XYZ data interpreted by a 12-lead computer program using the derived electrocardiogram

Myocardial infarction detection using ITD, DWT and deterministic learning based on ECG signals

Nowadays, cardiovascular diseases (CVD) is one of the prime causes of human mortality, which has received tremendous and elaborative research interests regarding the prevention issue. Myocardial ischemia is a kind of CVD which will lead to myocardial infarction (MI). The diagnostic criterion of MI is supplemented with clinical judgement and several electrocardiographic (ECG) or vectorcardiographic (VCG) programs. However the visual inspection of ECG or VCG signals by cardiologists is tedious, laborious and subjective. To overcome such disadvantages, numerous MI detection techniques including signal processing and artificial intelligence tools have been developed. In this study, we propose a novel technique for automatic detection of MI based on disparity of cardiac system dynamics and synthesis of the standard 12-lead and Frank XYZ leads. First, 12-lead ECG signals are synthesized with Frank XYZ leads to build a hybrid 4-dimensional cardiac vector, which is decomposed into a series of proper rotation components (PRCs) by using the intrinsic time-scale decomposition (ITD) method. The novel cardiac vector may fully reflect the pathological alterations provoked by MI and may be correlated to the disparity of cardiac system dynamics between healthy and MI subjects. ITD is employed to measure the variability of cardiac vector and the first PRCs are extracted as predominant PRCs which contain most of the cardiac vector's energy. Second, four levels discrete wavelet transform with third-order Daubechies (db3) wavelet function is employed to decompose the predominant PRCs into different frequency bands, which combines with three-dimensional phase space reconstruction to derive features. The properties associated with the cardiac system dynamics are preserved. Since the frequency components above 40 Hz are lack of use in ECG analysis, in order to reduce the feature dimension, the advisable sub-band (D4) is selected for feature acquisition. Third, neural networks are then used to model, identify and classify cardiac system dynamics between normal (healthy) and MI cardiac vector signals. The difference of cardiac system dynamics between healthy control and MI cardiac vector is computed and used for the detection of MI based on a bank of estimators. Finally, experiments are carried out on the PhysioNet PTB database to assess the effectiveness of the proposed method, in which conventional 12-lead and Frank XYZ leads ECG signal fragments from 148 patients with MI and 52 healthy controls were extracted. By using the tenfold cross-validation style, the achieved average classification accuracy is reported to be 98.20%. Results verify the effectiveness of the proposed method which can serve as a potential candidate for the automatic detection of MI in the clinical application.

Review of Processing Pathological Vectorcardiographic Records for the Detection of Heart Disease

Vectorcardiography (VCG) is another useful method that provides us with useful spatial information about the electrical activity of the heart. The use of vectorcardiography in clinical practice is not common nowadays, mainly due to the well-established 12-lead ECG system. However, VCG leads can be derived from standard 12-lead ECG systems using mathematical transformations. These derived or directly measured VCG records have proven to be a useful tool for diagnosing various heart diseases such as myocardial infarction, ventricular hypertrophy, myocardial scars, long QT syndrome, etc., where standard ECG does not achieve reliable accuracy within automated detection. With the development of computer technology in recent years, vectorcardiography is beginning to come to the forefront again. In this review we highlight the analysis of VCG records within the extraction of functional parameters for the detection of heart disease. We focus on methods of processing VCG functionalities and their use in given pathologies. Improving or combining current or developing new advanced signal processing methods can contribute to better and earlier detection of heart disease. We also focus on the most commonly used methods to derive a VCG from 12-lead ECG.

Classification of myocardial infarction based on hybrid feature extraction and artificial intelligence tools by adopting tunable-Q wavelet transform (TQWT), variational mode decomposition (VMD) and neural networks

Cardiovascular diseases (CVD) is the leading cause of human mortality and morbidity around the world, in which myocardial infarction (MI) is a silent condition that irreversibly damages the heart muscles. Currently, electrocardiogram (ECG) is widely used by the clinicians to diagnose MI patients due to its inexpensiveness and non-invasive nature. Pathological alterations provoked by MI cause slow conduction by increasing axial resistance on coupling between cells. This issue may cause abnormal patterns in the dynamics of the tip of the cardiac vector in the ECG signals. However, manual interpretation of the pathological alternations induced by MI is a time-consuming, tedious and subjective task. To overcome such disadvantages, computer-aided diagnosis techniques including signal processing and artificial intelligence tools have been developed. In this study we propose a novel technique for automatic detection of MI based on hybrid feature extraction and artificial intelligence tools. Tunable quality factor (Q-factor) wavelet transform (TQWT), variational mode decomposition (VMD) and phase space reconstruction (PSR) are utilized to extract representative features to form cardiac vectors with synthesis of the standard 12-lead and Frank XYZ leads. They are combined with neural networks to model, identify and detect abnormal patterns in the dynamics of cardiac system caused by MI. First, 12-lead ECG signals are reduced to 3-dimensional VCG signals, which are synthesized with Frank XYZ leads to build a hybrid 4-dimensional cardiac vector. Second, this vector is decomposed into a set of frequency subbands with a number of decomposition levels by using the TQWT method. Third, VMD is employed to decompose the subband of the 4-dimensional cardiac vector into different intrinsic modes, in which the first intrinsic mode contains the majority of the cardiac vector's energy and is considered to be the predominant intrinsic mode. It is selected to construct the reference variable for analysis. Fourth, phase space of the reference variable is reconstructed, in which the properties associated with the nonlinear cardiac system dynamics are preserved. Three-dimensional (3D) PSR together with Euclidean distance (ED) has been utilized to derive features, which demonstrate significant difference in cardiac system dynamics between normal (healthy) and MI cardiac vector signals. Fifth, cardiac system dynamics can be modeled and identified using neural networks, which employ the ED of 3D PSR of the reference variable as the input features. The difference of cardiac system dynamics between healthy control and MI cardiac vector is computed and used for the detection of MI based on a bank of estimators. Finally, data sets, which include conventional 12-lead and Frank XYZ leads ECG signal fragments from 148 patients with MI and 52 healthy controls from PTB diagnostic ECG database, are used for evaluation. By using the 10-fold cross-validation style, the achieved average classification accuracy is reported to be 97.98%. Currently, ST segment evaluation is one of the major and traditional ways for the MI detection. However, there exist weak or even undetectable ST segments in many ECG signals. Since the proposed method does not rely on the information of ST waves, it can serve as a complementary MI detection algorithm in the intensive care unit (ICU) of hospitals to assist the clinicians in confirming their diagnosis. Overall, our results verify that the proposed features may satisfactorily reflect cardiac system dynamics, and are complementary to the existing ECG features for automatic cardiac function analysis.

Extracting cardiac dynamics within ECG signal for human identification and cardiovascular diseases classification

Cardiac characteristics underlying the time/frequency domain features are limited and not comprehensive enough to reflect the temporal/dynamical nature of ECG patterns. This paper proposes a dynamical ECG recognition framework for human identification and cardiovascular diseases classification via a dynamical neural learning mechanism. The proposed method consists of two phases: a training phase and a test phase. In the training phase, cardiac dynamics within ECG signals is extracted (approximated) accurately by using radial basis function (RBF) neural networks through deterministic learning mechanism. The obtained cardiac system dynamics is represented and stored in constant RBF networks. An ECG signature is then derived from the extracted cardiac dynamics along the periodic ECG state trajectories. A bank of estimators is constructed using the extracted cardiac dynamics to represent the trained gait patterns. In the test phase, recognition errors are generated and taken as the similarity measure by comparing the cardiac dynamics of the trained ECG patterns and the dynamics of the test ECG pattern. Rapid recognition of a test ECG pattern begins with measuring the state of test pattern, and automatically proceeds with the evolution of the recognition error system. According to the smallest error principle, the test ECG pattern can be rapidly recognized. This kind of cardiac dynamics information represents the beat-to-beat temporal change of ECG modifications and the temporal/dynamical nature of ECG patterns. Therefore, the amount of discriminability provided by the cardiac dynamics is larger than the original signals. This paper further discusses the extension of the proposed method for cardiovascular diseases classification. The constructed recognition system can distinguish and assign dynamical ECG patterns to predefined classes according to the similarity of cardiac dynamics. Experiments are carried out on the FuWai and PTB ECG databases to demonstrate the effectiveness of the proposed method.

