Health Sense is a project to create data conversion tools. During the project, we will create tools that will make it easier and faster to release pseudonymized, blurred, and sometimes aggregated data that can be considered open data. This means that individuals are not identifiable and do not have to go through a long chain of coordination to obtain data.
The aim is to improve the process of preparing anonymised and pseudonymous data and thus their availability in order to foster the development of new products, services and solutions in the private sector and to support innovative public sector approaches to health management by linking them to R&D knowledge. To this end, a set of tools will be created that can be set up and also set up for the data itself, which will enable the desired data to be issued to the applicant in the agreed form as soon as possible and with low labor costs.
Use of health data
In the course of the project, we deal with the data in the Health information system, because there are the most people in the world who are interested in using health data, and it takes the most time for our specialists to release this data. It is possible to process data from any other field with the created tools. In the future, we also want to reach our other two data groups - data on social care and employment data. The tools you create will be free to install and use for anyone who wants to.
- Social Ministry
- Health and Welfare Information Systems Center
- University of Tartu
- Tallinn University of Technology
- Western Norway University of Applied Sciences
- Helse West ICT (Norway)
In order to achieve the results of the project, the following works will be carried out:
Pseudonymization tool – a tool that replaces data presented as a closed list (personal identification code, nationality, religion, medicine, diagnosis, document number, etc.) with a code that is different for the same value of the data element. The codes are taken from the HSM and are not repeatable outside the system. The pseudonym also allows you to aggregate pseudonymous data from different databases and data owners in a pseudonymous form.
The pseudonym's solution consists of two parts of the complete solution with different financing and purchased separately:
- The pseudonym engine, ie the procurement of the development of service-based basic functionality, will be financed within the framework of the Structural Funds project no. 2014-2020.12.03.20-0777.
- The procurement for the development of the pseudonym's administrative interface is funded by Norway Grants.
- Data obfuscator – allows specific data to be made more general: the date can be used to make a period, year or month number, the address can be left in the settlement, county or country, the hierarchical classification can be moved up one level by level, etc. The work is carried out by the project partner University of Tartu.
- Text Organizer – searches the text for meaningful information (medications, diagnoses, names, addresses, phone numbers, social security numbers, dates, etc.) and unpacks them into data fields.
- The purpose of the deserialiser and serializer is to structure the document-based data entity of the Health Information System in the form of a relational database as much as possible, which enables later data to be processed more easily and faster according to the required data query data counters.
- The terminology and data models required for the project will be prepared by the project partner Tallinn University of Technology.
- The data warehouse and data analysis environment is created by the Health and Welfare Information Systems Center.
One of the aims of the project is to involve small and medium-sized enterprises, as well as start-ups, in the use of project results and in directing project results.
Why does this project have an English name? This is because the project is being funded by international funding. The project is funded by the NORWAY GRANTS PROGRAM “GREEN ICT” support program launched by the Norwegian Financial Mechanism. Norwegian organizations are participating in the project as consultants, sharing best practices in the use of data processing tools and the implementation of data-driven projects.
However, every good name also has a meaning. We formed this name as a paraphrase from the English term "life sense". Although our chosen phrase "Health Sense" does not directly mean this, we do understand it as "the idea of health", which is the deeper meaning of our project - to make health data more widely available and meaningful in analyzing and shaping human health behavior. All in order to prolong the healthy years and lives of our people.