Lectures & Training

This summer school was the second edition of MOOD’s capacity building event, planned for improving knowledge on epidemic intelligence for disease surveillance, including identification of re-emerging infectious diseases and antimicrobial resistance, the changing drivers fueling disease spread, and surveillance and early warning techniques in pandemic threats. During these 6 days, at the MEDILS institute in Split, Croatia, hands-on skills improvement through the use of MOOD tools were highlighted, as well as online materials such as data processing tutorials.

All the lectures were recorded and are hosted on the Leibniz Information Centre for Science and Technology and University Library (TIB AV-Portal), which provides ad-free videos on science, research, industry and business with literature and information. 

Tom Hengl is the co-founder of OpenGeoHub Foundation, the Netherlands, and leader of the Work Package “Dissemination, project sustainability, and impact assessment” of the MOOD project. During the 2023 MOOD Summer School, he gave an introductory course about reproducible research in R.
Daniele Da Re is a Postdoctoral Researcher, at the University of Trento, Italy. During the 2023 MOOD Summer School, he gave a general overview on species distribution modeling from both the conceptual and technical aspects. On the conceptual aspect, he focused on the historical development of the environmental niche concept and on the different but complementary environmental niche concepts. On the technical aspect, he focused on both correlative and mechanistic species distribution models approaches and best practices for performing SDMs exercises.
Daniele Da Re is a Postdoctoral Researcher, at the University of Trento, Italy. Pachka Hammami is a modeler and epidemiologist specialized in epidemiological models for metapopulations and network dynamics, and currently works at CIRAD (UMR ASTRE), France. During the 2023 MOOD Summer School, these two experts hosted a session that gave a general overview on mechanistic models in epidemiology and for vector borne diseases (VBD) in particular. They gave an introduction to two published models for VBD: ArboCarto and dynamAedes. They also gave a demo on both models, and did a comparison of the predicted mosquitoes population dynamics of the two models.
Sarah is a scientist within Avia-GIS, Belgium. During the 2023 MOOD Summer School, she gave a demo of the generic part of the platform allows users to visualize different co-variates data layers. Users can import their own shape files on the platform and export a CSV file with the co-variates values in a zone of interest or at specific points (disease cases, traps, sampling points…). The MOOD platform is co-created by the MOOD expert and the end-users. During this summer school, the students were able to test it and to give a feed-back on the actual state of it.
MOOD project coordinator Elena Arsevska is also a veterinary epidemiologist within Cirad in Montpellier, France. During the 2023 MOOD Summer School, she teached about the different types of spatial data, and provided some examples from real practice. Using the primary biliary cirrhosis (PBC) dataset from the sparr R package, she teached about basic spatial point pattern analysis and specifically, and allowed attendees to explore how to do the following: Divide our study zone into quadrants, followed by performing spatial randomness test Estimate and map kernel density to look for the density of cases in space Estimate and map relative risk (RR) to identify hotspots for higher density of cases over controls Save our RR (heat map) as a raster layer.
Daniele Da Re is a Postdoctoral Researcher, at the University of Trento, Italy. Cedric Marsboom is CTO of Avia-GIS, Belgium. During the 2023 MOOD Summer School, these two experts hosted a session to give an introduction to correlative SDMs in R using virtual species as example. A tutorial was provided and both the GLM and RF methods were explained. We first analyze each algorithm separately and the produced ensemble models. In the final part of the lesson we focused on discussing different predictive accuracy metrics.
Tom Hengl is the co-founder of OpenGeoHub Foundation, the Netherlands, and leader of the Work Package “Dissemination, project sustainability, and impact assessment” of the MOOD project. As a PhD candidate and research within OpenGeoHub Foundation, Carmelo focuses on data science projects such as GeoHarmonizer and the MOOD H2020 project. During the 2023 MOOD Summer School, these two experts gave a lecture where the students learned how to combine all the tools that were introduced in the previous lectures: point data, predictor variables, different modeling and validation techniques. The algorithms explored in the previous lectures are here combined to produce results that are in general more robust than when using a single algorithm only.
MOOD project coordinator Elena Arsevska is also a veterinary epidemiologist within Cirad in Montpellier, France. Bahdja Boudoua is a second-year PhD student at the UMR TETIS, France. In this session of the 2023 MOOD Summer School, the two experts showed the open access tool Padi-web tool (https://padi-web.cirad.fr/en/) developed by CIRAD/INRAE. Padi-web monitors online news and extracts of information on epidemiological events (such as outbreaks) detected in the news. They showed how to filter news by disease, syndrom, and explore combinations with different hosts and time period. They also showed some research activities using the Padi-web datasets and disease case studies, ranging from text mining to network analysis and epidemiological modelling.
Mehtab is a researcher within Cirad. In this session of the 2023 MOOD Summer School, attendees practically explored the process of transforming the Avian-Influenza article dataset into an informative dashboard using various visualizations. Specifically, they focused on extracting location information from the text of the articles. In the next step, they transformed the extracted location information into different visual representations such as word clouds, top 10 countries, heatmaps, map clusters, choropleth maps and time-series heatmaps etc.
Alan Radford is a Professor in Veterinary Health Informatics Infection Biology & Microbiomes and is currently involved in teh SAVSNET, the Small Animal Veterinary Surveillance Network. During the 2023 MOOD Summer School he gave a presentation on Mining Electronic Health Records (EHRs) for improved disease surveillance.
Tom Hengl is the co-founder of OpenGeoHub Foundation, the Netherlands, and leader of the Work Package “Dissemination, project sustainability, and impact assessment” of the MOOD project. As a PhD candidate and research within OpenGeoHub Foundation, Carmelo focuses on data science projects such as GeoHarmonizer and the MOOD H2020 project. In this lecture of the 2023 MOOD Summer School, Tom and Carmelo showed how to do space-time machine learning using ensemble of machine learning methods. He used an example of the SAVSNET (Small Animal Veterinary Surveillance Network) dataset containing over seven million spatial point records, among which 0.16% with tick attachment. He and his team overlayed these points with over seventy covariates to produce space-time monthly and long term predictions for the period between 2014 and 2021.
Laura Espinosa is an Epidemic Intelligence Expert at the European Centre for Disease Prevention and Control (ECDC). In October 2020, ECDC developed an R-based open-source tool, epitweetr, for early detection of public health threats using Twitter data. In this session, attendees learned the process behind building such open-source R package for real-time monitoring of Twitter, understood the main functionalities of epitweetr, learned how to modify existing R packages locally and how to apply epitweetr functions to other case studies.
The MOOD Summer School was a three-day, full-immersion training on June 20th, 21st and 22nd, 2022 in Montpellier (France), where expert lecturers promoted analytical software and computing techniques, tools and datasets around Epidemic Intelligence and epidemiological analysis.

