July 9, 2026 — Elucid recently announced first patient enrollment in AI-Predict, a retrospective, international, multicenter study designed to establish a new lesion-centric paradigm for cardiovascular risk stratification. Enrollment is underway at three of more than 20 planned sites across the U.S., Europe and Asia: Emory University, the Medical University of South Carolina, and Centro Cardiologico Monzino, Milan, led by site principal investigators Carlo N. De Cecco, MD, PhD, Akos Varga-Szemes, MD, PhD, MBA, and Gianluca Pontone, MD, PhD, respectively.
AI-Predict will enroll approximately 1,000 subjects, including both patients who experienced a myocardial infarction (MI) within 36 months of a baseline CCTA and clinically matched, event-free controls, generating a dataset of individual coronary lesions. All scans will be analyzed by a central core lab, blinded to outcomes, using Elucid’s Plaque-IQ and FFR-CT1 software to measure key morphological, anatomical and physiological features.
“We joined AI-Predict early because it asks the question: among the many plaques in a patient, which features distinguish the one plaque that causes harm from the many that don’t? This study expects to extract that detail lesion by lesion, which is why we wanted to be part of AI-Predict,” said Dr. Pontone.
Lesion Identification
Heart disease remains the top cause of death globally.2 Despite massive investment in cardiovascular medicine3, the problem persists due in part to limitations of traditional diagnostic methodologies.4 Many heart attacks arise from plaques that progressed silently, in the moderate stenosis range, producing no symptoms before causing the problem.5 The AI-Predict study is designed to better identify and stratify those lesions in advance.
The AI-Predict study is led by a team of internationally recognized cardiovascular scientists and imaging specialists. Serving as principal investigator is Jagat Narula, MD, PhD, president of the World Heart Federation and one of the world's foremost authorities on cardiovascular imaging and plaque biology. Serving as co-principal investigator is Dr. De Cecco, professor of Radiology and Biomedical Informatics and director of the Cardiothoracic Imaging Division at Emory University School of Medicine, whose work has advanced the use of AI and quantitative imaging in cardiac CT. The study's Steering Committee is co-chaired by Amir Ahmadi, MD, clinical associate professor of medicine (cardiology) at the Icahn School of Medicine at Mount Sinai, and lead scientific advisor at Elucid, and Michael Hadley, MD, system director of Advanced Cardiac Imaging at Northwell Health, a leading expert in cardiac CT and its clinical applications.
“AI-Predict represents a fundamental shift in how we think about cardiovascular risk,” said Dr. Narula. “For too long, we have assessed risk at the population level while heart attacks happen at the lesion level. This study is designed to take a step towards closing that gap.”
Dr. Ahmadi added, “By comparing culprit lesions and non-culprit bystander lesions in the same MI patient, and stable lesions in matched controls, we will, for the first time, have a rigorous, large-scale framework for understanding risk at a lesion level. This could be key in guiding personalized CAD prevention.”
AI-Predict reflects Elucid’s work to move cardiovascular care towards CCTA 3.0, the company's vision for personalized, lesion-level care.
References
1. FFR-CT is under FDA review
2. World Health Organization (WHO), Cardiovascular diseases (CVDs). 2017 23, April 2020. Available at www.who.int/en/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
3. Ashraf, M. Cardiovascular R&D, M&A and Venture Funding in H2 2024. Dec 12, 2024 https://dealforma.com/cardiovascular-rd-ma-and-venture-funding-in-h2-2024/
4. Mueller, A. S., Leipsic, J, et. al. Limitations of Risk- and Symptom-Based Screening in Predicting First Myocardial Infarction. JACC: Advances, vol 4, number 12, part 2, 1 December 2025. www.jacc.org/doi/10.1016/j.jacadv.2025.102361
5. Virmani, R, et. al. Lessons From Sudden Coronary Death: A Comprehensive Morphological Classification Scheme for Atherosclerotic Lesions. Arteriosclerosis, Thrombosis, and Vascular Biology, vol. 20, no. 5, May 2000. Available from https://doi.org/10.1161/01.ATV.20.5.1262
June 12, 2026 
