Resources and Data

From Epidemium
Jump to: navigation, search

Epidemium relies on different resources to achieve it's goal to fight cancer through Big Data analysis

A Community


The community that Epidemium created is what makes its true strength. It is a community that is active and keeps growing, built on a community of competent individuals, experts, partners and institutions, driven by their willingness to fight cancer and conscious of the skills and knowledge they can bring.

After the first edition of the program, Epidemium is a community of more than 700 members with heterogeneous skills and profiles (data scientists, doctors, patients, researchers, sociologists, graphic designers, etc.). It is the commitment of these individuals, each with different reasons but united in their willingness to advance research, taking part in their free time on the program, which underlined both the feasibility and the legitimacy of such a initiative.

Joining Epidemium means being part of a dynamic and varied community of people from all around the world, entering an ecosystem of experts and partners, but also having access technical tools that we made available.

The Datasets

Data overview

As part of Epidemium program and of the Challenge4Cancer Challenges, we collected and prepared data from four open databases. These are from the WHO (World Health Organization), the Worldbank, and the ILO (International Labor Organization) and the FAO (Food and Agriculture Organization of the United Nations).
The granularity of the data is identical for each of these databases. They are broken down by country and year.

  • WHO: health data. We have developed two datasets, a cancer incidence dataset by type of cancer; a cancer mortality dataset by type of cancer.
  • Worldbank: includes a wide range of socio-economic indicators (e.g.: a country's GDP or the level of education of individuals).
  • ILO: includes indicators specific to the professional world (e.g.: the unemployment rate for a given age group).
  • FAO: includes indicators related to food and agriculture (e.g.: pesticide use or the amount of meat consumed per inhabitant per year).

Access to data

You will find the directory of the data available here. It contains three files:

  • An epidemiology_dataset file for epidemiological data that includes three sub-folders (one per database collected by Epidemium: WorldBank, Faostat, Ilostat).
  • An incidence_dataset file that includes cancer incidence data by type of cancer. This dataset is made up of data from the WHO.
  • A mortality_dataset file that includes mortality data by type of cancer. This dataset is made up of data from the WHO.


The platform

The Epidemium platform registers all the Challenge4Cancer participants and all the projects. It is designed in order to be a collaborative tool, to associate participants with one another and to facilitate the contribution to the projects.

You can discover on the platform:

1.The profile of the other participants and:

  • their description;
  • their skills;
  • the project(s) to which they participate;
  • the project(s) they follow;
  • the tasks on which they are working and their activities since their registration;

2.The projects and:

  • the associated and sought-after skills;
  • the corresponding team and the function of the members;
  • the descriptions and the research project;
  • the defined milestones;
  • the tasks in progress and completed;
  • the obtained results.

The platform allows you to easily get in touch with other participants, get into a project and easily take on a task.

The included tools

To help you develop your project, document it and work as a team, several tools have been directly integrated into the platform:

Rocketchat.png GitLab.png OwnCloud.png Wiki.png
Rocketchat GitLab OwnCloud Wiki
an open source online discussion platform (private and public channels, file sharing ...), so you can chat and work with all members of your team at any time, wherever you are.
It is structured in several channels (General, Data support, Medical support, Platform support, Legal support): chose the right one to comment or ask your question and do not hesitate to ping the people in charge (see the Channel Information) !
a software development tool, which allows you to manage repositories, track bugs and tasks, propose merge, etc.

to share, store files and images between members of your teams and work anywhere.

following the creation of your project on the Epidemium platform, a wiki page is automatically created on the Epidemium Wiki. All you have to do is to document your project (team, hypotheses, methods, tools used, results ...) so that it can be seen and read by all, and especially evaluated by the jury members at the end of the Challenge.


A data analysis and data visualization studio equipped with a large range of click-and-go tools designed to prove intuitions and construct hypothesis around datasets.

To access the service, you can start by using the free version to test your assumptions. To access the full service, please contact the Epidemium team at

Before you start, here is some practical information:

Tools and platform tutorials