All the lectures are hosted on the Leibniz Information Centre for Science and Technology and University Library (TIB AV-Portal), which provides ad-free videos on science, research, industry and business with literature and information. 

In this video tutorial, Timothee Dub and Henna Mäkelä (Finnish Institute for Health and Welfare, Finland ) discussed the basics of infectious disease surveillance (event-based and indicator-based surveillance, active versus passive surveillance), as well as the advantages and limitations of each type of systems, followed by the example of how surveillance activities for TBE are conducted in Finland. By the end of this lecture, participants should be aware of the limitations and quality issues that can occur when using surveillance data for comparison and/or modelling.

In this session, Facundo Muñoz (Cirad, France) describex tools and workflows to cumulatively improve the reproducibility of analyses performed in R. R is a mature, world-class, open-source statistical computing and data-analysis platform with a huge community of users from all areas of science and industry. Yet, most researchers rely only on its most basic scripting features, missing the opportunity to unleash its full potential, in particular concerning reproducible-research workflows. Specifically, we discuss encoding and platform-specific packages, the advantages of organising code into functions, using project-directories and relative paths, reproducible reports with RMarkdown, controlling package versions with Renv, organising code into a pipeline with targets, keeping track of changes from various collaborators with git, reproducibly publishing results with Continuous Integration in Git(Hu|La)b pages, reproducing the complete environment with docker, and controlling versions of the complete software stack with GNU Guix.

This lecture, Francesca Dagostin (Fondazione Edmund Mach, Italy) gave an overview of how to extract relevant information from published literature, with a special focus on metadata related to covariates affecting disease emergence. Since data retrieved from literature are often complex and tricky to explore, the practical session showed the participants how to organize them into relational tables in order to build customizable and ready-to-share dashboards, which allow to efficiently visualize and summarize the information collected.

In this session, Timothee Dub (Finnish Institute for Health and Welfare, Finland) & Tom Hengl (OpenGeoHub, Netherlands) discussed the basics of Time Series Analysis, including with panel data. We looked into how to take into account seasonality, how to identify a trend and how to investigate the relationship between two-time series, with a focus on practical tips and R packages. By the end of this lecture, participants are able to analyze surveillance data, identify seasonality and investigate potential trends.

In this tutorial, Mathieu Roche (Cirad, France) Nejat Arinik (INRAE, France) and Mehtab Alam Syed (Cirad, France) first presented an overview of NLP (Natural Language Processing) approaches in order to mine media data for EBS systems. The second part focus on textual classification issues based on data science approaches. Finally, original representations of results are presented for highlighting new knowledge for EBS systems.

ProMED is a longstanding informal disease surveillance network. It has a worldwide network of clinicians, who send in reports of any unusual health events in plants, animals, or humans. These reports are then vetted by subject matter experts at ProMED before being shared with ProMED’s subscribers. ProMED emails usually contain a wealth of quantitative information about outbreak events. However, this information has so far not been utilised in real-time outbreak analysis. Using the West African Ebola epidemic as a case study, Dr Sangeeta Bhatia (Imperial College London, UK) demonstrated the challenges of using data extracted from ProMED for real-time analysis, with the use of a cleaned data set for the same epidemic that was collated by the World Health Organization as a benchmark to understand what can be inferred in real-time using digital disease surveillance data. Data and code are available at https://www.nature.com/articles/s41746-021-00442-3

In this block lead by Tom Hengl and Leandro Parente (OpenGeoHub) participants learn how to use state-of-the-art Machine Learning algorithms in R (mlr, mlr3) for the purpose of building models and producing spatial and spatiotemporal predictions. We used some of the disease datasets and covariate layers (MOOD study area) mentioned in the previous sections, then show step-by-step how to run spatial spatiotemporal overlays, optimize models, run model diagnostics, produce and visualize predictions (as maps or animations). The block is based on the R bookdown: https://opengeohub.github.io/spatial-prediction-eml/