How to make more from exposure data? An integrated machine learning pipeline to predict pathogen exposure

Abstract

Predicting infectious disease dynamics is a central challenge in disease ecology.Models that can assess which individuals are most at risk of being exposed to a pathogen not only provide valuable insights into disease transmission and dynamics but can also guide management interventions. Constructing such models for wild animal populations, however, is particularly challenging; often only serological data are available on a subset of individuals and nonlinear relationships between variables are common.2. Here we provide a guide to the latest advances in statistical machine learning to construct pathogen-risk models that automatically incorporate complex nonlinear relationships with minimal statistical assumptions from ecological data with missing data. Our approach compares multiple machine learning algorithms in a unified environment to find the model with the best predictive performance and uses game theory to better interpret results. We apply this framework on two major pathogens that infect African lions: canine distemper virus (CDV) and feline parvovirus.3. Our modelling approach provided enhanced predictive performance compared to more traditional approaches, as well as new insights into disease risks in a wild population. We were able to efficiently capture and visualize strong nonlinear patterns, as well as model complex interactions between variables in shaping exposure risk from CDV and feline parvovirus. For example, we found that lions were more likely to be exposed to CDV at a young age but only in low rainfall years.4. When combined with our data calibration approach, our framework helped us to answer questions about risk of pathogen exposure that are difficult to address with previous methods. Our framework not only has the potential to aid in predicting disease risk in animal populations, but also can be used to build robust predictive models suitable for other ecological applications such as modelling species distribution or diversity patterns. K E Y W O R D Sboosted regression trees, disease ecology, gradient boosting models, machine learning, model-agnostic methods, random forests, serology, support vector machines Plotting prevalence relationships across host age and time is an essential first step to start calibrating exposure models. When evaluating year-prevalence curves, spikes in prevalence in certain years may estimate the timing of likely epidemics, particularly when the yearprevalence curves of juveniles are considered (Figure 1; Packer et al., 1999). Knowledge of pathogen natural history (e.g. chronic vs. acute infection) and analyses such as chi-squared test that quantify temporal fluctuations can be used to support these estimates (Figure 1, | 1449Journal of Animal Ecology FOUNTAIN-JONES ET Al.

Using Machine Learning to Unveil Demographic and Clinical Features of COVID-19 Symptomatic and Asymptomatic Patients

“…We used an extensive ML ensemble pipeline [18], which is comprised of ve supervised algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), gradient boosting (GBM), and extreme gradient boosting (XGB) to build a predictive model for the SARS-CoV-2 symptom status. We used multiple ML algorithms and compared the differences in their predictive performances.…”

“…We used multiple ML algorithms and compared the differences in their predictive performances. Some ML algorithms are less exible to missing data (i.e., SVM) [18], and therefore we imputed missing data using the RF-based nonparametric routine implemented in 'missForest' R package [19]. Also, because some of our selected algorithms (i.e., LR) cannot accommodate strongly collinear features, we removed features with the largest mean absolute correlation ( > 0.7) [20].…”

“…We calculated these parameters using the average confusion matrix across all folds of the cross-validation and used the default grid parameter settings in the training process of all algorithms. The K-fold approach was selected, because it can prevent over tting and arti cial in ation of Acc, due to the use of the same data for training and validation [18]. We then selected the best performing algorithm to predict the probability ( ) of COVID-19 symptom status by comparing the estimated validation parameters of each model using the testing dataset.…”

Uptake of Diagnostic Tests by Livestock Farmers: A Stochastic Game Theory Approach

“…In the context of veterinary disease control, relatively little research has applied game-theoretic techniques, mostly using the standard static strategic-form game approach (21,22). Here, we combine epidemiological and economic parameters in type of game called a stochastic game that aims to analyse the adoption of the new diagnostic ELISA test for sheep scab in Scotland, where sheep scab is a notifiable disease requiring treatment upon confirmatory diagnosis.…”

Machine-learning model led design to experimentally test species thermal limits: the case of kissing bugs (Triatominae)

“…To facilitate the design of such kind of experiments (which, in theory, could involve hundreds or thousands of combinations) we propose a methodology based upon a machine learning pipeline approach [25] in order to predict the survival of triatomines by different combinations of micro-climatic temperature values and exposure times. This approach leverages recent advance in machine learning to construct powerful but interpretable predictive models that can guide what combinations of variables could be important in shaping a species thermal limit and thus can configure feasible experimental designs.…”