Is (AI-guided) coronary CT angiography ready for prime time in diabetes care and research?
Year: 2026
Type: article
Abstract: Due to its increasing prevalence, the burden of diabetes-attributable cardiovascular disease is projected to increase substantially. At the same time, there is a growing need to better identify patients at the highest cardiovascular risk and to optimize the use of increasingly available—but costly—weight-, glucose-, and lipid-lowering therapies. We postulate that coronary computed tomography angiography (CCTA), potentially enhanced by novel artificial intelligence (AI)-based image analysis, could serve as a valuable tool for diabetologists to more accurately assess atherosclerotic cardiovascular risk. With ongoing reductions in cost and radiation exposure, CCTA has become a more feasible modality to quantify coronary artery disease burden, particularly in patients with diabetes, who represent one of the highest-risk populations. AI-guided analysis may further enhance scalability by reducing radiologist workload and improving reproducibility. In this perspective, we discuss both the promise and the current limitations of this approach, including questions surrounding whether to use intravenous contrast, and the management of incidental findings or clinically significant stenoses. We also explore the potential role of CCTA-derived endpoints in clinical trials for anti-atherosclerotic therapies, which could complement or partially replace traditional major adverse cardiovascular event outcomes that increasingly require large sample sizes due to declining event rates. A trial design combining non-inferiority on hard endpoints with superiority on CCTA measures may reduce costs while accelerating evidence generation. Ultimately, integrating AI-guided CCTA into clinical care and research may enable more precise and scalable cardiovascular risk stratification in diabetes care.
Source: Cardiovascular Diabetology
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $4,290
OpenAlex ID: W7222821832
FWCI:
Cites:
Cited by:
Related to: