A Systematic Survey of Data Augmentation of ECG Signals for AI Applications

Rahman, Md. Moklesur; Rivolta, Massimo W.; Badilini, Fabio; Sassi, Roberto

doi:10.3390/s23115237

Cited by 15 publications

(6 citation statements)

References 144 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, based on our trials, the trio of signal transformations discussed previously proved optimal for our distinct task and dataset. This aligns with Rahman et al's systematic review [37]…”

Section: Augmentationsupporting

confidence: 89%

End-to-End Premature Ventricular Contraction Detection Using Deep Neural Networks

Kraft,

Bieber,

Jokisch

et al. 2023

Sensors

View full text Add to dashboard Cite

In Holter monitoring, the precise detection of standard heartbeats and ventricular premature contractions (PVCs) is paramount for accurate cardiac rhythm assessment. This study introduces a novel application of the 1D U-Net neural network architecture with the aim of enhancing PVC detection in Holter recordings. Training data comprised the Icentia 11k and INCART DB datasets, as well as our custom dataset. The model’s efficacy was subsequently validated against traditional Holter analysis methodologies across multiple databases, including AHA DB, MIT 11 DB, and NST, as well as another custom dataset that was specifically compiled by the authors encompassing challenging real-world examples. The results underscore the 1D U-Net model’s prowess in QRS complex detection, achieving near-perfect balanced accuracy scores across all databases. PVC detection exhibited variability, with balanced accuracy scores ranging from 0.909 to 0.986. Despite some databases, like the AHA DB, showcasing lower sensitivity metrics, their robust, balanced accuracy accentuates the model’s equitable performance in discerning both false positives and false negatives. In conclusion, while the 1D U-Net architecture is a formidable tool for QRS detection, there’s a clear avenue for further refinement in its PVC detection capability, given the inherent complexities and noise challenges in real-world PVC occurrences.

show abstract

Section: Augmentationsupporting

confidence: 89%

End-to-End Premature Ventricular Contraction Detection Using Deep Neural Networks

Kraft,

Bieber,

Jokisch

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In this proof-of-concept study, we demonstrated that performant ML algorithms can be trained on Ca 2+ fluctuations in activated monoclonal T cells to predict polyclonal T cell responses, using a limited amount of data (~10,000 cells). Substantially increasing the size of the dataset with additional time lapses or through AI-assisted methods may further improve model performance, especially when it comes to differentiating the distinct pattern of Ca 2+ fluctuation associated with nonspecific T cells mispredicted as antigen-specific from bona fide antigen-specific T cells ( 43 – 45 ). Furthermore, it has been previously demonstrated that Ca 2+ oscillations contain information about the affinity of TCR-pMHC interactions; lower affinity TCR engagement will typically lead to more transient Ca 2+ fluctuations and distinct early activation dynamics ( 14 – 16 ).…”

Section: Discussionmentioning

confidence: 99%

Machine learning predictions of T cell antigen specificity from intracellular calcium dynamics

This,

Costantino,

Melichar

2024

Sci. Adv.

View full text Add to dashboard Cite

Adoptive T cell therapies rely on the production of T cells with an antigen receptor that directs their specificity toward tumor-specific antigens. Methods for identifying relevant T cell receptor (TCR) sequences, predominantly achieved through the enrichment of antigen-specific T cells, represent a major bottleneck in the production of TCR-engineered cell therapies. Fluctuation of intracellular calcium is a proximal readout of TCR signaling and candidate marker for antigen-specific T cell identification that does not require T cell expansion; however, calcium fluctuations downstream of TCR engagement are highly variable. We propose that machine learning algorithms may allow for T cell classification from complex datasets such as polyclonal T cell signaling events. Using deep learning tools, we demonstrate accurate prediction of TCR-transgenic CD8 + T cell activation based on calcium fluctuations and test the algorithm against T cells bearing a distinct TCR as well as polyclonal T cells. This provides the foundation for an antigen-specific TCR sequence identification pipeline for adoptive T cell therapies.

show abstract

“…Basic data augmentation techniques encompass flipping, snipping, and introducing noise. In addition to these techniques, some other basic data augmentation techniques such as spatial inversion [11], time-spatial inversion [6], baseline wandering [20] are also applied to ECG signals. However, when it comes to the management of complex data such as medical imaging, these basic techniques are inadequate.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, when it comes to the management of complex data such as medical imaging, these basic techniques are inadequate. The variational autoencoder (VAE) [20] is a deep model that has received less attention compared to other more widely adopted techniques. Nevertheless, a prominent concern revolves around the recurrent occurrence of hazy and indistinct output images.…”

Section: Literature Reviewmentioning

confidence: 99%

A Generative Model for Deep Fake Augmentation of Phonocardiogram and Electrocardiogram Signals Using Lsgan and Cycle Gan

Rayavarapu,

Prasanthi,

Kumar

et al. 2023

IAPGOS

View full text Add to dashboard Cite

In order to diagnose a range of cardiac conditions, it is important to conduct an accurate evaluation of either phonocardiogram (PCG) and electrocardiogram (ECG) data. Artificial intelligence and machine learning-based computer-assisted diagnostics are becoming increasingly commonplace in modern medicine, assisting clinicians in making life-or-death decisions. The requirement for an enormous amount of information for training to establish the framework for a deep learning-based technique is an empirical challenge in the field of medicine. This increases the risk of personal information being misused. As a direct result of this issue, there has been an explosion in the study of methods for creating synthetic patient data. Researchers have attempted to generate synthetic ECG or PCG readings. To balance the dataset, ECG data were first created on the MIT-BIH arrhythmia database using LS GAN and Cycle GAN. Next, using VGGNet, studies were conducted to classify arrhythmias for the synthesized ECG signals. The synthesized signals performed well and resembled the original signal and the obtained precision of 91.20%, recall of 89.52% and an F1 score of 90.35%.

show abstract

A Systematic Survey of Data Augmentation of ECG Signals for AI Applications

Cited by 15 publications

References 144 publications

End-to-End Premature Ventricular Contraction Detection Using Deep Neural Networks

End-to-End Premature Ventricular Contraction Detection Using Deep Neural Networks

Machine learning predictions of T cell antigen specificity from intracellular calcium dynamics

A Generative Model for Deep Fake Augmentation of Phonocardiogram and Electrocardiogram Signals Using Lsgan and Cycle Gan

Contact Info

Product

Resources

About