< Back to previous page
Integrated computer modelling of cardiorespiratory fitness for personalised risk profiling and heart failure prevention (iCAREFIT)
Clinical exercise tests could improve the personalized risk profiling and management of cardiovascular disease. Yet, current practice only considers a limited selection of cardiopulmonary exercise indexes in isolation. To utilize the full value of clinical exercise testing data, we will apply advanced machine learning (ML) approaches on big data that has been collected/will be collected in patients at UZ Leuven (n=1800) and within the general population (FLEMENGHO cohort; n=650). We will develop integrative models that characterize personalized cardiorespiratory fitness profiling and its relation to subclinical stages of heart failure. These models will be further validated in an external cohort of about 3500 patients at varying cardiovascular risk provided by the Stanford Cardiovascular Institute (USA). We will combine innovative immunometabolic profiling measured by an advanced -omics technique with integrative ML approaches to elucidate key pathways of inflammatory and metabolic stress associated with the cardiopulmonary response to exercise and subclinical heart dysfunction. This pioneering project will lead to novel cardiopulmonary exercise-based algorithms that enable more precise evaluation of cardiac health and boost the development of personalized exercise programs.
Date:1 Oct 2021 → Today
Keywords:Clinical exercise testing, Machine Learning, Personalized risk profiling, Subclinical heart failure, Population study
Disciplines:Data mining, Cardiac and vascular medicine not elsewhere classified, Preventive medicine