Building blocks and knowledge

"We Are" personal data platform (VITO)

Together with other partners (Domus Medica, Vlaams Patiƫntenplatform, Zorgnet Icuro, Koning Boudewijnstichting), VITO is developing the "We are" data platform and ecosystem. This uses "privacy by design" as a starting point and focuses on the Caring Technology principles.

The personal data platform uses SOLID4, a project by Tim Berners-Lee. SOLID is based on the concept of individual data pods, which store personal data. The stored data is owned and under the full control of the citizen: he/she decides who has what access to his/her personal data. This model runs counter to the current practice where large, data-driven commercial players store personal data on a large scale and further generate revenue from it, and offers opportunities to create a "level playing field," where large and small parties can access personal data.

VITO is currently running a pilot implementation of the SOLID platform as part of the BIBOPP project, in collaboration with Domus Medica and LiCaLab. Here we are working with data from the online "Health Guide," a survey tool that can assess a patient's overall health status and generate preventive health recommendations. This data is stored in SOLID pods and serves as the basis for translating these recommendations into concrete actions and referrals to local facilities and services.

Work is also underway to expand the SOLID sandbox. This gives companies the opportunity to test out data links within SOLID, experiment with visualizations, test out authentication and consensus systems, ... and thus prepare a business case technically. Within these implementations, further work and testing can be done on the scalability of the new developments within the SAVE DATA project and enable innovations with concrete practical applications.

PTRA (imec)

PTRA is analytics software to provide temporal clustering of (long-term, sparse) longitudinal event data. An example would be recording the history of patient visits to a hospital physician or the history of medications. From this data, PTRA calculates statistically relevant pathways (trajectories) and a physician can quickly identify which different care pathways are possible for the patient.

PTRA is an unsupervised AI tool and is used to test existing hypotheses and, more importantly, to generate new ones. Once a domain expert analyzes the different paths, they can notice unexpected paths and thus discover that for example administering a certain drug for diabetes increases the risk of depression.

Once the pathways are calculated, they can help predict the pathway. Seeing which path a patient is on also predicts statistically relevant future elements. This can then form the basis for adjusting behavior.

PTRA is specifically designed to be scalable and calculate paths quickly and accurately on large data sets. For example, it takes 2 hours on 1 server to calculate paths on data from 273,000 patients and 6 million patient visits.