Deliverable D5.1 Multilayer data acquisition and management services addresses the specific multiscale and multivariable data management architecture, on top of which the BD2Decide big data and prognostic modelling techniques will be implemented, with the ultimate aim to improve the decision making process in the treatment of Head and Neck cancer.

The involved datasets are presented in four categories, depending on the layer of the BD2Decide platform environment that the specific data is produced: i) collection datasets, which are collected from the information systems of the clinical centres about the electronic health records of the patients or from Internet sources, which provide population-based data, ii) analysis datasets, which are produced within the BD2Decide environment, as a result of the processing algorithms built (or deployed) within the project scope, iii) visualisation datasets, which complement the previous categories in order to enhance the visualisation capabilities of the BD2Decide environment, and iv) access control datasets, which refer to the identity management processes of the BD2decide platform environment.

Furthermore, the deliverable presents the BD2Decide data warehouse service architecture, which aggregates the required data repositories for hosting the type of data identified in the above mentioned categories.

The document is structured as follows:

  • Section 2 makes an overview of the data requirements in the BD2Decide project by analysing the findings of the Deliverable D2.1 (also published on the BD2Decide web site). It, then, presents the categories of the required datasets in the project and the sources from which is data is retrieved.
  • Section 3 describes the architecture of the BD2Decide data warehouse. It presents the logical structure of the data environment and provides a realisation of the expected functionalities to be implemented in the project in order to execute the use cases, reported in D2.1.
  • Section 4 elaborates on the details of the repositories defined in the previous section the BD2Decide data warehouse architecture, by providing an initial scheme of the repositories and the candidate technologies and tools, through which these repositories will be developed in the project.
  • Finally, Section 5 concludes on the expected role of this document in the project work plan.
Share This Post: