Using big data to put a cardiovascular digital twin into the hands of people
MyDigiTwin is a scientific initiative to develop a platform in which individuals can, for the first time, directly compare their personal health data with big-data reference data available from multiple cohorts, including ±200,000 national and ±500,000 international volunteers with long-term follow-up. This big-data will be queried via FAIR data access points and “on the fly” comparison by Artificial Intelligence (AI)-based algorithms will return results that will be used to render a “Digital Twin” (representative) of each individual user. This “Digital Twin” informs the user on the actual observed cardiovascular events of the identified “most alike” volunteers from big-data reference sets. The “Digital Twin” can also be modified for input variables to allow the user to simulate the effect of changes (e.g. in Lifestyle) and assess benefits or harm. The MyDigiTwin platform will also make AI tools available to the users to “check” whether their personal data, including possible pharmacotherapy, is in line with the official recommendations from professional cardiovascular practice guidelines. Dedicated research will be directed to obtain fundamental insights into the readiness of society to optimally align the foreseen platform and cockpit (user interface) with the needs and expectations of users. A co-creation strategy will be used to develop MyDigiTwin and its efficacy, in order to empower patients and enable shared decision-making. This will be tested in a real-life setting by our clinicians. MyDigiTwin contributes to self-management and improved interaction with health care professionals through knowledge-driven empowerment, technical solutions to enhance communication, and reports to simulate shared decision making.
Improving the vantage6 federated learning ecosystem
Coronary artery disease: risk estimations and interventions for prevention and Early detection
Targeting key risk factors for cardiovascular disease in at-risk individuals using a personalized and adaptive approach
Self tracking for prevention and diagnosis of heart disease
Fusible evolutionary deep neural network mixture learning from distributed data for robust medical...
Smart, secure container networks for trusted big data sharing
Detecting human sleep from wearable accelerometer data without the aid of sleep diaries
The CDF2Medmij-Mapping-tool facilitates the seamless transformation of cohort data into MedMij-compliant FHIR formats, enabling the harmonization of diverse datasets within a federated learning infrastructure.
This tool converts Lifelines cohort study data from CSV to CDF/JSON, a format used in the MyDigiTwin project. Lifelines tracks health data over time, but variables are often scattered across files, making analysis difficult. CDF organizes data per participant, enabling FHIR/MedMij-compliant analysis