Integrative personalized computer modeling for better cardiovascular health assessment
The cardiovascular (CV) area has tremendous potential for personalized medicine and is currently under fast development. Precise description of CV health and risk assessment are essential for optimal prevention and treatment strategies, but requires complex integration of many factors. Development of computer population-based models will ultimately support precision medicine. Therefore, the specific aims of this project are: (1) Applying machine learning algorithms to the available longitudinal highly standardized general population data to employ the complexity of clinical and behavioural variables, cardiac imaging sequences and pathophysiologically relevant circulating proteins and metabolites for construction of precision CV classifiers. These computer models will extract maximum information from individual clinical data, the most sensitive biosignatures and diagnostic imaging phenotypes for better CV risk prediction. (2) To determine the role of pathophysiologically relevant and organ specific circulating –omics markers (proteins and metabolites) to assess health of the CV system. (3) Applying (un-)supervised machine learning approach to create computer algorithms for fast, fully-automated and precise classification of cardiac maladaptation with particular focus on assessment of diastolic dysfunction. The precision computer models will help to create new strategies for risk stratification, prevention, detection and management of early stages of CV disease.