Christoniki Maga-Nteve, Gorka Epelde, Mikel Hernandez, Nikos Tsolakis, Evdokimos Konstantinidis, Georgios Meditskos, Panagiotis Bamidis and Stefanos Vrochidis, “Standardized and extensible reference data model for clinical research in Living Labs”, 12th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH 2022)

Author(s): Christoniki Maga-Nteve, Gorka Epelde, Mikel Hernandez, Nikos Tsolakis, Evdokimos Konstantinidis, Georgios Meditskos, Panagiotis Bamidis and Stefanos Vrochidis

Tags:

Abstract: Over the last few years, Living Labs (LL) have emerged as resilient research and innovation infrastructures to facilitate and promote activities, which can deal with the complexity of health and wellbeing research. Such systems integrate multiple types of data, including personal info or generated by ICT tools and devices (i.e., wearable sensors). Healthcare data models have the ability to integrate such data and focus on relevant content that will follow a specific data representation template that can be extended based on the needs of each LL. In this study, we propose a reference metamodel based on existing schemas to improve the efficiency of the LL research by pursuing a labor-intensive workflow with a hierarchical structure that simplifies the transformation process and minimizes data variation. OmH library has been used as the basis of the metamodel along with other standards in healthcare to design a complete and straightforward data reference model for LL. The presented data model has been designed within the Vitalise (H2020-INFRAIA 2021-2024) project and visualizes representations of the collected data elements and their relations. The main purpose is to provide an extensible data model that: 1) harmonizes representation formats of the information exchanged that will be used from the LL, 2) empowers other LL to develop solutions that adhere to this common definition and 3) provides a shared, common schema. The designed model will precisely represent and handle data from different devices or platforms (i.e., heart rate, BMI) and efficiently describe the collected dataset to produce meaningful metadata.