Anagrafe della ricerca

Cardiovascular disease is the leading cause of death and disability, with prevalent cases doubling in the past decades and the number of deaths steadily increasing. Identification of patients at high risk of cardiovascular events for intensive management of risk factors and stratified pharmacotherapy is key to addressing this societal burden, which would also lead to a reduction in unnecessary procedures and examinations. However, identifying patients at risk of cardiovascular events is highly challenging: atherosclerotic plaques may cause acute myocardial infarction, but can also heal without causing an event. In addition, current risk stratification based on imaging and known biomarkers is suboptimal due to the multifactorial nature of the disease. The objective of this proposal is to develop a multicriteria decision model for the non-invasive assessment of vulnerable atherosclerotic patients and to evaluate its ability to predict the occurrence of an adverse event in intermediate-to-high risk patients with suspected or known coronary artery disease. The planned workflow combines plaque imaging with biomechanical assessment to derive the most accurate risk stratification model. Coronary computed tomography angiography (CCTA) will be used to assess high-risk plaque features and extract current clinical plaque features (e.g., thin fibrous plaque, positive remodelling index, plaque burden, low-attenuation plaque, and napkin-ring sign), as well as to build computational models for structural and fluid dynamics analyses. Optical coherence tomography (OCT) images will be used for consistency check of the predicted results. Plaque features, biomechanical indices, and the patient’s medical history will be integrated to generate machine learning models for the presence of CCTA-defined high-risk plaques. Advanced classification techniques, including Support Vector Machines, Discriminant Analysis and Artificial Neural Networks, will be deployed. The developed tool will be validated in an independent patient cohort to assess the robustness and reliability of the proposed solution. Integrated predictive tools developed in COMPUTES may promote personalised approaches to ischemic heart disease in both its early and advanced stages. Specifically, in primary prevention settings COMPUTES will help the physician to better identify patients who will benefit the most from preventive treatments. In secondary prevention settings, identification of patients with a worse prognosis may prompt the clinician to more intensive surveillance. Overall, this may lead to a further reduction in cardiovascular events and hospitalization, including sequelae and late complications like heart failure, which in turn represents an important cost for the National Health Care System.

• POLITECNICO DI MILANO - Coordinatore
• POLITECNICO DI TORINO - AMMINISTRAZIONE CENTRALE
• Università degli Studi di Torino