Fully automated epicardial adipose tissue volume quantification with deep learning and relationship with CAC score and micro/macrovascular complications in people living with type 2 diabetes: the multicenter EPIDIAB study
Authors' conclusion
Fully-automated EAT volume quantification could provide useful information about the risk of both renal and macrovascular complications in T2D patients.
Study context
- Population
- Patients with T2D screened for diabetic retinopathy (DR) and deeply phenotyped for MVC (AngioSafe T2D, n = 7200) who had undergone cardiac CT for CAC scoring; median age 61, 57% men, median T2D duration 11 years, mean HbA1c 7.8 ± 1.4%cardiac CT subset
- Participants
- 1,253 patients
- Comparison
- Epicardial adipose tissue (EAT) volume by presence vs absence of micro/macrovascular complications and by CAC score
- Primary endpoint
- Relationship between EAT volume and micro and macrovascular complications of T2D
Methodological detailsmulticentre, deep learning segmentation pipeline
- Multicentre
- Deep learning segmentation pipeline
Primary result
As reported in the abstract
EAT volume
- EAT volume was neither associated with DR, nor with peripheral neuropathy
- CKD vs No CKD: P = 0.008
- CAD vs No CAD: P = 0.0004
- PAD vs No PAD: P = 0.0005
- CAC > 100 AU vs CAC < 100 AU: P < 0.0001
Further findings
EAT and CV risk factors
- EAT significantly associated with all traditional CV risk factors
Subgroup with high EAT volume and null CAC score
- More likely young women with high BMI, lower T2D duration, lower prevalence of microvascular complications and higher inflammatory profile
Original publication
Fully automated epicardial adipose tissue volume quantification with deep learning and relationship with CAC score and micro/macrovascular complications in people living with type 2 diabetes: the multicenter EPIDIAB study. Cardiovasc Diabetol. Published 3 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →