An Interpretable Hand-Crafted Feature-Based Model for Atrial Fibrillation Detection

Atrial Fibrillation (AF) is the most common type of cardiac arrhythmia. Early diagnosis of AF helps to improve therapy and prognosis. Machine Learning (ML) has been successfully applied to improve the effectiveness of Computer-Aided Diagnosis (CADx) systems for AF detection. Presenting an explanation for the decision made by an ML model is considerable from the cardiologists' point of view, which decreases the complexity of the ML model and can provide tangible information in their diagnosis. In this paper, a range of explanation techniques is applied to hand-crafted features based ML models for heart rhythm classification. We validate the impact of the techniques by applying feature selection and classification to the 2017 CinC/PhysioNet challenge dataset. The results show the effectiveness and efficiency of SHapley Additive exPlanations (SHAP) technique along with Random Forest (RF) for the classification of the Electrocardiogram (ECG) signals for AF detection with a mean F-score of 0.746 compared to 0.706 for a technique based on the same features based on a cascaded SVM approach. The study also highlights how this interpretable hand-crafted feature-based model can provide cardiologists with a more compact set of features and tangible information in their diagnosis.

Download Full-text

An Automatic System for Atrial Fibrillation by Using a CNN-LSTM Model

Discrete Dynamics in Nature and Society ◽

10.1155/2020/3198783 ◽

2020 ◽

Vol 2020 ◽

pp. 1-9

Author(s):

Fengying Ma ◽

Jingyao Zhang ◽

Wei Chen ◽

Wei Liang ◽

Wenjia Yang

Keyword(s):

Atrial Fibrillation ◽

Classification Accuracy ◽

Short Term Memory ◽

Sequence Data ◽

Detection System ◽

Heart Rhythm ◽

Classification Performance ◽

Ecg Signals ◽

Electrocardiogram Ecg

Atrial fibrillation (AF) is a common abnormal heart rhythm disease. Therefore, the development of an AF detection system is of great significance to detect critical illnesses. In this paper, we proposed an automatic recognition method named CNN-LSTM to automatically detect the AF heartbeats based on deep learning. The model combines convolutional neural networks (CNN) to extract local correlation features and uses long short-term memory networks (LSTM) to capture the front-to-back dependencies of electrocardiogram (ECG) sequence data. The CNN-LSTM is feeded by processed data to automatically detect AF signals. Our study uses the MIT-BIH Atrial Fibrillation Database to verify the validity of the model. We achieved a high classification accuracy for the heartbeat data of the test set, with an overall classification accuracy rate of 97.21%, sensitivity of 97.34%, and specificity of 97.08%. The experimental results show that our model can robustly detect the onset of AF through ECG signals and achieve stable classification performance, thereby providing a suitable candidate for the automatic classification of AF.

Download Full-text

Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks

10.21203/rs.3.rs-44313/v2 ◽

2021 ◽

Author(s):

Murside Degirmenci ◽

Mehmet Akif Ozdemir ◽

Elif Izci ◽

Aydin Akan

Keyword(s):

Heart Rhythm ◽

Classification Performance ◽

Network Architectures ◽

Test Results ◽

Detection Scheme ◽

Heartbeat Classification ◽

Ecg Signals ◽

Electrocardiogram Ecg ◽

Aided Diagnosis

Abstract Background: Electrocardiogram (ECG) is a method of recording the electrical activity of the heart and it provides a diagnostic means for heart-related diseases. Arrhythmia is any irregularity of the heartbeat that causes an abnormality in the heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG recordings is not practical for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to develop computer-aided-diagnosis (CAD) systems to automatically identify arrhythmias.Methods: This paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The proposed approach identifies arrhythmia classes using Convolutional Neural Network (CNN) trained by two-dimensional (2D) ECG beat images. Firstly, ECG signals, which consist of 5 different arrhythmias, are segmented into heartbeats which are transformed into 2D grayscale images. Afterward, the images are used as input for training a new CNN architecture to classify heartbeats. Results: The experimental results show that the classification performance of the proposed approach reaches an overall accuracy of 99.7%, sensitivity of 99.7%, and specificity of 99.22% in the classification of five different ECG arrhythmias. Further, the proposed CNN architecture is compared to other popular CNN architectures such as LeNet and ResNet-50 to evaluate the performance of the study.Conclusions: Test results demonstrate that the deep network trained by ECG images provides outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Moreover, the proposed method has lower computational costs compared to existing methods and is more suitable for mobile device-based diagnosis systems as it does not involve any complex preprocessing process. Hence, the proposed approach provides a simple and robust automatic cardiac arrhythmia detection scheme for the classification of ECG arrhythmias.

Download Full-text

ECG Heartbeat Classification Based on Signal-to-Image Transformation Using Convolutional Neural Networks

10.21203/rs.3.rs-44313/v1 ◽

2020 ◽

Author(s):

Murside Degirmenci ◽

Mehmet Akif Ozdemir ◽

Elif Izci ◽

Aydin Akan

Keyword(s):

Recognition Performance ◽

Heart Rhythm ◽

Classification Performance ◽

Test Accuracy ◽

Network Architectures ◽

Heartbeat Classification ◽

Ecg Signals ◽

Image Representations ◽

Electrocardiogram Ecg

Abstract Background: Electrocardiogram (ECG) is a method of recording the electrical activity of the heart and provides a diagnostic mean for heart-related diseases. An arrhythmia is any irregularity of heartbeat that causes an abnormality in one’s heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG signal is not sufficient for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to developed computer-aided diagnosis (CAD) systems to automatically identify arrhythmias.Methods: This paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The signals are obtained from MIT-BIH arrhythmia database and are categorized according to five arrhythmia types. The proposed approach identifies arrhythmia classes by using Convolutional Neural Network (CNN) architecture trained by two-dimensional (2D) ECG beat images. CNN architecture is selected due to high image recognition performance. ECG signals are segmented into heartbeats, then each heartbeat is transformed into a 2D grayscale image. The heartbeat images are used as input for the CNN. Results: The proposed CNN model is compared to other common CNN architectures such as LeNet and ResNet-50 to evaluate the performance of our study. Overall, the proposed study achieved 99.7% test accuracy in the classification of five different ECG arrhythmias.Conclusions: Testing results demonstrate that CNN trained by ECG image representations provide outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Hence, the proposed approach provides a robust method for the classification of ECG arrhythmias.

Download Full-text

Increased prevalence of psychosis in patients who get admitted with atrial fibrillation with worse outcomes

European Psychiatry ◽

10.1016/j.eurpsy.2017.01.856 ◽

2017 ◽

Vol 41 (S1) ◽

pp. S575-S576

Author(s):

Z. Mansuri ◽

S. Patel ◽

P. Patel ◽

O. Jayeola ◽

A. Das ◽

...

Keyword(s):

Atrial Fibrillation ◽

Hospital Admissions ◽

Temporal Trends ◽

International Classification Of Diseases ◽

Trend Test ◽

Classification Of Diseases ◽

Competing Interest ◽

Armitage Trend Test ◽

The Impact

ObjectiveTo determine trends and impact on outcomes of atrial fibrillation (AF) in patients with pre-existing psychosis.BackgroundWhile post-AF psychosis has been extensively studied, contemporary studies including temporal trends on the impact of pre-AF psychosis on AF and post-AF outcomes are largely lacking.MethodsWe used Nationwide Inpatient Sample (NIS) from the healthcare cost and utilization project (HCUP) from year's 2002–2012. We identified AF and psychosis as primary and secondary diagnosis respectively using validated international classification of diseases, 9th revision, and Clinical Modification (ICD-9-CM) codes, and used Cochrane–Armitage trend test and multivariate regression to generate adjusted odds ratios (aOR).ResultsWe analyzed total of 3.887.827AF hospital admissions from 2002–2012 of which 1.76% had psychosis. Proportion of hospitalizations with psychosis increased from 5.23% to 14.28% (P trend < 0.001). Utilization of atrial-cardioversion was lower in patients with psychosis (0.76%v vs. 5.79%, P < 0.001). In-hospital mortality was higher in patients with Psychosis (aOR 1.206; 95%CI 1.003–1.449; P < 0.001) and discharge to specialty care was significantly higher (aOR 4.173; 95%CI 3.934–4.427; P < 0.001). The median length of hospitalization (3.13 vs. 2.14 days; P < 0.001) and median cost of hospitalization (16.457 vs. 13.172; P < 0.001) was also higher in hospitalizations with psychosis.ConclusionsOur study displayed an increasing proportion of patients with Psychosis admitted due to AF with higher mortality and extremely higher morbidity post-AF, and significantly less utilization of atrial-cardioversion. There is a need to explore reasons behind this disparity to improve post-AF outcomes in this vulnerable population.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Download Full-text

