Today, almost all human activities generate and/or demand to store and process massive, diverse and complex data, either in scientific, academic, enterprise and even leisure pursuits – a scenario that has being called the “big data era”. Health-related and human activities are in the core of those activities, as they both produce big data and can take advantage of the technological storm, improving the behavior of everyone whose decision is increasingly guided by the information extracted from all these big data. In a clinical environment, for example, the Electronic Health Records (EHR) is the anchor to develop information extraction strategies. In this proposal, we aim at integrating novel, scalable database support, image processing, graph-based analysis, and visual analytics methods to leverage large amounts of EHR and repositories of clinical data to gather valuable and significant information for decision-making. The size and complexity large-scale databases offer great challenges when they need to be processed in terms both of applying analysis techniques and to support the development of subsequent applications for practical tools. However, it also embodies a cornucopia of opportunities to create algorithms and methods able to display smart and relevant information related to either a particular city or institution, coping strategic government decisions with the demands and benefits of big data. In this project we will develop methods and algorithms that will ultimately be materialized in a modular platform to be made available to the area community.
Postdoctoral fellowships (May 2021) - More information News (in Portuguese) - Clipping - Agência FAPESP: "Artigos de pesquisadores do ICMC-USP são premiados em conferência internacional" Best Paper - 32º SBBD (Prêmio José Mauro Castilho): "Relational graph data management on the edge: Grouping vertices' neighborhood with Edge-k", SBC. Best Paper - First Dataset Showcase Workshop (DSW) - SBBD 2017: "MAMMOSET: An Enhanced Dataset of Mammograms", SBC.