An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects

A Hybrid Deep Learning Approach for ECG-Based Arrhythmia Classification

Arrhythmias are defined as irregularities in the heartbeat rhythm, which may infrequently occur in a human’s life. These arrhythmias may cause potentially fatal complications, which may lead to an immediate risk of life. Thus, the detection and classification of arrhythmias is a pertinent issue for cardiac diagnosis. (1) Background: To capture these sporadic events, an electrocardiogram (ECG), a register containing the heart’s electrical function, is considered the gold standard. However, since ECG carries a vast amount of information, it becomes very complex and challenging to extract the relevant information from visual analysis. As a result, designing an efficient (automated) system to analyse the enormous quantity of data possessed by ECG is critical. (2) Method: This paper proposes a hybrid deep learning-based approach to automate the detection and classification process. This paper makes two-fold contributions. First, 1D ECG signals are translated into 2D Scalogram images to automate the noise filtering and feature extraction. Then, based on experimental evidence, by combining two learning models, namely 2D convolutional neural network (CNN) and the Long Short-Term Memory (LSTM) network, a hybrid model called 2D-CNN-LSTM is proposed. (3) Result: To evaluate the efficacy of the proposed 2D-CNN-LSTM approach, we conducted a rigorous experimental study using the widely adopted MIT–BIH arrhythmia database. The obtained results show that the proposed approach provides ≈98.7%, 99%, and 99% accuracy for Cardiac Arrhythmias (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR), respectively. Moreover, it provides an average sensitivity of the proposed model of 98.33% and a specificity value of 98.35%, for all three arrhythmias. (4) Conclusions: For the classification of arrhythmias, a robust approach has been introduced where 2D scalogram images of ECG signals are trained over the CNN-LSTM model. The results obtained are better as compared to the other existing techniques and will greatly reduce the amount of intervention required by doctors. For future work, the proposed method can be applied over some live ECG signals and Bi-LSTM can be applied instead of LSTM.

New criteria for evaluation of electroretinogram in patients with retinitis pigmentosa

BACKGROUND

Electroretinogram (ERG) plays an essential role in the diagnosis of retinal disease. Choosing appropriate methods could extract valuable information from ERG. In this study, a new criterion based on time-frequency domain analysis was proposed to investigate the retina in retinitis pigmentosa (RP) patients.

MATERIALS AND METHODS

The total number of 16 eyes from eight RP patients and 20 eyes from age-matched healthy subjects were assessed. The signals included photopic and scotopic ERGs. Continuous wavelet transform was applied to ERGs. Dominant frequencies were extracted, and the contours related to these dominant frequencies were selected. As a new criterion, the areas related to dominant frequency contours were considered a feature to differentiate the RP and normal groups. To better evaluate the proposed criterion results, the time-domain analysis characteristics of ERG were also considered.

RESULTS

The results showed an increase in implicit time and reduced amplitude in RP patients (P < 0.05). A significant decrease of dominant frequencies and increasing their occurrence time were seen in ERG of RP patients. Also, in RP patients, the third dominant frequency was disappeared from the three main frequencies observed in photopic ERGs of normal subjects. The area criterion showed a significant decrease in RP groups (P < 0.05).

CONCLUSION

RP can cause changes in the time and time-frequency components of the ERG. The area index could represent a new view of the characteristics of the ERG in the time-frequency domain. This criterion can help the ophthalmologist to have a better evaluation of retinal disease.

Extreme Learning Machine for Heartbeat Classification with Hybrid Time-Domain and Wavelet Time-Frequency Features

Automatic heartbeat classification via electrocardiogram (ECG) can help diagnose and prevent cardiovascular diseases in time. Many classification approaches have been proposed for heartbeat classification, based on feature extraction. However, the existing approaches face the challenges of high feature dimensions and slow recognition speeds. In this paper, we propose an efficient extreme learning machine (ELM) approach for heartbeat classification with multiple classes, based on the hybrid time-domain and wavelet time-frequency features. The proposed approach contains two sequential modules: (1) feature extraction of heartbeat signals, including RR interval features in the time-domain and wavelet time-frequency features, and (2) heartbeat classification using ELM based on the extracted features. RR interval features are calculated to reflect the dynamic characteristics of heartbeat signals. Discrete wavelet transform (DWT) is used to decompose the heartbeat signals and extract the time-frequency features of the heartbeat signals along the timeline. ELM is a single-hidden layer feedforward neural network with the hidden layer parameters randomly generated in advance and the output layer parameters calculated optimally using the least-square algorithm directly using the training samples. ELM is used as the heartbeat classification algorithm due to its high accuracy training accuracy, fast training speed, and good generalization ability. Experimental testing is carried out using the public MIT-BIH arrhythmia dataset to perform a 16-class classification. Experimental results show that the proposed approach achieves a superior classification accuracy with fast training and recognition speeds, compared with existing classification algorithms.