Detection of Atrial Fibrillation Using 1D Convolutional Neural Network

Abstract

The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which results in heavy training computation and high implementation cost. This paper proposes an AF detection method based on an end-to-end 1D convolutional neural network (CNN) architecture to raise the detection accuracy and reduce network complexity. By investigating the impact of major components of a convolutional block on detection accuracy and using grid search to obtain optimal hyperparameters of the CNN, we develop a simple, yet effective 1D CNN. Since the dataset provided by PhysioNet Challenge 2017 contains ECG recordings with different lengths, we also propose a length normalization algorithm to generate equal-length records to meet the requirement of CNN. Experimental results and analysis indicate that our method of 1D CNN achieves an average F1 score of 78.2%, which has better detection accuracy with lower network complexity, as compared with the existing deep learning-based methods.

Electrocardiogram lead selection for intelligent screening of patients with systolic heart failure

“…In many ECG AI studies, researchers used 1D-CNN to classify ECG signals, such as for atrial fibrillation classification 4 , 15 . We compare 1D and 2D-CNNs in this study by establishing three simple 1D-CNN models and applied the 1D-CNN structure of the two papers on our dataset 16 , 17 (Tables S4 – S7 ). According to the above comparison, our 2D-CNN shows the highest accuracy in predicting systolic heart failure compared to the other three 1D-CNN models.…”

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification

“…Recently, CNNs have achieved great success in image classification in daily use and have also been applied in scientific studies ( Hochuli et al, 2018 ; Hsieh et al, 2020 ; Zhou et al, 2018 ). A novel helix matrix transformation method was suggested to convert 1D array-type MS spectrum data into matrix-type.…”

“…The Softmax function defined in Eq. (7) was applied in the last layer to produce the prediction probability over the 14 output classes ( Hsieh et al, 2020 ).…”

“…Recently, convolutional neural networks (CNNs) have achieved great success in image classification, object recognition and natural language processing ( Hsieh et al, 2020 ). Unlike other machine learning algorithms, the convolutional layers in CNNs extract image feature information from source images to form a weight map during the training process, which provide more feature details than manual acquisition ( Wang et al, 2020 ).…”

Off-Person ECG Biometrics Using Spatial Representations and Convolutional Neural Networks

“…using cropping: while the clinical significance of standard 1D representations may be adversely affected by various augmentation procedures, multiple patches of reduced size may be extracted from a given spatial representation and further resized by linear interpolation [12], coping with the highly unbalanced training datasets scenario. Comparative analysis of 1D versus 2D approaches to ECG classification revealed up to 3% performance improvement [13], [14], while requiring more complex models and additional conversion overhead.…”