Deep learning analysis of electrocardiography (ECGs) detects Cardiovascular–Kidney–Metabolic syndrome burden in people with diabetes: a report from the Silesia Diabetes-Heart Project
Authors' conclusion
Deep learning applied to scanned ECG image data predicts CKM syndrome in individuals with diabetes with reasonable accuracy. This approach holds promise as a low-cost, scalable risk stratification tool and which could augment clinical decision-making in settings particularly with limited access to advanced diagnostics.
Study context
- Population
- Adults with T1D or T2D in the prospective Silesia Diabetes-Heart Project; Cardiovascular-kidney-metabolic (CKM) syndrome defined as chronic kidney disease (CKD) (estimated glomerular filtration rate (eGFR) < 60 mL/min/1.73 m² and/or urine albumin to creatinine ratio (UACR) ≥ 30 mg/g) or established CVD492 (17.7%) with CKM
- Participants
- 2,779 adults
- Outcome
- Detection of CKM syndrome from scanned limb and augmented limb lead ECG images (AUROC)
Methodological detailsdeep learning, ResNet-50-based convolutional neural network (CNN), bootstrap CIs
- Deep learning
- ResNet-50-based CNN
- Bootstrap CIs
Performance
As reported in the abstract
CKM syndrome detection
| Test or model | AUC | F1-score | Accuracy |
|---|---|---|---|
| Dual-channel ResNet-50 with soft voting ensemble | 0.8199 (95% CI 0.7549-0.8795) | 0.7213 (95% CI 0.6404-0.7957) | 0.7385 |
Dual-channel ResNet-50 with soft voting ensemble
AUC0.8199 (95% CI 0.7549-0.8795)
F1-score0.7213 (95% CI 0.6404-0.7957)
Accuracy0.7385
Original publication
Deep learning analysis of ECGs detects Cardiovascular–Kidney–Metabolic syndrome burden in people with diabetes: a report from the Silesia Diabetes-Heart Project. Cardiovasc Diabetol. Published 29 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →