Key result
Novel deep learning framework predicts SCD one hour before onset with ~95% accuracy.
Why the study?
Sudden cardiac death is a leading cause of global mortality, but accurately predicting it at an early stage remains a critical clinical challenge.
Does a fusion-based time-frequency deep learning framework accurately predict sudden cardiac death from ECG signals one hour before onset?
Does a fusion-based time-frequency deep learning framework accurately predict sudden cardiac death from ECG signals one hour before onset?
A novel fusion-based time-frequency deep learning framework achieved 94.6% accuracy in predicting sudden cardiac death from ECG signals one hour prior to onset.
Requires prospective validation before use; leaves open whether fusion DL models can predict SCD from ECG.
Sudden cardiac death (SCD) is one of the leading causes of global mortality, often occurring without warning and driven by complex cardiac dynamics. Despite significant advances in cardiovascular diagnostics, accurately predicting SCD at an early stage remains a critical challenge. This study proposes a novel fusion-based time-frequency (T-F) deep learning framework for the early prediction of SCD by classifying associated cardiac conditions. Electrocardiogram (ECG) signals were first denoised and segmented to isolate clinically relevant patterns. These signals were then transformed into two-dimensional T-F representations using spectrograms and scalograms, capturing complementary temporal and spectral information. An average fusion technique merged these representations, enriching T-F images with enhanced discriminatory power. The fused images were used to train deep learning (DL) models, and performance was evaluated using subject-wise data splits to assess generalizability across individuals. The proposed approach achieved a classification accuracy of 94.60 %, effectively identifying cardiac conditions associated with SCD one hour before its onset. This fusion-based framework shows strong potential for integration into real-time, automated diagnostic systems, enabling early warning, personalized monitoring, and timely intervention to reduce fatal outcomes.
No takes yet. Share an insight, caveat, or question.
Karimulla et al. (2025) studied Sudden cardiac death. Fusion-based time-frequency deep learning framework was evaluated on Classification accuracy for predicting sudden cardiac death. A novel fusion-based time-frequency deep learning framework achieved a classification accuracy of 94.60% for predicting sudden cardiac death one hour before its onset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: