Key result
Data augmentation boosts AI-based ECG classification performance by up to ~32%.
Why the study?
AI-based ECG analysis depends on large-scale labeled datasets that are challenging to accumulate, prompting the development of data augmentation strategies to improve model performance.
Do data augmentation techniques improve the performance of AI-based models for ECG signal classification?
Systematic Review (n=119)
Do data augmentation techniques improve the performance of AI-based models for ECG signal classification?
Data augmentation techniques, particularly advanced generative models like GANs and VAEs, can significantly improve the performance of AI-based ECG classification models by addressing data scarcity and class imbalance.
May enhance AI ECG tools in practice; extends evidence for data augmentation to address labeled dataset limits in model development.
AI techniques have recently been put under the spotlight for analyzing electrocardiograms (ECGs). However, the performance of AI-based models relies on the accumulation of large-scale labeled datasets, which is challenging. To increase the performance of AI-based models, data augmentation (DA) strategies have been developed recently. The study presented a comprehensive systematic literature review of DA for ECG signals. We conducted a systematic search and categorized the selected documents by AI application, number of leads involved, DA method, classifier, performance improvements after DA, and datasets employed. With such information, this study provided a better understanding of the potential of ECG augmentation in enhancing the performance of AI-based ECG applications. This study adhered to the rigorous PRISMA guidelines for systematic reviews. To ensure comprehensive coverage, publications between 2013 and 2023 were searched across multiple databases, including IEEE Explore, PubMed, and Web of Science. The records were meticulously reviewed to determine their relevance to the study's objective, and those that met the inclusion criteria were selected for further analysis. Consequently, 119 papers were deemed relevant for further review. Overall, this study shed light on the potential of DA to advance the field of ECG diagnosis and monitoring.
No takes yet. Share an insight, caveat, or question.
Rahman et al. (2023) conducted a systematic review in Cardiovascular diseases (ECG analysis) (n=119). Data augmentation techniques vs. Unaugmented datasets was evaluated on Performance improvements of AI-based models after data augmentation. Data augmentation techniques, including basic transformations and advanced generative models like GANs, demonstrated potential to improve AI-based ECG classification performance by up to 32%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: