Key result
Federated deep learning classifies 20 cardiac conditions with ~0.85 AUROC but misses rare diagnoses.
Why the study?
Does a federated learning-based ResNet-1D deep learning model accurately detect cardiovascular diseases from ECGs across different demographic groups?
Observational (n=18,869)
Does a federated learning-based ResNet-1D deep learning model accurately detect cardiovascular diseases from ECGs across different demographic groups?
Federated learning models for ECG analysis show strong diagnostic performance for common rhythm disorders but require class balancing and specific thresholds to safely detect rare conditions and atrial fibrillation.
Background: Federated learning (FL) enables privacy-preserving collaborative model training across healthcare institutions without sharing patient data. We evaluated disease-specific detection performance and demographic disparities in FL algorithms for ECG-based cardiovascular diagnosis across 20 cardiac conditions. Methods: Using the PTB-XL dataset (n=21,799 ECG recordings, 18,869 patients, 20 cardiac conditions), we trained a ResNet-1D deep learning model for multi-label classification. We assessed performance across critical conditions (atrial fibrillation, myocardial infarctions, AV blocks), rhythm disorders, and conduction abnormalities. Model evaluation included disease-specific AUROC, sensitivity, and clinical priority stratification across sex and age subgroups. Results: On 3,343 independent test samples, the model achieved mean AUROC of 0.853 across 20 conditions. Rhythm disorders showed excellent performance: sinus tachycardia (0.976), right bundle branch block (0.970), atrial flutter (0.970), and sinus bradycardia (0.953). Among myocardial infarctions, anteroseptal MI achieved 0.950 AUROC with 53.9% sensitivity, while inferior MI achieved 0.889 AUROC with 62.8% sensitivity. However, critical limitations emerged: atrial fibrillation showed only 24.7% sensitivity despite 0.881 AUROC, missing 75% of cases—a major clinical concern given stroke risk. Rare conditions suffered from class imbalance: third-degree AV block (n=4, 0% sensitivity) and second-degree AV block (n=2, 0% sensitivity). Demographic analysis revealed minimal sex disparity (0.09% accuracy difference) but age-related performance decline in elderly populations (>80 years). Conclusion: Deep learning achieves strong disease-specific detection for common cardiovascular conditions (AUROC >0.95 for rhythm disorders), but class imbalance severely limits rare condition detection. Low atrial fibrillation sensitivity represents a critical safety gap requiring intervention strategies. Federated learning offers promise for multi-site collaborative diagnosis while preserving patient privacy, though disease-specific validation is essential. Clinical Implications: Models excel at detecting frequent conditions but fail on rare, life-threatening diseases. Clinical deployment requires condition-specific performance thresholds, class balancing strategies (oversampling, focal loss), and mandatory rare condition review protocols.
No takes yet. Share an insight, caveat, or question.
Bouras et al. (2026) conducted an observational in Cardiovascular disease (20 cardiac conditions) (n=18,869). Federated learning ResNet-1D deep learning model was evaluated on Mean AUROC across 20 conditions on independent test samples. A federated learning ResNet-1D model achieved a mean AUROC of 0.853 across 20 cardiac conditions, though atrial fibrillation sensitivity was only 24.7% and rare conditions had 0% sensitivity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: