Atrial fibrillation classification and detection from ECG recordings

Gündüz, Ali Fatih; Talu, Muhammed Fatih

doi:10.1016/j.bspc.2022.104531

Cited by 14 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study demonstrated the usefulness of the simulator in data augmentation for AI models, as well as in evaluating AF detection performance. Fatih Gündüz and Fatih Talu (2023) investigated different combination between ML and DL models for AF detection from ECG data. Spectral features, P waves, and RR interval differences were used as input to a BiLSTM network, achieving the best performance among compared methods.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Salvi,

Acharya,

Seoni

et al. 2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Atrial fibrillation (AF) affects more than 30 million individuals worldwide, making it the most prevalent cardiac arrhythmia on a global scale. This systematic review summarizes recent advancements in applying artificial intelligence (AI) techniques for AF detection, prediction, and guiding treatment selection and risk stratification. In adherence with the PRISMA guidelines (Preferred Reporting Items for Systematic Reviews and Meta‐Analyses), a total of 171 pertinent studies conducted between 2013 and 2023 were examined. Studies applying machine learning (ML) and deep learning (DL) to electrocardiogram (ECG), photoplethysmography (PPG), wearable data, and other sources were evaluated. For AF detection, most works employed DL (48 studies) and ML (28 studies) on ECG data. DL methods directly analyzed ECG waveforms and outperformed approaches relying on hand‐crafted features. For prediction and risk stratification, 22 studies used ML while 7 leveraged DL on ECG. An emerging trend showed the growing potential of PPG for AF screening. Overall, AI demonstrated promising capabilities across various AF‐related tasks. However, real‐world implementation faces challenges including a lack of interpretability, the need for multimodal data integration, prospective performance validation, and regulatory compliance. Future research directions involve quantifying model uncertainty, enhancing transparency, and conducting population‐based clinical trials to facilitate translation into practice.This article is categorized under: Application Areas > Health Care Application Areas > Science and Technology Technologies > Artificial Intelligence

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Salvi,

Acharya,

Seoni

et al. 2024

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…We randomly divided the dataset into training, validation, and test sets, and evaluated and compared the model on these datasets. To ensure the quality of the training data, we used 10-fold cross-validation [6,7,8] and split the data using stratified sampling. In addition, we also performed noise cancellation in the ECG signal.…”

Section: Dataset and Preprocessmentioning

confidence: 99%

“…Specifically, we used a trap filter to eliminate external electrical noise and a Fourier transform to smooth the filtered signal [9] . We truncated and filled the clean ECG signal by first finding the location of the R wave and extracting the data points before and after the R wave with the R wave as the center, and then extracting the QRS waveform in the ECG signal, including the positive peak of the QRS waveform [7,8] . Finally, we normalized all the data before fed into our model.…”

Section: Dataset and Preprocessmentioning

confidence: 99%

Automatic classification and detection of 12-lead electrocardiogram signal classification with Fourier convolutions

Liu

Yao

et al. 2023

Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023)

View full text Add to dashboard Cite

In this paper, we propose an Electrocardiogram (ECG) classification model based on FFC (Fast Fourier Convolution) and ResNet. The model utilizes FFC and ResNet for feature extraction and classification. We further improve the network performance and convergence speed through batch normalization and residual concatenation. The experimental results demonstrate that the model exhibits excellent classification performance under different data distributions in the PTB-XL database and trains faster than traditional ResNet models. Additionally, we introduce a new module, FFC-R, and validate its excellent performance in ECG classification tasks. This innovation is expected to provide powerful support for the diagnosis and treatment of heart diseases.

show abstract

“…The technological evolution in the field has been significantly supported by the application of deep learning techniques, such as Convolutional Neural Networks (CNNs) [7], [8], [9], [10], [11], Recurrent Neural Networks (RNNs) [12], [13], and hybrid models like Convolutional Recurrent Neural Networks (CRNNs) [14], [15], [16]. These advancements have propelled Afib classification from single-lead ECG recordings to new heights.…”

Section: Introductionmentioning

confidence: 99%

Mitigating Data Variability and Overfitting in Deep Learning Models for Atrial Fibrillation Detection Using Single-Lead ECGs

Benchaira,

Bitam,

Djihane Agli

2024

IJCDS

View full text Add to dashboard Cite

Despite the growing potential of deep learning in diagnosing Atrial Fibrillation (Afib), challenges such as overfitting and limited generalizability continue to persist. These limitations are accentuated in single-lead ECGs generated from wearable devices, which frequently suffer from inadequate annotation and substantial data variability. This study seeks to address these challenges by enhancing both the accuracy and generalizability of Afib detection algorithms. We introduce Afib-CNN, a specialized Convolutional Neural Network engineered for 9-second, single-lead ECGs. The architecture comprises ten convolutional blocks and three fully connected layers, focusing on computational efficiency. To mitigate data variability, we apply advanced pre-processing techniques like Moving Average by Convolution Filter (MAConv) and Minimum-Maximum Normalization. Further dataset refinement is achieved using z-score normalization and a shifted-length overlapping technique. The effectiveness of our model is rigorously validated across three distinct ECG databases, demonstrating robust intra-and inter-patient generalizability. Employing 10-fold stratified cross-validation, Afib-CNN exhibits exemplary performance, achieving mean F1 scores of 98%, 97%, and 99% on the CinC2017, CPSC2018, and MIT-AFIB datasets, respectively. The model also attains an F1 score of 98% on the CinC2017 test set. Comparative analyses demonstrate that Afib-CNN successfully balances high performance, computational efficiency, and robust generalization. These characteristics render it well-suited for practical clinical deployment.

show abstract

Atrial fibrillation classification and detection from ECG recordings

Cited by 14 publications

References 33 publications

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

Automatic classification and detection of 12-lead electrocardiogram signal classification with Fourier convolutions

Mitigating Data Variability and Overfitting in Deep Learning Models for Atrial Fibrillation Detection Using Single-Lead ECGs

Contact Info

Product

Resources

About