ECG Beats Classification Using Mixture of Features

International Scholarly Research Notices ◽

10.1155/2014/178436 ◽

2014 ◽

Vol 2014 ◽

pp. 1-12 ◽

Cited By ~ 21

Author(s):

Manab Kumar Das ◽

Samit Ari

Keyword(s):

Feature Extraction ◽

Extraction Methods ◽

Ectopic Beat ◽

Extraction Techniques ◽

Efficient System ◽

Ecg Signals ◽

Temporal Features ◽

S Transform ◽

Electrocardiogram Ecg

Classification of electrocardiogram (ECG) signals plays an important role in clinical diagnosis of heart disease. This paper proposes the design of an efficient system for classification of the normal beat (N), ventricular ectopic beat (V), supraventricular ectopic beat (S), fusion beat (F), and unknown beat (Q) using a mixture of features. In this paper, two different feature extraction methods are proposed for classification of ECG beats: (i) S-transform based features along with temporal features and (ii) mixture of ST and WT based features along with temporal features. The extracted feature set is independently classified using multilayer perceptron neural network (MLPNN). The performances are evaluated on several normal and abnormal ECG signals from 44 recordings of the MIT-BIH arrhythmia database. In this work, the performances of three feature extraction techniques with MLP-NN classifier are compared using five classes of ECG beat recommended by AAMI (Association for the Advancement of Medical Instrumentation) standards. The average sensitivity performances of the proposed feature extraction technique for N, S, F, V, and Q are 95.70%, 78.05%, 49.60%, 89.68%, and 33.89%, respectively. The experimental results demonstrate that the proposed feature extraction techniques show better performances compared to other existing features extraction techniques.

Download Full-text

Classification of cardiac arrhythmias using deep learning

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.33.14195 ◽

2018 ◽

Vol 7 (3.3) ◽

pp. 401

Author(s):

Jeong Hwan Kim ◽

Jeong Whan Lee ◽

Kyeong Seop Kim

Keyword(s):

Deep Learning ◽

Normal Sinus Rhythm ◽

Premature Ventricular Contraction ◽

Heart Rhythm ◽

Future Research ◽

Normal Sinus ◽

Input Layer ◽

Hidden Layer ◽

Electrocardiogram Ecg

Background/Objectives: The main objective of this research is to design Deep Learning (DL) architecture to classify an electrocardiogram (ECG) signal into normal sinus rhythm (NSR), premature ventricular contraction (PVC), atrial premature contraction (APC) or right/left bundle branch block (RBBB/LBBB) arrhythmia by empirically optimizing the numbers of hidden layers, the number of neurons in each hidden layer and the number of neurons in input layer in DL model.Methods/Statistical analysis: For our experimental simulations, PhysioBank-MIT/BIH annotated ECG database was considered to classify heart beats into abnormal rhythms (PVC, APC, RBBB, LBBB) or normal sinus. The performance of classifying ECG beats by the proposed DL architecture was evaluated by computing the overall accuracy of classifying NSR or four different arrhythmias.Findings: Base on testing MIT/BIH arrhythmia database, the proposed DL model can classify the heart rhythm into one of NSR, PVC, APC, RBBB or LBBB beat with the mean accuracy of 95.5% by implementing DL architecture with 200 neurons in input layer, 100 neurons in the first and second hidden layer, respectively and 80 neurons in the 3rd hidden layer.Improvements/Applications: Our experimental results show that the proposed DL model might not be quite accurate for detecting APC beats due to its morphological resemblance of NSR. Therefore, we might need to design more sophisticated DL architecture by including more temporal characteristics of APC to increase the classification accuracy of APC arrhythmia in the future research efforts.

Download Full-text

Impact of Feature Selection on Clustering Images ofVertebral Compression Fractures

10.5753/eniac.2020.12176 ◽

2020 ◽

Author(s):

Raquel Candido ◽

Rafael Lama ◽

Natália Chiari ◽

Marcello Nogueira-Barbosa ◽

Paulo Azevedo Marques ◽

...

Keyword(s):

Feature Selection ◽

Metastatic Cancer ◽

Vertebral Compression Fractures ◽

Features Selection ◽

Correct Classification ◽

Compression Fractures ◽

Vertebral Bodies ◽

The Impact ◽

Aided Diagnosis

Non-traumatic Vertebral Compression Fractures (VCFs) are generally caused by osteoporosis (benign VCFs) or metastatic cancer (malignant VCFs) and the success of the medical treatment strongly depends on a fast and correct classification of VCFs. Recently, methods for computer-aided diagnosis (CAD) based on machine learning have been proposed for classifying VCFs. In this work, we investigate the problem of clustering images of VCFs and the impact of feature selection by genetic algorithms, comparing the clustering i)with all features and ii)with feature selection through the purity results. The analysis of the clusters helps to understand the results of classifiers and difficulties of differentiating images of different classes by an expert. The results indicate that features selection improved the separability of clusters and purity. Feature selection also helps to understand which attributes are most important for analysing the images of vertebral bodies.

Download Full-text

Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review

Information Sciences ◽

10.1016/j.ins.2018.07.063 ◽

2018 ◽

Vol 467 ◽

pp. 99-114 ◽

Cited By ~ 39

Author(s):

Yuki Hagiwara ◽

Hamido Fujita ◽

Shu Lih Oh ◽

Jen Hong Tan ◽

Ru San Tan ◽

...

Keyword(s):

Atrial Fibrillation ◽

Computer Aided Diagnosis ◽

Ecg Signals ◽

Computer Aided ◽

Aided Diagnosis

Download Full-text

A Wearable Electrocardiogram Telemonitoring System for Atrial Fibrillation Detection

Sensors ◽

10.3390/s20030606 ◽

2020 ◽

Vol 20 (3) ◽

pp. 606 ◽

Cited By ~ 3

Author(s):

Minggang Shao ◽

Zhuhuang Zhou ◽

Guangyu Bin ◽

Yanping Bai ◽

Shuicai Wu

Keyword(s):

Atrial Fibrillation ◽

Ecg Monitoring ◽

Web Browser ◽

Ecg Signals ◽

Cloud Server ◽

Android App ◽

Electrocardiogram Ecg ◽

The Web ◽

Ecg Data

In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on a smartphone and cloud computing. A wearable ECG patch was designed to collect ECG signals and send the signals to an Android smartphone via Bluetooth. An Android APP was developed to display the ECG waveforms in real time and transmit every 30 s ECG data to a remote cloud server. A machine learning (CatBoost)-based ECG classification method was proposed to detect AF in the cloud server. In case of detected AF, the cloud server pushed the ECG data and classification results to the web browser of a doctor. Finally, the Android APP displayed the doctor’s diagnosis for the ECG signals. Experimental results showed the proposed CatBoost classifier trained with 17 selected features achieved an overall F1 score of 0.92 on the test set (n = 7270). The proposed wearable ECG monitoring system may potentially be useful for long-term ECG telemonitoring for AF detection.

Download Full-text

Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics

Sensors ◽

10.3390/s19040935 ◽

2019 ◽

Vol 19 (4) ◽

pp. 935 ◽

Cited By ~ 9

Author(s):

Yeong-Hyeon Byeon ◽

Sung-Bum Pan ◽

Keun-Chang Kwak

Keyword(s):

Frequency Domain ◽

Training Transfer ◽

Training Data ◽

Deep Convolutional Neural Networks ◽

Ecg Signals ◽

Electrocardiogram Signals ◽

Noisy Signals ◽

The Time Domain ◽

Electrocardiogram Ecg

This paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted by transforming signals into a frequency domain that is efficient for analyzing noisy signals. By transforming the signal from the time domain to the frequency domain using the wavelet, the 1-D signal becomes a 2-D matrix, and it could be analyzed at multiresolution. However, this process makes signal analysis morphologically complex. This means that existing simple classifiers could perform poorly. We investigate the possibility of using the scalogram of ECG as input to deep convolutional neural networks of deep learning, which exhibit optimal performance for the classification of morphological imagery. When training data is small or hardware is insufficient for training, transfer learning can be used with pretrained deep models to reduce learning time, and classify it well enough. In this paper, AlexNet, GoogLeNet, and ResNet are considered as deep models of convolutional neural network. The experiments are performed on two databases for performance evaluation. Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, while Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The ResNet was 0.73%—0.27% higher than AlexNet or GoogLeNet on PTB-ECG—and the ResNet was 0.94%—0.12% higher than AlexNet or GoogLeNet on CU-ECG.

Download Full-text