Status: Closed

Coordinator: IRCCS Fondazione Salvatore Maugeri, Pavia (IT)

Involved centres: Atene, Valencia

Clinical field: Diabete

Start date: 1 gennaio 2013

Fund: EU

Platform: i2b2

MOSAIC is a project funded by the European Commission aimed at providing an innovative approach in the diagnosis and follow-up of people with chronic diabetes, in order to improve the patient characterisation and the ability to assess the risk of developing complications related to Type 2 Diabetes Mellitus.
The University of Pavia, in collaboration with BIOMERIS, has used the i2b2 framework to collect and integrate heterogeneous data from the database of diabetic patients of Fondazione Salvatore Maugeri, administrative data from the local health authority and environmental data from regional databases.
When a user of the system selects the group of patients of interest, the query engine retrieves from i2b2 the necessary information, then the Data-Mining module performs the temporal analysis and returns the control to the interface for the visualisation of the results. MOSAIC is already available for use in clinical practice in order to obtain statistics on diabetes care clinics and calculate patient-friendly risk indices. MOSAIC’s data set includes geo-referenced clinical data that allows each subject to be geographically located.


  • Dagliati A, Sacchi L, Bucalo M, Segagni D, Zarkogianni K, Martinez Millana A, Cancela J, Sambo F, Fico G, Meneu Barreira M, T, Cerra C, Nikita K, Cobelli C, Chiovato L, Arredondo M, T, Bellazzi R, (2014) A data gathering framework to collect Type 2 diabetes patients data. In EEE-EMBS International Conference on Biomedical and Health Informatics (BHI), pp. 244-247. (link, pdf)
  • Bellazzi R, Dagliati A, Sacchi L, Segagni D. Big Data Technologies: New Opportunities for Diabetes Management. J Diabetes Sci Technol. 2015 Apr 24. pii: 1932296815583505. (link, pdf)
  • Segagni D, Sacchi L, Dagliati A, Tibollo V, Leporati P, De Cata P, Chiovato L, Bellazzi R. Improving Clinical Decisions on T2DM Patients Integrating Clinical, Administrative and Environmental Data. Stud Health Technol Inform. 2015;216:682-6. (link, pdf)
  • Martinez-Millana A, Fernandez-Llatas C, Sacchi L, Segagni D, Guillen S, Bellazzi R, Traver V.From data to the decision: A software architecture to integrate predictive modelling in clinical settings.Conf Proc IEEE Eng Med Biol Soc. 2015 Aug;2015:8161-4. (link, pdf)