number of reported symptomatic infections so far.
+#' @param meanlog Number, the parameter of mean from the log-normal distribution.
+#' @param sdlog Number, the parameter of sd from the log-normal distribution.
+#' @return The total number of expected symptomatic infections.
#'
#' @examples
-#' get_expected_total_infections(20)
-#' get_expected_total_infections(20, age_group = "elderly", setting = "high risk")
+#' get_expected_total_infections(25, 5, 4)
#'
#' @export
get_expected_total_infections <- function(group_size,
- age_group = "mixed",
- setting = "neutral") {
+ last_day_reported_infection,
+ total_reported_infections,
+ meanlog = 1.69,
+ sdlog = 0.55) {
val_get_expected_total_infections(group_size,
- age_group,
- setting)
-
- exposed <- group_size # so far assumption everyone was exposed to virus
- ## but e.g. for a group of 500 probably not every person was really exposed
+ last_day_reported_infection,
+ total_reported_infections,
+ meanlog,
+ sdlog)
- if (age_group == "children") { # age < 20
- symptomatic_rate <- 0.25
- if (setting == "high risk") {
- infections <- 0.55 * exposed
- } else if (setting == "low risk") {
- infections <- 0.26 * exposed
- } else {
- infections <- 0.39 * exposed
- }
- } else if (age_group == "adults") { # age 20-59
- symptomatic_rate <- 0.38
- if (setting == "high risk") {
- infections <- 0.97 * exposed
- } else if (setting == "low risk") {
- infections <- 0.63 * exposed
- } else {
- infections <- 0.81 * exposed
- }
- } else if (age_group == "elderly") { # age >= 60
- symptomatic_rate <- 0.66
- if (setting == "high risk") {
- infections <- 0.95 * exposed
- } else if (setting == "low risk") {
- infections <- 0.63 * exposed
- } else {
- infections <- 0.81 * exposed
- }
- } else { # mixed age groups
- symptomatic_rate <- 0.41
- if (setting == "high risk") {
- infections <- 0.85 * exposed
- } else if (setting == "low risk") {
- infections <- 0.54 * exposed
- } else {
- infections <- 0.71 * exposed
- }
- }
+ theoretical_probs <- smidm::get_incubation_day_distribution(last_day_reported_infection,
+ meanlog,
+ sdlog)
- # round up for worst case
- return(ceiling(symptomatic_rate * infections))
+ return(min(ceiling(total_reported_infections * sum(theoretical_probs)^-1),
+ group_size))
}
val_get_expected_total_infections <- function(group_size,
- age_group,
- setting){
+ last_day_reported_infection,
+ total_reported_infections,
+ meanlog,
+ sdlog){
smidm_is_natural_number(group_size)
- smidm_is_character(age_group)
- smidm_is_character(setting)
+ smidm_is_natural_number(last_day_reported_infection)
+ smidm_is_natural_number(total_reported_infections)
+ smidm_is_parameter_log_mean(meanlog)
+ smidm_is_parameter_log_sd(sdlog)
}
diff --git a/man/get_expected_total_infections.Rd b/man/get_expected_total_infections.Rd
index a8a69faf7208ff165086a466ca2846f62715e341..e215cef075031521e7ab6bcd8917bc5194a280fc 100644
--- a/man/get_expected_total_infections.Rd
+++ b/man/get_expected_total_infections.Rd
@@ -6,37 +6,37 @@
\usage{
get_expected_total_infections(
group_size,
- age_group = "mixed",
- setting = "neutral"
+ last_day_reported_infection,
+ total_reported_infections,
+ meanlog = 1.69,
+ sdlog = 0.55
)
}
\arguments{
\item{group_size}{integer, size of the group.}
-\item{age_group}{character, the age group of the group, default is "mixed",
-possible other entries are "children", "adults" or "elderly".}
+\item{last_day_reported_infection}{Number of days the last infection was reported after the event (0 = event day).}
-\item{setting}{character, the setting of the event, default is "neutral",
-possible entries are "high risk" or "low risk".}
+\item{total_reported_infections}{Number of reported symptomatic infections so far.}
+
+\item{meanlog}{Number, the parameter of mean from the log-normal distribution.}
+
+\item{sdlog}{Number, the parameter of sd from the log-normal distribution.}
}
\value{
-The number of expected symptomatic infections.
+The total number of expected symptomatic infections.
}
\description{
-Calculates the expected total number of symptomatic infections,
-based on the size of the group, the age group and the setting of the event.
+Calculates the expected total number of symptomatic infections after a group event,
+based on the observed infections so far.
}
\details{
-The values of age-specific symptomatic and susceptibility rates are from
-Davies et al. (2020).
