Key result
GAN-augmented hybrid 1D CNN-BiLSTM model achieves ~92% ECG classification accuracy, outperforming the non-augmented model.
Why the study?
Does a GAN-augmented Hybrid 1D CNN-BiLSTM model improve ECG classification accuracy and minority class recall under patient-wise validation in the MIT-BIH Arrhythmia Database?
Does a GAN-augmented Hybrid 1D CNN-BiLSTM model improve ECG classification accuracy and minority class recall under patient-wise validation in the MIT-BIH Arrhythmia Database?
Absolute Event Rate: 91.69% vs 90.68%
p-value: p=0.0004
A GAN-augmented hybrid 1D CNN-BiLSTM model significantly improves ECG classification accuracy and minority class recall under rigorous patient-wise validation, highlighting that traditional beat-wise evaluation overestimates clinical performance.
Automated electrocardiogram (ECG) classification for heart disease detection encounters significant challenges, such as patient variability, inter-patient differences in heart signals, and data leakage when information from the same patient is present in both training and test sets. To mitigate these challenges, a Hybrid 1D CNN-BiLSTM (one- dimensional convolutional and bidirectional long short-term memory) deep learning framework is introduced, employing rigorous patient-wise validation on the MIT-BIH Arrhythmia Database. Patient-wise data splitting (34 records for training, 14 records for testing) ensures that each patient’s data is confined to a single set, effectively preventing data leakage. Under these conditions, the proposed Hybrid with GAN model achieves 91.69% accuracy (95% confidence interval: 91.41−91.99%), with a macro F1-score of 0.547 ± 0.374. Conditional GAN augmentation significantly improves minority class performance: Supraventricular recall increases from 9.2% to 20.9% (+127.2%), and Ventricular recall improves from 77.7% to 80.9% (+4.1%). Statistical significance testing using McNemar’s test demonstrates the superiority of Hybrid with GAN over the non-augmented hybrid model ( χ ² = 12.41 , p = 0.0004). The observed 7.31% performance gap between beat-wise (99.0%) and patient-wise (91.69%) evaluation highlights the critical importance of patient-wise validation for clinically realistic performance estimates. Overall, this framework provides a rigorous patient-wise evaluation protocol for automated ECG classification, with patient-wise results for a GAN-augmented hybrid model on the full 5-class MIT-BIH dataset.
No takes yet. Share an insight, caveat, or question.
Sa. I. Ibrahim (2026) studied Arrhythmia (n=47). Hybrid 1D CNN-BiLSTM with GAN augmentation vs. Non-augmented hybrid model was evaluated on Patient-wise classification accuracy (95% CI 91.41-91.99, p=0.0004). The proposed Hybrid 1D CNN-BiLSTM model with GAN augmentation achieved a patient-wise classification accuracy of 91.69%, significantly outperforming the non-augmented hybrid model.
Synapse has enriched 5 related papers. Consider them for comparative context: