Artificial Intelligence in Coronary Artery Disease: From Detection to Precision Management.
Authors
Affiliations (12)
Affiliations (12)
- Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, US.
- School of Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, US.
- Division of Cardiology, Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, Arkansas, US.
- Division of Cardiology, Department of Medicine, Medical College of Georgia at Augusta University, Augusta, Georgia, US.
- Division of Health Informatics, Department of Population Health Sciences, Weill Cornell Medicine, New York, New York, US.
- Department of Perioperative Cardiology and Cardiovascular Imaging, Centro Cardiologico Monzino IRCCS, Italy.
- Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy.
- Division of Cardiology, Lahey Hospital & Medical Center, Beth Israel Lahey Health, Burlington, Massachusetts, US.
- Division of Cardiology, Department of Medicine, John H. Stroger Hospital of Cook County, Chicago, Illinois, US.
- Cardiovascular Systems Imaging and Artificial Intelligence Lab, National Heart Research Institute Singapore, National Heart Centre Singapore.
- Department of Cardiology, National Heart Centre Singapore, Singapore.
- SingHealth Duke-National University of Singapore Cardiovascular Sciences Academic Clinical Programme, Duke-National University of Singapore Medical School, National University of Singapore, Singapore.
Abstract
Coronary artery disease (CAD) remains the leading cause of death worldwide, yet the landscape is rapidly evolving as artificial intelligence (AI) is increasingly applied to its detection, diagnosis, and management. This review surveys the expanding role of AI across the full spectrum of CAD care. In screening, deep-learning electrocardiography and electronic health record-based digital markers enable earlier identification of clinically significant disease. In noninvasive imaging, AI-driven coronary computed tomography angiography automates calcium scoring, derives fractional flow reserve without invasive wires, and quantifies high-risk plaque features that predict incident adverse events. Within the cardiac catheterization laboratory, angiography-derived physiologic assessment and AI-guided intravascular imaging segmentation support real-time procedural decision-making. Beyond diagnosis, machine-learning models integrating multimodality imaging data improve risk stratification over conventional clinical scores, while pharmacogenomic algorithms and wearable-based digital rehabilitation platforms enable patient-centric secondary prevention. Despite this progress, significant challenges persist, including limited evidence from randomized trials, algorithmic bias in underrepresented populations, regulatory uncertainty surrounding software-as-a-medical-device frameworks, and the risk of clinician de-skilling. AI has the potential to act as a collaborative tool that augments-rather than replaces-physician judgment. Future directions include foundation models, multiomics integration, agentic AI workflows, and equity-centered deployment strategies to ensure that AI-driven advances benefit all individuals with CAD.