With the emergence of new technologies that extend the capabilities of actual data collection methods, healthcare data are more and more amassed in the purpose of being later analyzed to serve the ultimate, well-known, goal of 4P medicine (Predictive, Preventive, Personalized, Participative). Given the sensitive nature of healthcare data, and in a matter of compliance with data protection and privacy regulations, there is a need to make data publishing more secure. This is one of the main goals of theEU H2020 QUALITOP research project, with particular regards to the issue of defining a big health data smart digital platform and the shared data lake. In this context, we design, implement and experimentally assess an innovative algorithmic framework calledAdvanced Privacy-PreservingBig Data Publishing in HierarchicalDOMains(AB-DOM). AB-DOM is based on state-of-the-art anonymization techniques mixed with agraph coloring algorithmand an integrateddata sampling methodto guarantee that sensitive data are highly secured.

In this paper, we introduce and experimentally assess an innovative big data analytics technique for mining and analyzing Quality-of-Life Indicators (QoL) over time among patients with lung cancer and treated with immunotherapy. In more details, given datasets of QoL indicators collected over time, at regular intervals, the F-TBDA technique (Frequency-based Temporal Big Data Analytics) computes temporal relative frequency tables over fixed-time intervals where data of subsequent observations (i.e., intermediate therapy) are compared with the baseline observation (i.e., starting therapy). Then, on the basis of these relative frequency tables, both simple and complex frequency-based big data analytics tools are developed, in order to unveil hidden patterns over cancer patient therapies. Experimental results on top of a real-life dataset nicely complete the theoretical contributions we provide in our research.