Deep learning-based coronary calcium score derived from non-gated chest CT and major adverse cardiovascular events in patients with type 2 diabetes mellitus
Authors' conclusion
DL-CACS derived from non-gated chest CT is an independent predictor of MACEs and provides incremental value in risk stratification for patients with T2DM compared with the FRS.
Study context
- Population
- Patients with T2DM who underwent non-gated chest CT, followed up ≥2 years; median age 61 years, 1,257 males; Hospital A (training/internal validation) and Hospital B (external validation)
- Participants
- 2,241 patients
- Exposure
- Model 2 vs Model 1
- Outcome
- MACE
- Follow-up
- At least 2 years
Methodological detailsprognostic model development and validation, internal and external validation, Hospital A patients randomly assigned 3:2 to training and internal validation cohorts; external validation cohort from Hospital B
- Prognostic model development and validation
- Internal and external validation
- Hospital A patients randomly assigned 3:2 to training and internal validation cohorts; external validation cohort from Hospital B
Main finding
As reported in the abstract
C-index for MACE prediction, external validation cohort
Model 2
0.70
C-index · CI 0.63–0.77
Model 1
0.67
C-index · CI 0.61–0.74
P = 0.007
- DL-CACS independent predictor of MACE (multivariate Cox, training cohort), HR
- 1.07; p < 0.001
Observational data: associations, not effects.
Further findings
MACE incidence during follow-up
- MACE occurred
- 10.71% (240/2241)
DL-CACS in patients with vs without MACE
- Significantly higher DL-CACS in patients with MACE than without
- P < 0.001
Original publication
Deep learning-based coronary calcium score derived from non-gated chest CT and major adverse cardiovascular events in patients with type 2 diabetes mellitus. Cardiovasc Diabetol. Published 8 October 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →