Arrhythmia recognition and classification using kernel ICA and higher order spectra

The conventional methodologies of arrhythmia identification are based on morphological features or certain transformation technique. These conventional techniques are partially successful in arrhythmia identification, because it treats heart as a linear structure. In this chapter, ECG based arrhythmia identification is assessed by employing MIT-BIH arrhythmia dataset. The proposed approach contains two major steps: feature extraction and classification. Initially, a combination of non-linear and linear feature extraction is carried-out using Principal Component Analysis, Kernel Independent Component Analysis and Higher Order Spectrum for achieving optimal feature subsets. The linear experiments on ECG data achieves high performance in noise free data and the non-linear experiments distinguish the ECG data more effectively, extract hidden information and also helps to attain better performance under noisy conditions. After finding the feature information, a binary classifier Support Vector Machine is employed for classifying the normality and abnormality of arrhythmia.

Detection and treatment of arrhythmias has become one of the main goals in cardiac care diagnosis provided by general practitioners. Electrocardiogram (ECG) analysis is one of the most commonly used tools to test and diagnose heart problems. Classification of ECG heartbeats enables the identification of specific arrhythmia or other heart conditions. This paper presents and contrasts the results from two effective ECG arrhythmia classification schemes. The first scheme consists of a principal component analysis (PCA) step for feature reduction at the input vector to the classifier, combined with soft independent modelling of class analogy (SIMCA). The second method uses a multi-class support vector machine (MSVM) classifier to differentiate between four different types of arrhythmia from ECG beats. The four types of beats include Normal (N), Premature Ventricular Contraction (PVC), and Atrial premature contraction (APC) and Right Bundle Branch Block Beat (RBBB). The time domain features were obtained from the St Petersburg INCART 12-lead Arrhythmia Database (incartdb). Between 10 and 30 Principal Components (PCs) were selected for reconstructing individual ECG beats and create the input vector to the classifier. The average classification accuracy of the proposed scheme is 76.83% and 98.33% using MSVM and SIMCA classifier respectively. The SIMCA classification algorithm provided better performance than the MSVM classifiers.

Most electrical equipment in the modern operating room (OR) radiates electrical noise (EN) that can interfere with patient monitors. We have described the EN that an intraoperative magnetic resonance imaging (iMRI) system emits and have shown that this high-energy EN diminishes the quality of the ECG waveform during iMRI scans in our neurosurgical OR. We have also shown that the ECG signal filters in our iMRI-compatible patient monitor reduce this interference but, in the process, disturb the true morphology of the displayed waveform. This simulation study evaluates how iMRI-generated EN affects the ability of the anesthetist to detect and identify ECG arrhythmias and whether the patient monitor's ECG signal filters can improve arrhythmia recognition. Using an ECG simulator, we generated Lead II and V5 ECG signal segments that contained either no arrhythmia or one of four common cardiac arrhythmias. We filtered the ECG segments with four filters available on our iMRI-compatible monitor (Veris MR, MEDRAD Inc., Indianola, PA USA). We then digitized the segments and mixed simulated iMRI EN into the resultant tracings. With institutional approval and written informed consent, board-certified anesthesiologists reviewed the tracings, determined if an arrhythmia was present and identified the arrhythmia. We conducted the study anonymously. We reported the data as percent correct arrhythmia detection and correct arrhythmia identification. Thirty-one anesthesiologists completed the study. Overall, the participants correctly detected 79.5% (95% CI: 77.2, 81.7%) of the arrhythmias and correctly identified 62.5% (95% CI: 59.8, 65.3%) of the arrhythmias, regardless of EN presence. Although the proportions among monitor noise filters studied were not significant, the manufacturer-designated MR5 Veris MR filter optimized arrhythmia detection and arrhythmia identification for our participants, regardless if EN was present in the ECG tracings. In the neurosurgical OR, the anesthetist must be able to effectively monitor a patient in the presence of iMRI-generated EN. Depending on the OR design, the patient may be out of the anesthetist's direct view during a scan procedure. The anesthetist must rely on monitored physiologic parameters to assess patient status during this time. He/she should be familiar with his/her monitor's filtering capabilities and routinely adjust the ECG filters to achieve the best compromise between minimized EN effects and maximized displayed ECG signal quality.

In many medical applications, feature selection is obvious; but in medical domains, selecting features and creating a feature vector may require more effort. The wavelet transform (WT) technique is used to identify the characteristic points of an electrocardiogram (ECG) signal with fairly good accuracy, even in the presence of severe high-frequency and low-frequency noise. Principal component analysis (PCA) is a suitable technique for ECG data analysis, feature extraction, and image processing — an important technique that is not based upon a probability model. The aim of the paper is to derive better diagnostic parameters for reducing the size of ECG data while preserving morphology, which can be done by PCA. In this analysis, PCA is used for decorrelation of ECG signals, noise, and artifacts from various raw ECG data sets. The aim of this paper is twofold: first, to describe an elegant algorithm that uses WT alone to identify the characteristic points of an ECG signal; and second, to use a composite WT-based PCA method for redundant data reduction and better feature extraction. PCA scatter plots can be observed as a good basis for feature selection to account for cardiac abnormalities. The study is analyzed with higher-order statistics, in contrast to the conventional methods that use only geometric characteristics of feature waves and lower-order statistics. A new algorithm — viz. PCA variance estimator — is developed for this analysis, and the results are also obtained for different combinations of leads to find correlations for feature classification and useful diagnostic information. PCA scatter plots of various chest and augmented ECG leads are obtained to examine the varying orientations of the ECG data in different quadrants, indicating the cardiac events and abnormalities. The efficacy of the PCA algorithm is tested on different leads of 12-channel ECG data; file no. 01 of the Common Standards for Electrocardiography (CSE) database is used for this study. Better feature extraction is obtained for some specific combinations of leads, and significant improvement in signal quality is achieved by identifying the noise and artifact components. The quadrant analysis discussed in this paper highlights the filtering requirements for further ECG processing after performing PCA, as a primary step for decorrelation and dimensionality reduction. The values of the parameters obtained from the results of PCA are also compared with those of wavelet methods.

The purpose of this paper is to develop an intelligent algorithm by integrating the Kernel Independent Component Analysis (KICA) and the Support Vector Machines (SVM) for forecasting the steel temperature. Characterized by nonlinearity, multivariable, coupling of the heating furnace, it is necessary to feature extraction. Thus, this study proposes the application of KICA to extract the hidden information of process before conducting LSSVM. An application study is carried out on the real production data acquired from a steel-making plant. Results demonstrate that the proposed method possesses superior accuracy when compared to conventional methods, including SVM, KICA-SVM and KICA-LSSVM.

Hierarchical deep learning with Generative Adversarial Network for automatic cardiac diagnosis from ECG signals

Machine learning and the electrocardiogram over two decades: Time series and meta-analysis of the algorithms, evaluation metrics and applications

Objective. Automatic detection of arrhythmia based on electrocardiogram (ECG) plays a critical role in early prevention and diagnosis of cardiovascular diseases. With the increase in widely available digital ECG data and the development of deep learning, multi-class arrhythmia classification based on automatic feature extraction of ECG has become increasingly attractive. However, the majority of studies cannot accept varied-length ECG signals and have limited performance in detecting multi-class arrhythmias. Approach. In this study, we propose a multi-branch signal fusion network (MBSF-Net) for multi-label classification of arrhythmia in 12-lead varied-length ECG. Our model utilizes the complementary power between different structures, which include Inception with depthwise separable convolution (DWS-Inception), spatial pyramid pooling (SPP) Layer, and multi-scale fusion Resnet (MSF-Resnet). The proposed method can extract features from each lead of 12-lead ECG recordings separately and then effectively fuse the features of each lead by integrating multiple convolution kernels with different receptive fields, which can achieve the information of complementation between different angles of the ECG signal. In particular, our model can accept 12-lead ECG signals of arbitrary length. Main results. The experimental results show that our model achieved an overall classification F1 score of 83.8% in the 12-lead ECG data of CPSC-2018. In addition, the F1 score of the MBSF-Net performed best among the MBF-Nets which are removed the SPP layer from MBSF-Net. In comparison with the latest ECG classification algorithms, the proposed model can be applied in varied-length signals and has an excellent performance, which not only can fully retain the integrity of the original signals, but also eliminates the cropping/padding signal beforehand when dealing with varied-length signal database. Significance. MBSF-Net provides an end-to-end multi-label classification model with outperfom performance, which allows detection of disease in varied-length signals without any additional cropping/padding. Moreover, our research is beneficial to the development of computer-aided diagnosis.

Heart arrhythmia is a condition in which the heartbeat is too fast, too slow, or irregular. As Electrocardiography (ECG) is an efficient measurement of heart arrhythmia, lots of research efforts have been spent on the identification of heart arrhythmia by classifying ECG signals for health care. Among them, support vector machines (SVMs) and artificial neural networks (ANNs) are the most popular. However, most of the previous studies reported the performance of either the SVMs or the ANNs without in-depth comparisons between these two methods. Also, a large number of features can be extracted from ECG signals, and some may be more relevant to heart arrhythmia than the others. This paper is to enhance the performance of heart arrhythmia classification by selecting relevant features from ECG signals, applying dimension reduction on the feature vectors, and applying deep neural networks (DNNs) for classification. A holistic comparison among DNNs, SVMs, and ANNs will be provided. Experimental results suggest that DNNs outperform both SVMs and ANNs, provided that relevant features have been selected.

Due to the high sampling rate, the recorded Electrocardiograms (ECG) data are huge. For storing and transmitting ECG data, wide spaces and more bandwidth are therefore needed. The ECG data are also very important to preprocessing and compress so that it is distributed and processed with less bandwidth and less space effectively. This manuscript is aimed at creating an effective ECG compression method. The reported ECG data are processed first in the pre-processing unit (ProUnit) in this method. In this unit, ECG data have been standardized and segmented. The resulting ECG data would then be sent to the Compression Unit (CompUnit). The unit consists of an algorithm for lossy compression (LosyComp), with a lossless algorithm for compression (LossComp). The randomness ECG data is transformed into high randomness data by the failure compression algorithm. The data's high redundancy is then used with the LosyComp algorithm to reach a high compression ratio (CR) with no degradation. The LossComp algorithms recommended in this manuscript are the Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT). LossComp algorithms such as Arithmetic Encoding (Arithm) and Run Length Encoding (RLE) are also suggested. To evaluate the proposed method, we measure the Compression Time (CompTime), and Reconstruction Time (RecTime) (T), RMSE and CR. Simulation results suggest the highest output in compression ratio and in complexity by adding RLE after the DCT algorithm. The simulation findings indicate that the inclusion of RLE following the DCT algorithm increases performance in terms of CR and complexity. With CR = 55% with RMSE = 0:14 and above 94% with RMSE = 0:2, DCT as a LossComp algorithm was utilized initially, followed by RLE as a LossComp algorithm.

To determine viability of drowsiness detection, researchers study the feasibility of photoplethysmogram (PPG) data collection from the geography of the aviation headset, correlating to electrocardiogram (ECG) reference. Fatigue has been a probable cause, contributing factor, or a finding in 20% of transportation incidents and accidents studied between January 2001 and December 2012. This operational hazard is particularly troublesome within aviation and airline operations. PPG and ECG data were collected synchronously from Federal Aviation Administration (FAA) commercially rated pilots during flight simulation in the window of circadian low (WOCL). Valid PPG and ECG data from 14 participants were analyzed, which yielded approximately 2 hr of data per participant for fatigue-related analysis. The results of the study demonstrate clear trends toward decreased heart rate for both ECG and PPG and suggest progression of drowsiness between four separate periods (T1, T2, T3, and T4) selected during the study; however, the mean heart rate change from T1 to T4 was statistically significant. The results suggest that ECG and PPG data can be an important tool to observe conditions where drowsiness or fatigue may add risk to the operation. In addition, the data show high correlation between ECG and PPG data, further suggesting that a simpler PPG sensor, mounted within the geography of the aviation headset, may streamline the operationalization of important physiological data. Incorporation of PPG sensors and associated signal processing methods into facilitating equipment, such as the aviation headset, may add a layer to operational safety.

