The project is in line with the RIS3 strategy, focusing on interdisciplinary medical innovation and the development of high added-value products for preventive healthcare, thus addressing RIS3 investment priority 1. It aims to create a pro-active, patient-centred, digital platform-based cloud-based module on ‘Prevention and early diagnosis of cardiometabolic diseases’. This is in line with the RIS3 priorities in biomedical, medical technology and pharmaceuticals. The initiative supports the objectives of RIS3 in the development of new products and technologies (#2), as well as in the development of the Latvian knowledge base and human resources in the fields of biomedical and medical technologies (#6). In addition, the project is in line with the Ministry of Health's Action Plan on Obesity, focusing on proactive and preventive healthcare. NACE code: 72.19 - Other research and experimental development on natural sciences and engineering. The proposed project activities include industrial and experimental research. Objective of the project: develop a pro-active, patient-adapted, digital platform-based cloud-based module on ‘Prevention and early diagnosis of cardiometabolic diseases’. The module focuses on early detection of diseases, personalised health interventions and reducing healthcare costs. FORD classification: 1.2. Natural Sciences – Computer Science and Informatics 3.5. Medical and Health Sciences – Other Medical Sciences Project Scientific Manager: The project is led by Dr. Dmitry Bļizņuks, Associate Professor of Riga Technical University with extensive experience in digital health innovation and project management. Dr. Bļizņuks is a leading expert in the management of interdisciplinary teams and the development of advanced health care solutions approved by international awards and patents. Partners involved in the project: 1. Riga Technical University (RTU): RTU provides calculation infrastructure and data science expertise in machine learning applications and PROM/PREM data analysis. 2. Pauls Stradins Clinical University Hospital (PSKUS): PSKUS provides clinical experience, patient data and knowledge in the field of healthcare, ensuring the practical application of the digital platform. 3. SIA Longenesis: A leading digital health technology company specializing in patient engagement and data management solutions will adapt its existing platform to achieve the project objectives and ensure compliance with GDPR requirements. Overview of the problem: Cardiometabolic diseases represent a significant public health burden, with obesity alone costing the EU billions of euros per year. Existing health systems lack integrated and personalised screening methods to prevent these diseases at national level. Resource scarcity and under-use of digital solutions make it difficult to proactively manage health. Research objectives: Establish a module based on a digital platform for the assessment of cardiometabolic risk factors, using data and clinical information provided by patients. Introduce a patient monitoring approach with personalised feedback and lifestyle recommendations based on PROM/PREM data. Identify different phenotypes of patients to adapt prevention strategies and improve clinical outcomes. Previous work: Within the framework of the National Research Programme (NRP) "Public Health", the team of Pauls Stradins Clinical University Hospital is carrying out a pilot project of the digital health education programme, within the framework of which more than 1000 participants have participated in face-to-face activities. Consortium members have also invested time in developing a web-based platform for cardiovascular risk assessment and personalised remote patient monitoring, including the integration of the SCORE2 risk assessment model. Methodology: The project builds on previous studies, integrating validated survey tools and machine learning models for data analysis. A GDPR-compliant digital platform will manage participants' data, provide personalised feedback and engage users through gamification and dynamic health recommendations. Machine learning will be used for phenotyping patients and improving prevention strategies. Operations WP1. Integration of survey tools, development and validation of personalised recommendations with focus groups: T1.1 Integration of health risk assessment questionnaires. T1.3 Focus groups and validation. T1.2 Development of personalised recommendations based on health risk assessment. WP2 Involvement of citizens through the digital platform. Providing life-style recommendations in a digital solution: T2.1 Digitalisation of health risk questionnaires and lifestyle recommendations T2.2. Involvement of citizens through the digital platform. Dynamic health monitoring of participants based on PREM/PROM data points. WP3 Data analysis and phenotyping of participants: T3.1 Expert system for sorting high-risk patients T3.2. Analysis of clusters. T3.3 Epidemiological analysis WP4 D
