Ambulatory Electrocardiogram Signals Research Articles

QTNet: Deep Learning for Estimating QT Intervals Using a Single Lead ECG.

QT prolongation often leads to fatal arrhythmia and sudden cardiac death. Antiarrhythmic drugs can increase the risk of QT prolongation and therefore require strict post-administration monitoring and dosage control. Measurement of the QT interval from the 12-lead electrocardiogram (ECG) by a trained expert, in a clinical setting, is the accepted method for tracking QT prolongation. Recent advances in wearable ECG technology, however, raise the possibility of automated out-of-hospital QT tracking. Applications of Deep Learning (DL) - a subfield within Machine Learning - in ECG analysis holds the promise of automation for a variety of classification and regression tasks. In this work, we propose a residual neural network, QTNet, for the regression of QT intervals from a single lead (Lead-I) ECG. QTNet is trained in a supervised manner on a large ECG dataset from a U.S. hospital. We demonstrate the robustness and generalizability of QTNet on four test-sets; one from the same hospital, one from another U.S. hospital, and two public datasets. Over all four datasets, the mean absolute error (MAE) in the estimated QT interval ranges between 9ms and 15.8ms. Pearson correlation coefficients vary between 0.899 and 0.914. By contrast, QT interval estimation on these datasets with a standard method for automated ECG analysis (NeuroKit2) yields MAEs between 22.29ms and 90.79ms, and Pearson correlation coefficients 0.345 and 0.620. These results demonstrate the utility of QTNet across distinct datasets and patient populations, thereby highlighting the potential utility of DL models for ubiquitous QT tracking.Clinical Relevance- QTNet can be applied to inpatient or ambulatory Lead-I ECG signals to track QT intervals. The method facilitates ambulatory monitoring of patients at risk of QT prolongation.

Development and Optimization of Silicon-Dioxide-Coated Capacitive Electrode for Ambulatory ECG Measurement System.

This paper presents a silicon-dioxide-coated capacitive electrode system for an ambulatory electrocardiogram (ECG). The electrode was coated with a nano-leveled (287 nm) silicon dioxide layer which has a very high resistance of over 200 MΩ. Due to this high resistance, the electrode can be defined as only a capacitor without a resistive characteristic. This distinct capacitive characteristic of the electrode brings a simplified circuit analysis to achieve the development of a high-quality ambulatory ECG system. The 240 um thickness electrode was composed of a stainless-steel sheet layer for sensing, a polyimide electrical insulation layer, and a copper sheet connected with the ground to block any electrical noises generated from the back side of the structure. Six different diameter electrodes were prepared to optimize ECG signals in ambulatory environment, such as the amplitude of the QRS complex, amplitude of electromagnetic interference (EMI), and baseline wandering of the ECG signals. By combining the experimental results, optimal ambulatory ECG signals were obtained with electrodes that have a diameter from 1 to 3 cm. Moreover, we achieved high-quality ECG signals in a sweating simulation environment with 2 cm electrodes.

Optimising and validating deep learning approaches for diagnosing atrial fibrillation from few-lead ambulatory electrocardiogram signals

Abstract Funding Acknowledgements Type of funding sources: None. Background Deep learning (DL) has received much attention as a solution for automatically diagnosing atrial fibrillation (AF) from raw ECG signals. However, few studies exist to investigate how DL approaches can be optimally configured and whether their diagnostic performance is externally validated. Purpose To explore how signal-related parameter tuning affects the ability of DL approaches to diagnose AF and validate the optimal approach internally and externally. Methods We applied two dedicated DL models (InceptionTime and MINIROCKET) on a set of 7,966 AF and non-AF (normal or with other abnormalities) ambulatory ECG samples, originating from the MIT-BIH AF, MIT-BIH Normal Sinus Rhythm and Long Term AF databases. We tested the effect of different sample lengths (30sec (s), 10s, 30/10s -30s with a "sliding window" of 10s-), sampling frequencies (200, 100, 50 Hz) and lead numbers (two-, single-), and the role of denoising (Discrete Wavelet Transformation, no denoising) on the ability to diagnose AF, by measuring ROC AUC and sensitivity (SEN) after repeated model training and testing. Under the optimal configuration, we trained 10 replicas of both models on 90% of the data and tested their performance on the remaining 10% (internal validation). Finally, we applied both pre-trained models on a separate dataset (MIT-BIH Arrhythmia) to determine their external validity. Results Although the diagnostic performance did not differ between 30s and 10s signals, the 30/10s setting displayed significantly higher median AUC (0.98) and sensitivity (97.3%, p<0.05 for all comparisons). Signals sampled at 50Hz performed poorer (AUC=0.88, SEN=79.9%) than those at 100Hz (AUC=0.92, SEN=88.7%) and 200Hz (AUC=0.93, SEN=89.2%), although this difference slightly failed to reach statistical significance. Despite denoised signals showing a higher median AUC (0.95 vs. 0.92) and sensitivity (92.8% vs. 88.7%), the difference was not found significant. Similarly, two-lead signals performed better than single-lead ones (AUC=0.92 vs. 0.9 and SEN=88.7% vs. 84.1%, respectively), but without crossing the significance threshold. The internal validation with denoised, 30/10s, two-lead signals, at 100Hz, yielded similarly high performance metrics for both InceptionTime and MINIROCKET (AUC=0.98, SEN=96.9% and AUC=0.98, SEN=97.4%, respectively). In contrast, the performance on the external set dropped significantly (AUC=0.79, SEN=81.4% and AUC=0.72, SEN=83.7%, respectively, p<0.001 for all comparisons). Conclusions Both DL approaches can effectively detect AF in ambulatory ECG signals, with only 3 out of 100 cases missed, designating their promising utility as screening tools for automated AF detection. While optimising tunable parameters can enhance the internal performance of such efforts, their external validation is necessary to establish their robustness "in the wild", since their performance on "unseen" data can be, similarly to our case, notably lower.

An Automatic Method to Reduce Baseline Wander and Motion Artifacts on Ambulatory Electrocardiogram Signals.

Today’s wearable medical devices are becoming popular because of their price and ease of use. Most wearable medical devices allow users to continuously collect and check their health data, such as electrocardiograms (ECG). Therefore, many of these devices have been used to monitor patients with potential heart pathology as they perform their daily activities. However, one major challenge of collecting heart data using mobile ECG is baseline wander and motion artifacts created by the patient’s daily activities, resulting in false diagnoses. This paper proposes a new algorithm that automatically removes the baseline wander and suppresses most motion artifacts in mobile ECG recordings. This algorithm clearly shows a significant improvement compared to the conventional noise removal method. Two signal quality metrics are used to compare a reference ECG with its noisy version: correlation coefficients and mean squared error. For both metrics, the experimental results demonstrate that the noisy signal filtered by our algorithm is improved by a factor of ten.

A multi-stage denoising framework for ambulatory ECG signal based on domain knowledge and motion artifact detection

Electrocardiogram (ECG) acquired by wearable devices is increasingly used for healthcare applications. However, the ECG signals are severely corrupted by various noises (e.g. baseline wander and motion artifacts) in daily activities, resulting in unreliable or wrong detection of heart problems and hindering the automatic ECG analysis. Because of the overlap of different kinds of noises in the time and frequency domains, noise removal is a difficult task for ambulatory ECG signals. Especially, motion artifacts with variable frequencies and amplitudes pose a great challenge to ECG denoising. To address this problem, we propose a multi-stage ECG denoising framework concentrating on the detection of motion artifact based on domain knowledge. In the framework, motion artifact candidates are first located by noise-adaptive thresholding. Then we use multiple metrics combined with decision rules to find actual motion artifacts and suppress them by local scaling and morphological filtering. The complete ensemble empirical mode decomposition (CEEMD) and wavelet transform are employed to remove baseline wander and high-frequency noise, respectively. The proposed method is evaluated on the MIT-BIH arrhythmia database, the TELE database, and the Sport database. The results on the MIT-BIH database show that the proposed method achieved statistically significant improvement of signal-to-noise ratio (SNR) ranging from 7% to 25% compared with other approaches. The results also demonstrate that the proposed method effectively suppressed QRS-like motion artifacts and hence decreased false positives generated by the QRS detector, which is important for clinical diagnosis.

Motion Artifact Removal in Ambulatory ECG Signal for Heart Rate Variability Analysis

This work presents an efficient method for motion artifact removal from ambulatory electrocardiogram (ECG) signal for heart rate variability (HRV) in wearable/portable healthcare devices. HRV is the fluctuation in the time interval between the adjacent heartbeats. Motion artifacts affect HRV analysis by creating some outliers. A two-phase method using stationary wavelet transform with level thresholding (SWT-LT) is used to remove motion artifact from the ECG signal. Multi-channel system prototype is used for ambulatory ECG signal recording which is developed using commercial integrated circuit components. Motion artifact affected ECG signals are recorded by emulating daily activity movements. Recorded ECG database (60 signals) and Motion Artifact Contaminated ECG Database (27 signals) are used for validation of the proposed SWT-LT method. Implemented results show that the proposed SWT-LT method removes various in-band motion artifacts efficiently with an average correlation coefficient of 0.9337 and an average normalized mean square error of 0.012 which are better than the other reported methods. The proposed method has shown improvement in features of HRV analysis by removing outliers due to motion artifact from the ECG signal which is verified using MATLAB app HRVTool 1.03 developed by Marcus Vollmer.

Cancellation of motion artifacts in ambulatory ECG signals using TD-LMS adaptive filtering techniques

Wearable electrocardiogram (ECG) measurement systems have been widely used in patients with CVD (Cardiovascular Disease) which can be worn in daily lives. However, currently the main problem is motion artifact interference, and reducing motion artifacts (MA) is one of the most challenging problems encountered in the filtering and processing of physiological signals. In this paper, by analyzing the spectral energy changes during the input process of motion artifacts, a cosine transform LMS adaptive cancellation algorithm (DCT-LMS) implementation is proposed aiming to remove the motion artifacts from the ECG. In order to study the performance of the algorithm and effectively remove the motion artifacts in the ECG signal, this thesis collects ECG signals of people's daily activities from fabric-based chest straps with dry electrodes. It verifies the classic LMS adaptive elimination algorithm and the normalized one. Besides, two LMS adaptive cancellation algorithms based on sine and cosine transform are compared. The simulation and experimental results show that the cosine-based adaptive algorithm is superior to the classical LMS algorithm in eliminating high-amplitude motion artifact noise of ECG.

Physical activities recognition from ambulatory ECG signals using neuro-fuzzy classifiers and support vector machines

The use of wearable recorders for long-term monitoring of physiological parameters has increased in the last few years. The ambulatory electrocardiogram (A-ECG) signals of five healthy subjects with four body movements or physical activities (PA)—left arm up down, right arm up down, waist twisting and walking—have been recorded using a wearable ECG recorder. The classification of these four PAs has been performed using neuro-fuzzy classifier (NFC) and support vector machines (SVM). The PA classification is based on the distinct, time-frequency features of the extracted motion artifacts contained in recorded A-ECG signals. The motion artifacts in A-ECG signals have been separated first by the discrete wavelet transform (DWT) and the time–frequency features of these motion artifacts have then been extracted using the Gabor transform. The Gabor energy feature vectors have been fed to the NFC and SVM classifiers. Both the classifiers have achieved a PA classification accuracy of over 95% for all subjects.

Design and Implementation of Digital Filters for Mobile Healthcare Applications

Digital filtering process is often necessary to suppress the noisy characteristics embedded in biomedical signals such as ECG (Electrocardiogram), EEG (Electroencephalogram), and EMG (Electromyogram). As the availability and usage levels of Information and Communication Technology (ICT) increases, the applications of ubiquitous healthcare are expected to be accelerated in the form of pervasive healthcare utilizing the mobile devices for the next decade. One of these aspects, ambulatory ECG signals can be transmitted to a mobile device to offer telecardiology healthcare delivery. However the signal is vulnerable to base-line drift and power-line source fluctuations. With this aim, the digital filtering algorithms are implemented with an android platform smartphone to eliminate the noisy components especially in the ECG signal transmitted wirelessly from the wearable patch-style heart activity monitoring system. Graphical User Interface (GUI) is designed and implemented in an Android OS smartphone with programming multi-thread- Java modules to realize FIR (Finite Impulse Response Filter) and IIR (Infinite Impulse Response Filter). With applying our implemented digital filters built in a mobile device, we can conclude the fact that the artifacts in the ambulatory ECG signal due to base-line wandering and power- line instability can be efficiently reduced. 

스마트폰 연동 생체신호 왜곡보정을 위한 디지털 필터 설계 및 구현

In this study, the novel digital filtering algorithms are implemented to suppress the noisy characteristics embedded in ambulatory electrocardiogram signals by an android smartphone platform. With this aim, Graphical User Interface (GUI) is designed and implemented by utilizing multithread-Java programming to realize Finite Impulse Response and Infinite Impulse Response filter. With simulating our implemented digital filters built in an android smartphone, we can find the fact that we can efficiently suppresses the noisy characteristics due to baseline wandering and 60 Hz powerline source fluctuations especially in electrocardiograms.

A wavelet-based ECG delineation algorithm for 32-bit integer online processing

BackgroundSince the first well-known electrocardiogram (ECG) delineator based on Wavelet Transform (WT) presented by Li et al. in 1995, a significant research effort has been devoted to the exploitation of this promising method. Its ability to reliably delineate the major waveform components (mono- or bi-phasic P wave, QRS, and mono- or bi-phasic T wave) would make it a suitable candidate for efficient online processing of ambulatory ECG signals. Unfortunately, previous implementations of this method adopt non-linear operators such as root mean square (RMS) or floating point algebra, which are computationally demanding.MethodsThis paper presents a 32-bit integer, linear algebra advanced approach to online QRS detection and P-QRS-T waves delineation of a single lead ECG signal, based on WT.ResultsThe QRS detector performance was validated on the MIT-BIH Arrhythmia Database (sensitivity Se = 99.77%, positive predictive value P+ = 99.86%, on 109010 annotated beats) and on the European ST-T Database (Se = 99.81%, P+ = 99.56%, on 788050 annotated beats). The ECG delineator was validated on the QT Database, showing a mean error between manual and automatic annotation below 1.5 samples for all fiducial points: P-onset, P-peak, P-offset, QRS-onset, QRS-offset, T-peak, T-offset, and a mean standard deviation comparable to other established methods.ConclusionsThe proposed algorithm exhibits reliable QRS detection as well as accurate ECG delineation, in spite of a simple structure built on integer linear algebra.

Semia: semi-automatic interactive graphic editing tool to annotate ambulatory ECG records.

We designed and developed a special purpose interactive graphic editing tool semi-automatic (Semia) to annotate transient ischaemic ST segment episodes and other non-ischaemic ST segment events in 24h ambulatory electrocardiogram (ECG) records. The tool allows representation and viewing of the data, interaction with the data globally and locally at different resolutions, examining data at any point, manual adjustment of heart-beat fiducial points, and manual and automatic editing of annotations. Efficient and fast display of ambulatory ECG signal waveforms, display of diagnostic and morphology feature-vector time-series, dynamic interface controls, and automated procedures to help annotate, made the tool efficient, user friendly and usable. Human expert annotators used the Semia tool to successfully annotate the Long-Term ST database (LTST DB), a result of a multinational effort. The tool supported paperless editing of annotations at dislocated geographical sites. We present design, characteristic "look and feel", functionality, and development of Semia annotating tool.