,
Lasse Engbo Christiansen [aut, cre]
,
Statens Serum Institut, SSI [cph, fnd]| Title: | Automated and Early Detection of Disease Outbreaks |
|---|---|
| Description: | A powerful tool for automating the early detection of disease outbreaks in time series data. 'aeddo' employs advanced statistical methods, including hierarchical models, in an innovative manner to effectively characterize outbreak signals. It is particularly useful for epidemiologists, public health professionals, and researchers seeking to identify and respond to disease outbreaks in a timely fashion. For a detailed reference on hierarchical models, consult Henrik Madsen and Poul Thyregod's book (2011), ISBN: 9781420091557. |
| Authors: | Kasper Schou Telkamp [aut] ,
Lasse Engbo Christiansen [aut, cre]
,
Statens Serum Institut, SSI [cph, fnd] |
| Maintainer: | Lasse Engbo Christiansen <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 0.1.1.9000 |
| Built: | 2025-03-11 05:47:35 UTC |
| Source: | https://github.com/ssi-dk/aeddo |
![[Stable]](data:image/svg+xml;base64,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)
This function performs automated an early detection of disease outbreaks, (aeddo), on a time series data set. It utilizes hierarchical models in an innovative manner to infer one-step ahead random effects. In turn, these random effects are used directly to characterize an outbreak.
aeddo( data = data.frame(), formula = formula(), k = integer(), sig_level = 0.95, exclude_past_outbreaks = TRUE, init_theta = numeric(), lower = numeric(), upper = numeric(), method = "BFGS" )aeddo( data = data.frame(), formula = formula(), k = integer(), sig_level = 0.95, exclude_past_outbreaks = TRUE, init_theta = numeric(), lower = numeric(), upper = numeric(), method = "BFGS" )
data |
A tibble containing the time series data, including columns 'y' for observed values,'n' for population size, and other covariates of interest. |
formula |
A model formula for the fixed effects in the hierarchical model to fit to the data. |
k |
An integer specifying the rolling window size employed for parameter estimation. |
sig_level |
The quantile from the random effects distribution used for defining the for outbreak detection threshold, a numeric value between 0 and 1. |
exclude_past_outbreaks |
logical value indicating whether past outbreak related observations should be excluded from future parameter estimation. |
init_theta |
Initial values for model parameters in optimization. |
lower |
Lower bounds for optimization parameters. |
upper |
Upper bounds for optimization parameters. |
method |
The optimization method to use, either "BFGS" (default) or "L-BFGS-B". |
A tibble-like 'aedseo' object containing:
'window_data': A list of tibble, each representing the data for this windowed parameter estimation.
'reference_data': A list of tibble, each representing the data for the reference time point.
'phi': The dispersion parameter.
'lambda': The estimated outbreak intensity.
'u': The one-step ahead random effect.
'u_probability': The probability of observing the one-step ahead random effect.
'outbreak_alarm': Logical. Indicates if an outbreak is detected.
# Create an example aedseo_tsd object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Print the results print(aeddo_results)# Create an example aedseo_tsd object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Print the results print(aeddo_results)
This function generates a complete 'ggplot' object suitable for
visualizing time series data in an aeddo object. It creates a line
plot connecting the observations and adds points at each data point.
autoplot(object, ...) ## S3 method for class 'aeddo' autoplot(object, ...)autoplot(object, ...) ## S3 method for class 'aeddo' autoplot(object, ...)
object |
An |
... |
Additional arguments (not used). |
A 'ggplot' object for visualizing the time series data.
# Create an example aeddo object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Create a ggplot visualization for the aeddo object autoplot(aeddo_results)# Create an example aeddo object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Create a ggplot visualization for the aeddo object autoplot(aeddo_results)
Calculate the negative log-likelihood for the Poisson Gamma modeling framework.
nll_poisson_gamma(theta, data, formula)nll_poisson_gamma(theta, data, formula)
theta |
A numeric vector containing model parameters. The first part of the vector represents fixed effects, and the remaining part represents model parameters. |
data |
A tibble containing the time series data, including columns 'y' for observed values,'n' for population size, and other covariates of interest. |
formula |
A formula specifying the model structure. |
The negative log-likelihood value.
# Initial parameters theta <- c(0.5, 0.1) # Sample data data <- data.frame( y = c(10, 15, 20, 30, 50, 100, 200, 40, 20, 10), n = c(100, 150, 200, 300, 500, 1000, 2000, 400, 200, 100) ) # Fixed effects model formula fixed_effects_formula <- y ~ 1 # Calculate negative log likelihood nll_poisson_gamma( theta = theta, data = data, formula = fixed_effects_formula )# Initial parameters theta <- c(0.5, 0.1) # Sample data data <- data.frame( y = c(10, 15, 20, 30, 50, 100, 200, 40, 20, 10), n = c(100, 150, 200, 300, 500, 1000, 2000, 400, 200, 100) ) # Fixed effects model formula fixed_effects_formula <- y ~ 1 # Calculate negative log likelihood nll_poisson_gamma( theta = theta, data = data, formula = fixed_effects_formula )
This function generates a complete 'ggplot' object suitable for
visualizing time series data in an aeddo object. It creates a line
plot connecting the observations and adds points at each data point.
## S3 method for class 'aeddo' plot(x, ...)## S3 method for class 'aeddo' plot(x, ...)
x |
An |
... |
Additional arguments (not used). |
A 'ggplot' object for visualizing the time series data.
# Create an example aeddo object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Create a ggplot visualization for the aeddo object plot(aeddo_results)# Create an example aeddo object aeddo_data <- data.frame( time = as.Date(c( "2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04", "2023-01-05", "2023-01-06" )), y = c(100, 120, 180, 110, 130, 140), n = 1 ) # Supply a model formula fixed_effects_formula <- y ~ 1 # Choose a size for the rolling window k <- 2 # ... and quantile for the threshold sig_level <- 0.9 # Employ the algorithm aeddo_results <- aeddo( data = aeddo_data, formula = fixed_effects_formula, k = k, sig_level = sig_level, exclude_past_outbreaks = TRUE, init_theta = c(1, 0), lower = c(-Inf, 1e-6), upper = c(Inf, 1e2), method = "L-BFGS-B" ) # Create a ggplot visualization for the aeddo object plot(aeddo_results)