+meanlog and sdlog are the log-normal distribution parameters derived from
+the incubation period characteristics described in Xin et al. (2021).
+Note that the function often clearly overestimates the number of symptomatic infections
+if last_day_reported_infections is less than 3.
}
\examples{
-get_expected_total_infections(20)
-get_expected_total_infections(20, age_group = "elderly", setting = "high risk")
+get_expected_total_infections(25, 5, 4)
}
-\references{
-Davies NG, Klepac P, Liu Y et al. (2020) "Age-dependent effects
-in the transmission and control of COVID-19 epidemics". \emph{Nature Medicine},
-26: 1205-1211.
-}
diff --git a/man/predict_future_infections.Rd b/man/predict_future_infections.Rd
index 889d8c3c5cde79ddf36ada3e6d4ee355075afaf3..51bdbf3dbd6cd438e0ee9e2f882a23d9da613a54 100644
--- a/man/predict_future_infections.Rd
+++ b/man/predict_future_infections.Rd
@@ -13,11 +13,11 @@ predict_future_infections(
)
}
\arguments{
-\item{last_day_reported_infection}{Number of days the last infection was reported after the event (1 = event day)}
+\item{last_day_reported_infection}{Number of days the last infection was reported after the event (0 = event day).}
-\item{total_reported_infections}{Number of reported symptomatic infections so far}
+\item{total_reported_infections}{Number of reported symptomatic infections so far.}
-\item{total_expected_infections}{Number of expected symptomatic infections in total}
+\item{total_expected_infections}{Number of expected symptomatic infections in total.}
\item{meanlog}{Number, the parameter of mean from the log-normal distribution.}
diff --git a/tests/testthat/test_get_expected_total_infections.R b/tests/testthat/test_get_expected_total_infections.R
index f487b636ec7b8125165f913fe8ea25828a219a24..c8f79d15ee90b0798ed1d2efe54e4e5cd8a82bf9 100644
--- a/tests/testthat/test_get_expected_total_infections.R
+++ b/tests/testthat/test_get_expected_total_infections.R
@@ -1,23 +1,14 @@
test_that("get_expected_total_infections_defaults", {
- expect_equal(get_expected_total_infections(1),1)
- expect_equal(get_expected_total_infections(10),3)
- expect_equal(get_expected_total_infections(100),30)
-})
+ expect_equal(get_expected_total_infections(1,1,1),1)
+ expect_equal(get_expected_total_infections(10,1,1),10)
+ expect_equal(get_expected_total_infections(100,1,1),100)
+ expect_equal(get_expected_total_infections(1,3,1),1)
+ expect_equal(get_expected_total_infections(10,3,1),8)
+ expect_equal(get_expected_total_infections(100,3,1),8)
-test_that("get_expected_total_infections_high_risk_elderly", {
- age_group <- "elderly"
- setting <- "high risk"
- expect_equal(get_expected_total_infections(1, age_group, setting),1)
- expect_equal(get_expected_total_infections(10, age_group, setting),7)
- expect_equal(get_expected_total_infections(100, age_group, setting),63)
+ expect_equal(get_expected_total_infections(1,5,1),1)
+ expect_equal(get_expected_total_infections(10,5,1),3)
+ expect_equal(get_expected_total_infections(100,5,1),3)
})
-
-test_that("get_expected_total_infections_low_risk_children", {
- age_group <- "children"
- setting <- "low risk"
- expect_equal(get_expected_total_infections(1, age_group, setting),1)
- expect_equal(get_expected_total_infections(10, age_group, setting),1)
- expect_equal(get_expected_total_infections(100, age_group, setting),7)
-})
diff --git a/vignettes/future_infections.Rmd b/vignettes/future_infections.Rmd
index b87b1253a4d5e62aefe89852388cf6b50fc2fd26..24828b4bcbc45b90fe73af7c79cfcedaac06a465 100644
--- a/vignettes/future_infections.Rmd
+++ b/vignettes/future_infections.Rmd
@@ -53,9 +53,9 @@ library(ggplot2)
## Question
-A family party with 25 participants took place on the 15.03.2022 in a closed room and no masks were worn. In the following days some participants start to show symptoms of a COVID-19 infection: one on 17.03.2022 and three on 18.03.2022. How many further symptomatic infections can be expected in the following days?
+A family party with 25 participants took place on the 15.03.2022 in a closed room and no masks were worn. In the following days some participants start to show symptoms of a COVID-19 infection: one on 18.03.2022 and three on 20.03.2022. How many further symptomatic infections can be expected in the following days?
-## Calculating a literature-based prediction of total number of infections with `get_expected_total_infections`
+## Calculating a prediction of the total number of infections with `get_expected_total_infections`
The function `get_expected_total_infections()` can be used to give a first answer to the question. It returns a prediction how many people in the group are expected to show symptoms in total.
@@ -65,30 +65,30 @@ The following input values are necessary for the function `get_expected_total_in
The `group_size` is the number of people participating in the event, including all observed infections.
-Next, the `age_group` can be given as `"children"` for people aged 0-19, `"adults"` for people aged 20-59, `"elderly"` for people of age 60 or older and `"mixed"` (the default) if there is no clear age group or it is unknown.
+The `last_day_reported_infection` is the number of days after the event when the last symptom begin was observed and the `total_reported_infections` is the total number of observed infections so far.
-Lastly, the `setting` can be described as `"high risk"`, e.g. if no masks were worn in a closed room for a long time, `"low risk"`, e.g. if masks were worn outside and the people kept enough distance, or `"neutral"` (the default) if the risk is between high and low or unknown.
+Finally, `meanlog` and `sdlog` are the mean and standard deviation parameters of the log-normal distribution for the incubation time.
### Methodology
-It is assumed that every participant was directly exposed to the virus. Hence, the `group_size` is simply multiplied by the rate of expected symptomatic infections based on the `age_group` and the `setting`. The values of age-specific symptomatic and susceptibility rates are from Davies et al. [1].
+Based on the incubation time distribution one can calculate the percentage of all symptomatic infections that will have their symptom onset up to the `last_day_reported_infection`. Then, said percentage is combined with the `total_reported_infections` to calculate the total symptomatic infections. The minimum between the result and the `group_size` is returned, because the `group_size`is obviously an upper bound for the total infections.
### Output
```{r get_expected_total_infections}
group_size = 25
-age_group = "mixed"
-setting = "high risk"
+last_day_reported_infections = 5 # day 0 = event day
+total_reported_infections = 4
predicted_total_infections <- get_expected_total_infections(group_size,
- age_group,
- setting)
+ last_day_reported_infections,
+ total_reported_infections)
print(predicted_total_infections)
```
The output represents how many people are expected to get a symptomatic infection.
-In the example 9 infections are predicted in total, which implies one can expect 5 further people starting to show symptoms in the next days because 4 infections were already observed.
+In the example 10 infections are predicted in total, which implies one can expect 6 further people starting to show symptoms in the next days because 4 infections were already observed.
## Generating a vector with number of people starting to show symptoms on each day using \newline `predict_future_infections`
@@ -101,7 +101,7 @@ Multiple arguments are necessary for the function `predict_future_infections()`
The `last_day_reported_infection` is the number of days after the event when the last symptom begin was observed and the `total_reported_infections` is the total number of observed infections so far.
-Then, the `total_expected_infections` is needed, which defines the total number of expected infections, including the ones already observed. If no own estimation for this is available, the output of `get_expected_total_infections()` can be used.
+Then, the `total_expected_infections` is needed, which defines the total number of expected infections, including the ones already observed. One can use the output of `get_expected_total_infections()` or an own estimation based on e.g. reported symptomatic infection rates in a population of interest. If the output of `get_expected_total_infections()` is used, then it should be based on the same `meanlog` and `sdlog` as in the call to `predict_future_infections()`.
Finally, `meanlog` and `sdlog` are the mean and standard deviation parameters of the log-normal distribution for the incubation time.
@@ -119,9 +119,9 @@ When at some point the updated `total_reported_infections` is not smaller than `
### Output
```{r predict_future_infections}
-last_day_reported_infections = 3 # day 0 = event day
+last_day_reported_infections = 5 # day 0 = event day
total_reported_infections = 4
-total_expected_infections = get_expected_total_infections(25, "mixed", "high risk")
+total_expected_infections = get_expected_total_infections(25, 5, 4)
predicted_daily_infections <- predict_future_infections(last_day_reported_infections,
total_reported_infections,
@@ -135,8 +135,8 @@ The function `predict_future_infections()` creates a vector with values represen
## An example for visualizing the output of \newline `predict_future_infections`
```{r libraries, foldcode = TRUE, message = FALSE}
-data <- data.frame("Erkrankungsdatum" = as.Date("2022-03-15") + 0:3,
- "Neue_Faelle" = c(0, 0, 1, 3))
+data <- data.frame("Erkrankungsdatum" = as.Date("2022-03-15") + 0:5,
+ "Neue_Faelle" = c(0, 0, 0, 1, 0, 3))
expected <- data.frame("Erkrankungsdatum" = as.Date("2022-03-15") + 1:(length(predicted_daily_infections)),
"ErwarteteWeitereFaelle" = predicted_daily_infections)
g <- ggplot(expected) +