Coronary artery disease (CAD) is a major burden for patients and health care systems worldwide. The most common cause of CAD is atherosclerosis, an inflammatory disease gradually obstructing arteries, with life-threatening effects in the coronary circulation. Often, the circulation adapts through collateral artery formation, leading to significantly improved long-term post-ischemic outcome. Hence, timely determination of the collateral profile presents a pivotal factor in the Personalized Medicine of CAD. However, the coronary collateral circulation (CCC) development is not well predicted by traditional CAD risk factors. Moreover, manifold inconsistencies are still apparent in CCC research, mainly associated with the difficulty of quantifying CCC accurately and reproducibly.
The overarching objective of PROGRESS is to develop a tool for more accurate, reproducible and automated prediction of patients’ potential to develop CCC, which could be used for a more efficient CAD patient management.
Our hypothesis is that patients’ potential to develop CCC is, in part, determined by genetics. Thus, uncovering the genetic risk variants holds the potential of predicting CCC formation. To overcome previous difficulties of CCC research, we harness Artificial Intelligence (AI)-based angiogram image and genetics analyses aiming to improve risk stratification and management of CAD patients, based on their CCC formation profile, followed by timely application of therapeutic approaches in order to stimulate CCC formation and thus improve survival rates of patients after diagnosis. We have collected well-powered CAD cohorts with genetic and imaging data. AI-based image analysis will aid in phenotyping CCC and also to generate post-hoc surrogate functional parameters (validated against a cohort of invasively phenotyped patients) in an unbiased fashion. This provides the basis for a genome-wide association study (GWAS) on CCC performed in large detection and validation cohorts.