AI-Guided Cardiac Computer Tomography in Type 1 Diabetes Patients with Low Coronary Artery Calcium Score
Authors' conclusion
AI-QCT may reveal subclinical atherosclerotic burden and high-risk features that remain undetected by traditional risk models or CAC. These findings challenge the assumption that a low CAC score equates to a low cardiovascular risk in T1D.
Study context
- Population
- T1D patients aged ≥30 years, disease duration ≥10 years, no manifest or symptomatic atherosclerotic cardiovascular disease (ASCVD); AI-QCT in coronary artery calcium (CAC) 0 with ≥1 carotid plaque or CAC 1–9952 underwent AI-QCT
- Participants
- 167 patients
- Exposure
- AI-QCT vs CAC and STENO1 risk categories
- Outcome
- Burden of clinically significant atherosclerosis in T1D patients with CAC <100 using AI-QCT
Main finding
As reported in the abstract
Atherosclerosis on AI-QCT (n = 52)
No evidence of coronary artery disease
11
21%
Significant coronary stenosis
17%
At least one high-risk plaque
30
73%
Observational data: associations, not effects.
Further findings
CAC distribution (all participants)
- CAC = 0
- 93 (56%)
- CAC 1-99
- 46 (28%)
- CAC 100-299
- 8 (5%)
- CAC ≥300
- 20 (12%)
Reclassification and agreement of AI-QCT vs CAC and STENO1 risk categories
- Reclassified by AI-QCT vs CAC-based risk categories
- 58%
- Reclassified by AI-QCT vs STENO1 risk categories
- 21%
- Agreement AI-QCT vs CAC (fair), κ
- 0.25
- Agreement AI-QCT vs STENO1 (slight), κ
- 0.02
Original publication
AI-Guided Cardiac Computer Tomography in Type 1 Diabetes Patients with Low Coronary Artery Calcium Score. Diabetes Technol Ther. Published 31 July 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →