Adverse cardiovascular events in coronary Plaques not undeRgoing pErcutaneous coronary intervention evaluateD with optIcal Coherence Tomography. The PREDICT-AI risk model.
Authors
Affiliations (22)
Affiliations (22)
- Azienda Ospedaliero-Universitaria Città della Salute e della Scienza di Torino, Turin, Italy [email protected] [email protected].
- Department of Advanced Biomedical Sciences, University of Naples Federico II, Naples, Italy.
- Dipartimento di Ingegneria Meccanica e Aerospaziale, Politecnico di Torino, Turin, Italy.
- Fondazione Policlinico Universitario A Gemelli IRCCS, Rome, Italy.
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- Department of Cardiology and Structural Heart Diseases, Medical University of Silesia, Katowice, Poland.
- Medical University of Silesia, Katowice, UK.
- Rivoli Hospital, Rivoli, Italy.
- Dipartimento Cardio-Toraco-Vascolare, IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
- UO Cardiologia, Azienda Ospedaliero-Universitaria di Ferrara Arcispedale Sant'Anna, Cona, Italy.
- Interventional Cardiology, Univ Piemonte Orientale, Alessandria, Italy.
- University Hospital Maggiore della Carità, Novara, Italy.
- Department of Cardiovascular, Respiratory, Nephrological and Geriatrical Sciences, University of Rome La Sapienza, Roma, Italy.
- University of Rome La Sapienza, Rome, Italy.
- Azienda Ospedaliero-Universitaria Città della Salute e della Scienza di Torino, Turin, Italy.
- AOU Careggi, Florence, Italy.
- Azienda Ospedaliera Papa Giovanni XXIII, Bergamo, Italy.
- Azienda Ospedaliera Brotzu, Cagliari, Italy.
- Interventional Cardiology, PO S Andrea di Vercelli, Vercelli, Italy.
- Azienda Ospedaliera Universitaria Integrata Verona, Verona, Italy.
- Faculty of Medicine and Surgery, University of Messina, Messina, Italy.
- Cardiology Department, Azienda Sanitaria Universitaria Giuliano Isontina Dipartimento ad Attività Integrata Cardiotoracovascolare, Trieste, Italy.
Abstract
Most acute coronary syndromes (ACS) originate from coronary plaques that are angiographically mild and not flow limiting. These lesions, often characterised by thin-cap fibroatheroma, large lipid cores and macrophage infiltration, are termed 'vulnerable plaques' and are associated with a heightened risk of future major adverse cardiovascular events (MACE). However, current imaging modalities lack robust predictive power, and treatment strategies for such plaques remain controversial. The PREDICT-AI study aims to develop and externally validate a machine learning (ML)-based risk score that integrates optical coherence tomography (OCT) plaque features and patient-level clinical data to predict the natural history of non-flow-limiting coronary lesions not treated with percutaneous coronary intervention (PCI). This is a multicentre, prospective, observational study enrolling 500 patients with recent ACS who undergo comprehensive three-vessel OCT imaging. Lesions not treated with PCI will be characterised using artificial intelligence (AI)-based plaque analysis (OctPlus software), including quantification of fibrous cap thickness, lipid arc, macrophage presence and other microstructural features. A three-step ML pipeline will be used to derive and validate a risk score predicting MACE at follow-up. Outcomes will be adjudicated blinded to OCT findings. The primary endpoint is MACE (composite of cardiovascular death, myocardial infarction, urgent revascularisation or target vessel revascularisation). Event prediction will be assessed at both the patient level and plaque level. The PREDICT-AI study will generate a clinically applicable, AI-driven risk stratification tool based on high-resolution intracoronary imaging. By identifying high-risk, non-obstructive coronary plaques, this model may enhance personalised management strategies and support the transition towards precision medicine in coronary artery disease.