Aortic & peripheral vascular disease
Determinants of ascending aortic morphology: cross-sectional deep learning-based analysis on 25 073 non-contrast-enhanced NAKO MRI studies
Authors' conclusion
This study demonstrates the potential of DL and causal analysis for understanding ascending aortic morphology. By disentangling observed correlations using causal analysis, this approach identifies possible causal determinants, such as age, BSA, hypertension, and alcohol consumption. These findings can inform targeted diagnostics and preventive strategies, supporting clinical decision-making for cardiovascular health.
Study context
- Population
- Participants of the German National Cohort (NAKO) with 3D NC-MRANC-MRAs analysed
- Participants
- 25,073 participants
- Exposure
- Relationships between mid-ascending aortic diameter (mid-AAoD) and demographic factors, hypertension, diabetes, alcohol, and tobacco consumption
- Outcome
- mid-AAoD by sex
Methodological detailsdeep learning-based analysis, 3D non-contrast-enhanced magnetic resonance angiography (NC-MRA), causal analysis (Peter-Clark algorithm)
- Deep learning-based analysis
- 3D non-contrast-enhanced magnetic resonance angiography (NC-MRA)
- Causal analysis (Peter-Clark algorithm)
Main finding
As reported in the abstract
Observational data: associations, not effects.
Further findings
mid-AAoD with daily alcohol consumption · highest mid-AAoD
mid-AAoD with smoking history exceeding 16.5 pack-years · highest mid-AAoD
| Outcome | Males | Females |
|---|---|---|
| Correlation of age with mid-AAoDPositively correlated | r²=0.20 | r²=0.16 |
| P | P < 0.001 | P < 0.001 |
| Correlation of BSA with mid-AAoDPositively correlated | r²=0.08 | r²=0.05 |
| P | P < 0.001 | P < 0.001 |
mid-AAoD with hypertension and diabetes
- ΔHypertension
- 2.9±0.5 mm
- ΔDiabetes
- 1.5±0.6 mm
- Hypertension was linked to higher mid-AAoD regardless of age and body surface area (BSA)
- Diabetes and mid-AAoD were uncorrelated across age-stratified subgroups
Causal analysis (Peter-Clark algorithm)
- Age, BSA, hypertension, and alcohol consumption are possibly causally related to mid-AAoD
- Diabetes and smoking are likely spuriously correlated
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →