Classification of De novo post-operative and persistent atrial fibrillation using multi-channel ECG recordings

Moghaddasi, Hanie; Hendriks, Richard C.; Veen, Alle-Jan van der; Groot, Natasja M.S. de; Hunyadi, Borbála

doi:10.1016/j.compbiomed.2022.105270

Cited by 5 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we focus, in particular, on the classification between paroxysmal AF (PAF) and persistent AF (PsAF) to investigate the development stages of AF. Moreover, AF is a progressive disease and the success rate of the most common treatment, ablation therapy, highly depends on the severity of AF [2,3]. Therefore, understanding how rank-related features of atrial potentials can differ between different stages of AF is important.…”

Section: Introductionmentioning

confidence: 99%

Novel Rank-based Features of Atrial Potentials for the Classification Between Paroxysmal and Persistent Atrial Fibrillation

Moghaddasi¹,

Hendriks²,

Veen³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Atrial fibrillation (AF) is the most common arrhythmia. Although the exact cause is unclear, electropathology of atrial tissue is one contributing factor. Electropathological characteristics derived from intra-operative epicardial measurements, such as conduction block (CB) and continues conduction delay and block (cCDCB), can be used to assess the severity of AF. In sinus rhythm, however, these parameters do not indicate significant difference between different development stages of AF, such as paroxysmal and persistent AF. Therefore, we propose a methodology to improve AF severity detection using intra-operative electrograms. We propose a model that describes the spatial diversity of atrial potential waveforms during a single beat on the multi-channel electrograms. Based on this model, we derive two novel features. During sinus rhythm, we used 293 beats from patients with a history of paroxysmal or persistent AF. Using a random forest classifier, we achieved 78.42% classification accuracy, while classification based on the CB and cCDCB leads to an accuracy of 58.34%.

show abstract

Section: Introductionmentioning

confidence: 99%

Novel Rank-based Features of Atrial Potentials for the Classification Between Paroxysmal and Persistent Atrial Fibrillation

Moghaddasi¹,

Hendriks²,

Veen³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

show abstract

“…The intricacy of P-QRS-T waves and the nuanced shifts in ECGs pose substantial challenges for clinicians in accurately interpreting and analyzing the data, thereby underscoring the demand for more efficient and precise methods for protracted ECG analysis. Responding to this need, ECG-based arrhythmia detection CAD systems have been proposed [206,207], aiming to minimize manual effort and enhance the accuracy of detection. However, a significant obstacle to reliable automatic heartbeat detection arises from the variations in waveform and ECG characteristics between individuals and diverse groups [208].…”

Section: Introductionmentioning

confidence: 99%

Domain adaptation in biomedical engineering: unsupervised, source-free, and black box approaches

Yuan

View full text Add to dashboard Cite

The remarkable advancements in deep learning methodologies over recent years can be attributed to the availability of large, high-quality labeled datasets, intricate network structures, and the swift progression of hardware technologies. However, in the biomedical engineering, the scarcity of data often poses a significant challenge in training a well-generalized model. This thesis delves into the potential of transfer learning methods as a viable solution to this data scarcity issue. The research provides a comprehensive exploration of Transfer Learning (TL), Unsupervised Domain Adaptation (UDA), Source-Free Domain Adaptation (SFDA), and Black-Box Domain Adaptation (BBDA) within the realm of biomedical engineering. It tackles the issue of data dependency in deep learning, with a particular emphasis on the application of TL in fine-tuning neural networks for specialized tasks. The study further investigates UDA techniques, specifically in the context of cross-dataset EEG classification tasks, and proposes entropy minimization-based methodologies to alleviate domain shifts. The thesis also scrutinizes SFDA in the context of medical imaging segmentation and abnormal ECG classification, introducing three innovative methodologies to overcome inherent challenges. Expanding on SFDA, the thesis evaluates the efficiency and accuracy of BBDA in real-time applications for cross-subject EEG driver drowsiness detection. This research contributes novel insights into handling data dependency, domain shifts, and privacy concerns in biomedical engineering, advocating for a nuanced approach where the scope of achievements is judiciously balanced against the challenges posed by scarce data.

show abstract

Target-oriented augmentation privacy-protection domain adaptation for imbalanced ECG beat classification

Liqiang

Siyal

2023

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Classification of De novo post-operative and persistent atrial fibrillation using multi-channel ECG recordings

Cited by 5 publications

References 48 publications

Novel Rank-based Features of Atrial Potentials for the Classification Between Paroxysmal and Persistent Atrial Fibrillation

Novel Rank-based Features of Atrial Potentials for the Classification Between Paroxysmal and Persistent Atrial Fibrillation

Domain adaptation in biomedical engineering: unsupervised, source-free, and black box approaches

Target-oriented augmentation privacy-protection domain adaptation for imbalanced ECG beat classification

Contact Info

Product

Resources

About