Simultaneous Monitoring of ECG and EDA Using a Wearable Armband for Analyzing Sympathetic Nerve Activity

The Electrocardiogram (ECG) is commonly used to detect arrhythmias. Traditionally, a single ECG observation is used for diagnosis, making it difficult to detect irregular arrhythmias. Recent technology developments, however, have made it cost-effective to collect large amounts of raw ECG data over time. This promises to improve diagnosis accuracy, but the large data volume presents new challenges for cardiologists. This paper introduces ECGLens, an interactive system for arrhythmia detection and analysis using large-scale ECG data. Our system integrates an automatic heartbeat classification algorithm based on convolutional neural network, an outlier detection algorithm, and a set of rich interaction techniques. We also introduce A-glyph, a novel glyph designed to improve the readability and comparison of ECG signals. We report results from a comprehensive user study showing that A-glyph improves the efficiency in arrhythmia detection, and demonstrate the effectiveness of ECGLens in arrhythmia detection through two expert interviews.

Owing to a lack of easy access to an individual's electrocardiogram (ECG) data that may be distributed across multiple hospitals, medical practice using serial ECG analysis has not so far been extensively used. Motivated to address this problem, we design and implement an architecture for cross-hospital access to ECG data. The architecture provides a Web portal for retrieving a particular patient's ECG data distributed across a number of ECG data sources. Two important features of this architecture are (1) the distributed search mechanism that uses a master patient index to determine what ECG data sources are likely to contain the ECG data pertaining to a specified patient and (2) the Web service-based interoperable method for accessing disparate ECG data sources. We show that the architecture provides an effective search and retrieval facility for cross-hospital access to ECG data; we show this by implementing and employing a prototype in an experimental scenario consisting of two disparate ECG data sources located at two sites. Our study demonstrates a significant effort to improve the ease of cross-hospital access to ECG data.

Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): ITEA. Background Accurate detection of myocardial ischemia and arrhythmia’s during free-living exercise could play a pivotal role in optimizing screening and monitoring of individuals with underlying cardiovascular disease. Although remote electrocardiogram (ECG) solutions are emerging rapidly, these applications are generally not designed nor validated for continuous use during vigorous exercise. Purpose In this proof-of-concept study, we evaluated the usability, signal quality and arrhythmia detection of a new self-adhesive dry electrode ECG patch, the Nighthawk Vital Signs patch, during exercise and prolonged continuous ECG monitoring in individuals with chronic coronary syndrome (CCS). Methods Six consecutive CCS patients scheduled for an exercise stress test as part of routine cardiac follow-up were recruited. The traditional 12-lead exercise ECG was combined with monitoring with the 1-lead patch. Following the exercise test, the subjects continuously wore the sensor for five days. Intraclass correlation coefficients (ICC) and Wilcoxon signed-rank tests were used to assess the utility to detect arrhythmias with the patch. Signal quality for ECG recording was evaluated by using a signal quality indicator (SQI) based on the average QRS complex. Connection time and signal-to-noise ratio (SNR) were additionally calculated for prolonged ECG monitoring. Comfort and usability of the patch were evaluated by an online questionnaire. Results Six male patients with CCS (mean age 69.8 ± 6.2 years) completed the protocol. The mean time the patch was worn, was 118.3 hours (SD 5.6). The level of agreement between the patch and the 12-lead ECG was excellent for amount of premature atrial contractions (PAC’s) and premature ventricular contractions (PVC’s) during exercise stage, recovery stage and total test duration (ICC = 0.998, 0.998, 1.000, 1.000, 0.998, 1.000). There were no significant differences in the total amount of PAC’s and PVC’s detected with both methods during the exercise test (p = 0.785 and 0.180, respectively). One episode of atrial fibrillation was detected identically on both recorded ECG’s. Signal quality based on average QRS SQI during exercise did decrease slightly during (sub)maximal effort. Total connection time during recording was above 88% in all subjects and the SNR was above the target limit of 18dB. There were no reports on skin irritation, erythema or pain. Conclusion The Nighthawk Vital Signs ECG patch based on self-adhesive dry electrodes technology can be used for accurate arrhythmia detection during vigorous exercise. The sensor is also usable for prolonged ECG monitoring in free-living conditions and can therefore be of potential use in cardiac rehabilitation and telemonitoring for prevention of exercise-related cardiovascular events. However, more research is needed in order to analyze the signal quality over time together with a larger-scale validation study focusing on both arrhythmia and ischemia detection.