A Novel Deep-Learning-Based Framework for the Classification of Cardiac Arrhythmia

A noninvasive hyperkalemia monitoring system for dialysis patients based on a 1D-CNN model and single-lead ECG from wearable devices

This study aimed to develop a real-time, noninvasive hyperkalemia monitoring system for dialysis patients with chronic kidney disease. Hyperkalemia, common in dialysis patients, can lead to life-threatening arrhythmias or sudden death if untreated. Therefore, real-time monitoring of hyperkalemia in this population is crucial. We propose a wearable single-lead ECG monitoring system, offering enhanced comfort and feasibility for extended use. The key innovation of this system is the design of a compact, multi-channel convolutional neural network. This model offers high stability, strong performance, and exceptional computational efficiency, making it ideal for seamless integration into wearable devices for real-time monitoring applications. The model automatically extracts features from ECG signals at different frequencies through multiple convolutional channels, eliminating the need for manual feature extraction before data input. Data is input using a non-overlapping sliding window approach, reducing preprocessing complexity while maintaining model performance. We investigated the optimal window length and the number of convolution channels for ECG signal input. Experimental results indicate that the model achieves optimal performance with a 1200 ms window length and four parallel convolutional branches, yielding an accuracy of 98.25% (4.52%), F1-score of 98.31% (3.26%), sensitivity of 98.63% (2.41%), and specificity of 97.88% (5.13%). This system holds significant potential for improving patient monitoring comfort and real-time responsiveness.

Generalization challenges in electrocardiogram deep learning: insights from dataset characteristics and attention mechanism

Aim: Deep learning's widespread use prompts heightened scrutiny, particularly in the biomedical fields, with a specific focus on model generalizability. This study delves into the influence of training data characteristics on the generalization performance of models, specifically in cardiac abnormality detection. Materials & methods: Leveraging diverse electrocardiogram datasets, models are trained on subsets with varying characteristics and subsequently compared for performance. Additionally, the introduction of the attention mechanism aims to improve generalizability. Results: Experiments reveal that using a balanced dataset, just 1% of a large dataset, leads to equal performance in generalization tasks, notably in detecting cardiology abnormalities. Conclusion: This balanced training data notably enhances model generalizability, while the integration of the attention mechanism further refines the model's ability to generalize effectively.

An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

BACKGROUND AND OBJECTIVES

Valvular heart diseases (VHDs) are one of the dominant causes of cardiovascular abnormalities that have been associated with high mortality rates globally. Rapid and accurate diagnosis of the early stage of VHD based on cardiac phonocardiogram (PCG) signal is critical that allows for optimum medication and reduction of mortality rate.

METHODS

To this end, the current study proposes novel deep learning (DL)-based high-performance VHD detection frameworks that are relatively simpler in terms of network structures, yet effective for accurately detecting multiple VHDs. We present three different frameworks considering both 1D and 2D PCG raw signals. For 1D PCG, Mel frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) features, whereas, for 2D PCG, various deep convolutional neural networks (D-CNNs) features are extracted. Additionally, nature/bio-inspired algorithms (NIA/BIA) including particle swarm optimization (PSO) and genetic algorithm (GA) have been utilized for automatic and efficient feature selection directly from the raw PCG signal. To further improve the performance of the classifier, vision transformer (ViT) has been implemented levering the self-attention mechanism on the time frequency representation (TFR) of 2D PCG signal. Our extensive study presents a comparative performance analysis and the scope of enhancement for the combination of different descriptors, classifiers, and feature selection algorithms.

MAIN RESULTS

Among all classifiers, ViT provides the best performance by achieving mean average accuracy Acc of 99.90 % and F1-score of 99.95 % outperforming current state-of-the-art VHD classification models.

CONCLUSIONS

The present research provides a robust and efficient DL-based end-to-end PCG signal classification framework for designing a automated high-performance VHD diagnosis system.

Distinguishing Malicious Drones Using Vision Transformer

Drones are commonly used in numerous applications, such as surveillance, navigation, spraying pesticides in autonomous agricultural systems, various military services, etc., due to their variable sizes and workloads. However, malicious drones that carry harmful objects are often adversely used to intrude restricted areas and attack critical public places. Thus, the timely detection of malicious drones can prevent potential harm. This article proposes a vision transformer (ViT) based framework to distinguish between drones and malicious drones. In the proposed ViT based model, drone images are split into fixed-size patches; then, linearly embeddings and position embeddings are applied, and the resulting sequence of vectors is finally fed to a standard ViT encoder. During classification, an additional learnable classification token associated to the sequence is used. The proposed framework is compared with several handcrafted and deep convolutional neural networks (D-CNN), which reveal that the proposed model has achieved an accuracy of 98.3%, outperforming various handcrafted and D-CNNs models. Additionally, the superiority of the proposed model is illustrated by comparing it with the existing state-of-the-art drone-detection methods.