Projects

This multidisciplinary study aims to decrease cardiovascular mortality in Estonia by increasing treatment adherence and empowering patients to create a supportive self-management environment for monitoring their health and actively participating in the treatment process. Analysing 1) the LDL-cholesterol values of North Estonia Medical Centre (NEMC) patients to find underdiagnosed and undertreated patients and 2) treatment adherence to lipid-lowering drugs (LLD). Identifying patient groups who need additional support. During the pilot project, a novel application will be developed, together with personal support, used to increase LLD adherence. The novelty of the tool – combining the data used in Estonia from the Nationwide Health Information System, ePrescription, and NEMC electronic medical record with the data collected by the patient and enabling two-way communication between the patient and medical staff. In the last stage of the study, an impact assessment of the tool is planned.

The challenge in modern industry is to find the best ways for human-robot interaction in workplaces, enabling robots to realize optimal solutions by combining AI and human capabilities. The project's goal is to contribute to the automation of company production processes, focusing on the social and psychological aspects of human-robot collaboration to ensure that human workers in the industry feel safe and satisfied. Research directions include: - creating a collaborative robotics experimental lab - designing robotized workplaces - modelling of human-robot interaction, assessments and analysis of influencing factors and risks. Expected results are methodologies and validated human-robot interaction models, skills for their implementation, impact factors and risk assessments, a developed laboratory with hardware, software and expertise; providing user-centred design solutions services. All of this leads to safer human-robot interactions, increasing user trust in robotic systems.

The overall goal of the project is to increase the number of healthy life years of the population. Currently, Estonia has recorded one of the lowest number of healthy life years at birth in the EU. To achieve this goal, three closely related areas of digital health are researched, developed and piloted. We use the standardized data exchange environment and digital data of the Estonian health information system (EHIS) to develop applications that increase the use of data collected by the person for health promotion, prevention and control of chronic conditions. Second, we focus on sensors and digital applications supported by artificial intelligence (AI) to allow a person to collect both biosignals and textual data in machine-readable form. With this, we speed up the detection of health risks and reduce the healthcare workload. Thirdly, we develop various AI methods by combining the data in EHIS and the Health Insurance Fund's database, as well as the data collected by the person.

TThe EuroTeQ 2030 is the next stage in the European Universities Alliance to deepen, expand and intensify the existing cooperation. Eight partners propose an unprecedented approach to collaborative education that not only brings together various countries but also a broad coalition of stakeholders in industry, society, and both academic and non-academic education. With our partnership, we will enhance today’s engineering study programmes with new core competencies, transversal skills, design methodologies, and structured links to relevant stakeholders. New ideas will occur from merging different perspectives, and new groups of learners will enrich the diversity in the classroom, which leads to innovation. Participating in EuroTeQ initiatives shall train learners to find answers to societal challenges, human needs, and real-world questions in a collaborative and responsible approach. We strongly believe that this European network will foster and strengthen European values by enabling young citizens to meet their peers and inviting the entire university family to make connections across Europe

Project objective: Develop a solution for automatic processing of medical texts, identification and structuring of clinical terms using SNOMED CT codes and FHIR standard. Work plan: 1. Clinical term identification - Preprocessing of Estonian medical texts - Application of machine learning/language models for term identification from text - Structuring of identified terms for further processing 2. Standardization and coding - Linking identified terms with SNOMED CT codes - Semantic matching of data with standardized ontologies - Converting results to FHIR format Demo solution and expected outputs: - Practical demonstration solution for complete workflow - Working system for automatic identification of clinical terms from Estonian texts - Structured output of terms linked with SNOMED CT codes - Standard data presentation in FHIR format for further use Keywords: medical texts, SNOMED CT, FHIR, language processing, clinical terms, automatic annotation, structured data