Key result
A novel heartbeat classification method using hybrid time-frequency analysis and ResNet-101 achieved an overall F1-score of 0.9595 for 5 categories and 99.75% accuracy for 14 beat kinds.
Why the study?
Heartbeat classification is important for cardiac arrhythmia analysis, but traditional methods require manual feature extraction.
A novel hybrid time-frequency analysis and ResNet-101 transfer learning method demonstrates high accuracy and F1-scores for automated heartbeat classification using the MIT-BIH arrhythmia database.
The classification of heartbeats is an important method for cardiac arrhythmia analysis. This study proposes a novel heartbeat classification method using hybrid time-frequency analysis and transfer learning based on ResNet-101. The proposed method has the following major advantages over the afore-mentioned methods: it avoids the need for manual features extraction in the traditional machine learning method, and it utilizes 2-D time-frequency diagrams which provide not only frequency and energy information but also preserve the morphological characteristic within the ECG recordings, and it owns enough deep to make better use of performance of CNN. The method deploys a hybrid time-frequency analysis of the Hilbert transform (HT) and the Wigner-Ville distribution (WVD) to transform 1-D ECG recordings into 2-D time-frequency diagrams which were then fed into a transfer learning classifier based on ResNet-101 for two classification tasks (i.e., 5 heartbeat categories assigned by the ANSI/AAMI standard (i.e., N, V, S, Q and F) and 14 original beat kinds of the MIT/BIH arrhythmia database). For 5 heartbeat categories classification, the results show the F1-score of N, V, S, Q and F categories are F<tex-math notation="LaTeX">N</tex-math> 0.9899, F<tex-math notation="LaTeX">V</tex-math> 0.9845, F<tex-math notation="LaTeX">S</tex-math> 0.9376, F<tex-math notation="LaTeX">Q</tex-math> 0.9968, F<tex-math notation="LaTeX">F</tex-math> 0.8889, respectively, and the overall F1-score is 0.9595 using the combination data balancing. The results show the average values for accuracy, sensitivity, specificity, predictive value and F1-score on test set for 14 beat kinds the MIT-BIH arrhythmia database are 99.75%, 91.36%, 99.85%, 90.81% and 0.9016, respectively. Compared with other methods, the proposed method can yield more accurate results.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2021) studied Cardiac arrhythmia. Hybrid time-frequency analysis and transfer learning based on ResNet-101 vs. Traditional machine learning methods was evaluated on Classification performance for 5 heartbeat categories and 14 original beat kinds. A novel heartbeat classification method using hybrid time-frequency analysis and ResNet-101 achieved an overall F1-score of 0.9595 for 5 categories and 99.75% accuracy for 14 beat kinds.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: