Limits...
Accuracy of climate-based forecasts of pathogen spread

View Article: PubMed Central - PubMed

ABSTRACT

Species distribution models (SDMs) are a tool for predicting the eventual geographical range of an emerging pathogen. Most SDMs, however, rely on an assumption of equilibrium with the environment, which an emerging pathogen, by definition, has not reached. To determine if some SDM approaches work better than others for modelling the spread of emerging, non-equilibrium pathogens, we studied time-sensitive predictive performance of SDMs for Batrachochytrium dendrobatidis, a devastating infectious fungus of amphibians, using multiple methods trained on time-incremented subsets of the available data. We split our data into timeline-based training and testing sets, and evaluated models on each set using standard performance criteria, including AUC, kappa, false negative rate and the Boyce index. Of eight models examined, we found that boosted regression trees and random forests performed best, closely followed by MaxEnt. As expected, predictive performance generally improved with the length of time series used for model training. These results provide information on how quickly the potential extent of an emerging disease may be determined, and identify which modelling frameworks are likely to provide useful information during the early phases of pathogen expansion.

No MeSH data available.


Related in: MedlinePlus

(a) Random forest and (b) boosted regression trees prediction maps from the five-part chronological analysis. Training data were Bd points from 1980–2008; test data were points from 2009–2011.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5383844&req=5

RSOS160975F6: (a) Random forest and (b) boosted regression trees prediction maps from the five-part chronological analysis. Training data were Bd points from 1980–2008; test data were points from 2009–2011.

Mentions: We used maps of suitability to visually compare outputs of the two best models, RF and BRT. Mapped predictions (figure 6) generally aligned with Bd observations (figure 1) and are similar between the two models. Model outputs suggested that Southeast Asia and Australia, already infected by Bd, could see further interior spread (figure 6). Additionally, both models identify suitable uncolonized areas in eastern Madagascar, the Middle East and near the Chinese-Russian border (figure 6).Figure 6.


Accuracy of climate-based forecasts of pathogen spread
(a) Random forest and (b) boosted regression trees prediction maps from the five-part chronological analysis. Training data were Bd points from 1980–2008; test data were points from 2009–2011.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5383844&req=5

RSOS160975F6: (a) Random forest and (b) boosted regression trees prediction maps from the five-part chronological analysis. Training data were Bd points from 1980–2008; test data were points from 2009–2011.
Mentions: We used maps of suitability to visually compare outputs of the two best models, RF and BRT. Mapped predictions (figure 6) generally aligned with Bd observations (figure 1) and are similar between the two models. Model outputs suggested that Southeast Asia and Australia, already infected by Bd, could see further interior spread (figure 6). Additionally, both models identify suitable uncolonized areas in eastern Madagascar, the Middle East and near the Chinese-Russian border (figure 6).Figure 6.

View Article: PubMed Central - PubMed

ABSTRACT

Species distribution models (SDMs) are a tool for predicting the eventual geographical range of an emerging pathogen. Most SDMs, however, rely on an assumption of equilibrium with the environment, which an emerging pathogen, by definition, has not reached. To determine if some SDM approaches work better than others for modelling the spread of emerging, non-equilibrium pathogens, we studied time-sensitive predictive performance of SDMs for Batrachochytrium dendrobatidis, a devastating infectious fungus of amphibians, using multiple methods trained on time-incremented subsets of the available data. We split our data into timeline-based training and testing sets, and evaluated models on each set using standard performance criteria, including AUC, kappa, false negative rate and the Boyce index. Of eight models examined, we found that boosted regression trees and random forests performed best, closely followed by MaxEnt. As expected, predictive performance generally improved with the length of time series used for model training. These results provide information on how quickly the potential extent of an emerging disease may be determined, and identify which modelling frameworks are likely to provide useful information during the early phases of pathogen expansion.

No MeSH data available.


Related in: MedlinePlus