Key result
MFDN model outperforms deep learning benchmarks for detecting cardiac hypertrophy from ECGs, achieving ~0.91 AUC.
Why the study?
Conventional ECG diagnostic criteria for cardiac hypertrophy have low sensitivity and existing deep learning methods inadequately capture frequency-domain abnormalities and inter-lead dependencies.
The MFDN deep learning model effectively captures frequency-domain features and inter-lead dependencies to achieve high accuracy and recall in automated ECG detection of cardiac hypertrophy.
MFDN shows competitive ECG performance for hypertrophy detection; hypothesis-generating pending prospective validation before clinical use.
Cardiac hypertrophy (HYP) is associated with an increased risk of heart failure and sudden death. Although the electrocardiogram (ECG) is widely available, conventional diagnostic criteria suffer from low sensitivity. Existing deep learning methods often fail to effectively capture frequency-domain abnormalities and inter-lead dependencies in hypertrophic ECG signals. To address these limitations, we propose the Multi-scale Frequency-domain Enhanced Dual Network (MFDN) for automated HYP-label diagnosis, which fully leverages both the time- and frequency-domain information in 12-lead ECGs. Specifically, the backbone network integrates a Multi-scale Frequency Enhancement (MSFE) module utilizing a trainable soft-adaptive threshold mechanism to adaptively decouple overlapping frequency components and extract precise pathological spectral representations. Furthermore, a lightweight topology-aware branch network and Prior Lead Fusion Network (PLFN) is designed to preserve the spatial topology of the 12-lead ECG. These dual-network representations are dynamically aligned and integrated through a PLFN via a channel-wise gating mechanism to guide the backbone network for precise hypertrophy detection. The model is evaluated on the PTB-XL database that comprises 2,649 subjects are annotated with HYP, using an 8:1:1 train–validation–test split. It achieves highly competitive performance compared to recent benchmarks at a low computational cost, achieving a recall of 0.7175, an AUC of 0.9070, an Accuracy of 0.8906, and an F1-score of 0.6506. This robust performance highlights the value of effectively capturing frequency-domain features for automated ECG annotation. Finally, feature importance analysis using Shapley values confirms that MFDN relies on clinically relevant pathological features.
No takes yet. Share an insight, caveat, or question.
Luo et al. (2026) studied Cardiac hypertrophy (n=2,649). Multi-scale Frequency-domain Enhanced Dual Network (MFDN) vs. State-of-the-art deep learning benchmarks (e.g., MsMdST, HCM-NET) was evaluated on Recall (Sensitivity) for cardiac hypertrophy detection (p=0.035). The MFDN model achieved a recall of 0.7175 and an AUC of 0.9070 for detecting cardiac hypertrophy from 12-lead ECGs, significantly outperforming state-of-the-art deep learning benchmarks.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: