Predicting dengue importation into Europe, using machine learning and model-agnostic methods

Salami, Donald; Sousa, Carla A.; Martins, Maria do Rosário Oliveira; Capinha, César

doi:10.1101/19013383

Cited by 6 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work has a clear public health relevance. Integrating this approach into existing disease transmission or importation models (Lieberthal and Gardner, 2021; Salami et al, 2020b, 2020a) or with disease-related Internet search activity (Aiken et al, 2020; Yang et al, 2017) and using high resolution environmental data will likely contribute to improve operational, early warning systems of disease risk and guide the implementation of mosquito control measures.…”

Section: Discussionmentioning

confidence: 99%

“…More than half of the world’s population is at risk of disease and economic costs are large, with the costs of dengue alone estimated at US$ 9 billion/year (Mayer et al, 2017; Messina et al, 2019; Shepard et al, 2016). Such diseases are transmitted by mosquitoes of the genus Aedes whose distribution is expanding - and projected to expand further in the future - due to climate change and increased transportation and human mobility (Kraemer et al, 2019; Salami et al, 2020b; Santos et al, 2022). These species are now established in many regions of the world, including in several areas of Europe (Capinha et al, 2014; Oliveira et al, 2021), where outbreaks of Aedes -borne diseases occurred recently (Brady and Hay, 2019; Sousa et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting the numbers of disease vectors with deep learning

Ceia-Hasse

Sousa

Gouveia

et al. 2022

Preprint

View full text Add to dashboard Cite

Arboviral diseases such as dengue, Zika, chikungunya or yellow fever are a worldwide concern. The abundance of vector species plays a key role in the emergence of outbreaks of these diseases, so forecasting these numbers is fundamental in preventive risk assessment. Here we describe and demonstrate a novel approach that uses state-of-the-art deep learning algorithms to forecast disease vector numbers. Unlike classical statistical and machine learning methods, deep learning models use time series data directly as predictors and identify the features that are most relevant from a predictive perspective. We demonstrate the application of this approach to predict temporal trends in the number of Aedes aegypti mosquito eggs across Madeira Island for the period 2013 to 2019. Specifically, we apply the deep learning models to predict whether, in the following week, the number of Ae. aegypti eggs will remain unchanged, or whether it will increase or decrease, considering different percentages of change. We obtained high predictive accuracy for all years considered (mean AUC = 0.92 +- 0.05 sd). We also found that the preceding numbers of eggs is a highly informative predictor of future numbers. Linking our approach to disease transmission or importation models will contribute to operational, early warning systems of arboviral disease risk.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Forecasting the numbers of disease vectors with deep learning

Ceia-Hasse

Sousa

Gouveia

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For Dengue and other comparable diseases, the data could improve projections. Salami, Sousa, Martins, and Capinha (2020) displayed that Dengue fever is a global public health concern when it spreads (Salami et al, 2020). Dengue's spread from locations where it is frequent to areas where it isn't common has increased in cases.…”

Section: Literature Reviewmentioning

confidence: 99%

Dengue Cases Prediction Using Machine Learning Approach

Aziz

2021

iRASD J. Comp. & Info Tech.

View full text Add to dashboard Cite

Dengue fever, spread by mosquitoes, affects about 3.9 billion people worldwide. Health officials could use indicators of dengue fever outbreaks to start taking preventative measures. Controlling dengue fever may be more straightforward for local authorities if they have timely and accurate disease forecasts. As one of the most rapidly spreading diseases globally, dengue fever is a threat to everyone. Dengue outbreaks can be predicted using machine learning, according to this study. Dengue prediction models could benefit from nature-based algorithms being boosted or used. The only thing that mattered in the prediction and training model was the week of the year, which was the only thing that signified. A standard machine learning algorithm cannot simulate long-term dependencies in time-series data, which is necessary for accurate projections in Dengue fever cases. When it comes to developing risk criteria for severe Dengue, machine learning could be a valuable implement in determining the possible behavior to formulate.

show abstract

“…In addition, a popular approach in current research is to interpret the model after building it, that is, a post hoc model-agnostic interpretation method, which is an interpretation method independent of the training model. Even if the prediction results are obtained through a "black box" model, the use of post hoc-assisted attribution interpretation and visualization tools enables explanatory studies of the model [8][9][10], which can help the application personnel understand the process and reason of the model's decision-making.…”

Section: Introductionmentioning

confidence: 99%

Opening the black box: interpretable machine learning for predictor finding of metabolic syndrome

Zhang

Razbek

et al. 2022

BMC Endocr Disord

View full text Add to dashboard Cite

Objective The internal workings ofmachine learning algorithms are complex and considered as low-interpretation "black box" models, making it difficult for domain experts to understand and trust these complex models. The study uses metabolic syndrome (MetS) as the entry point to analyze and evaluate the application value of model interpretability methods in dealing with difficult interpretation of predictive models. Methods The study collects data from a chain of health examination institution in Urumqi from 2017 ~ 2019, and performs 39,134 remaining data after preprocessing such as deletion and filling. RFE is used for feature selection to reduce redundancy; MetS risk prediction models (logistic, random forest, XGBoost) are built based on a feature subset, and accuracy, sensitivity, specificity, Youden index, and AUROC value are used to evaluate the model classification performance; post-hoc model-agnostic interpretation methods (variable importance, LIME) are used to interpret the results of the predictive model. Results Eighteen physical examination indicators are screened out by RFE, which can effectively solve the problem of physical examination data redundancy. Random forest and XGBoost models have higher accuracy, sensitivity, specificity, Youden index, and AUROC values compared with logistic regression. XGBoost models have higher sensitivity, Youden index, and AUROC values compared with random forest. The study uses variable importance, LIME and PDP for global and local interpretation of the optimal MetS risk prediction model (XGBoost), and different interpretation methods have different insights into the interpretation of model results, which are more flexible in model selection and can visualize the process and reasons for the model to make decisions. The interpretable risk prediction model in this study can help to identify risk factors associated with MetS, and the results showed that in addition to the traditional risk factors such as overweight and obesity, hyperglycemia, hypertension, and dyslipidemia, MetS was also associated with other factors, including age, creatinine, uric acid, and alkaline phosphatase. Conclusion The model interpretability methods are applied to the black box model, which can not only realize the flexibility of model application, but also make up for the uninterpretable defects of the model. Model interpretability methods can be used as a novel means of identifying variables that are more likely to be good predictors.

show abstract

Predicting dengue importation into Europe, using machine learning and model-agnostic methods

Cited by 6 publications

References 47 publications

Forecasting the numbers of disease vectors with deep learning

Forecasting the numbers of disease vectors with deep learning

Dengue Cases Prediction Using Machine Learning Approach

Opening the black box: interpretable machine learning for predictor finding of metabolic syndrome

Contact Info

Product

Resources

About