A Review of Automated Methods for Detection of Myocardial Ischemia and Infarction Using Electrocardiogram and Electronic Health Records

There is a growing body of research focusing on automatic detection of ischemia and myocardial infarction (MI) using computer algorithms. In clinical settings, ischemia and MI are diagnosed using electrocardiogram (ECG) recordings as well as medical context including patient symptoms, medical history, and risk factors-information that is often stored in the electronic health records. The ECG signal is inspected to identify changes in the morphology such as ST-segment deviation and T-wave changes. Some of the proposed methods compute similar features automatically while others use nonconventional features such as wavelet coefficients. This review provides an overview of the methods that have been proposed in this area, focusing on their historical evolution, the publicly available datasets that they have used to evaluate their performance, and the details of their algorithms for ECG and EHR analysis. The validation strategies that have been used to evaluate the performance of the proposed methods are also presented. Finally, the paper provides recommendations for future research to address the shortcomings of the currently existing methods and practical considerations to make the proposed technical solutions applicable in clinical practice.

Lead transformations and the dipole approximation: Practical applications

The transformation of recorded electrocardiographic leads (source leads) into leads that are wanted but were not recorded (target leads) has many practical applications. In general, two transformation methods are put to use, a purely statistical one and a model-based one. They are briefly reviewed and compared. Lead transformations were first used in the early nineteen-sixties to transform the component leads of one vectorcardiographic lead system into those of another. Since then, the use of lead transformations has proliferated and they are currently applied for a variety of purposes. Lead transformations can be grouped according to the source and target leads that are involved. A few applications of lead transformations from the different groups are presented, with a focus on the practicality of the application. The validity and value of the dipole approximation in relation to lead transformations is discussed.

Spatiotemporal representation of cardiac vectorcardiogram (VCG) signals

Background

Vectorcardiogram (VCG) signals monitor both spatial and temporal cardiac electrical activities along three orthogonal planes of the body. However, the absence of spatiotemporal resolution in conventional VCG representations is a major impediment for medical interpretation and clinical usage of VCG. This is especially so because time-domain features of 12-lead ECG, instead of both spatial and temporal characteristics of VCG, are widely used for the automatic assessment of cardiac pathological patterns.

Materials and methods

We present a novel representation approach that captures critical spatiotemporal heart dynamics by displaying the real time motion of VCG cardiac vectors in a 3D space. Such a dynamic display can also be realized with only one lead ECG signal (e.g., ambulatory ECG) through an alternative lag-reconstructed ECG representation from nonlinear dynamics principles. Furthermore, the trajectories are color coded with additional dynamical properties of space-time VCG signals, e.g., the curvature, speed, octant and phase angles to enhance the information visibility.

Results

In this investigation, spatiotemporal VCG signal representation is used to characterize various spatiotemporal pathological patterns for healthy control (HC), myocardial infarction (MI), atrial fibrillation (AF) and bundle branch block (BBB). The proposed color coding scheme revealed that the spatial locations of the peak of T waves are in the Octant 6 for the majority (i.e., 74 out of 80) of healthy recordings in the PhysioNet PTB database. In contrast, the peak of T waves from 31.79% (117/368) of MI subjects are found to remain in Octant 6 and the rest (68.21%) spread over all other octants. The spatiotemporal VCG signal representation is shown to capture the same important heart characteristics as the 12-lead ECG plots and more.

Conclusions

Spatiotemporal VCG signal representation is shown to facilitate the characterization of space-time cardiac pathological patterns and enhance the automatic assessment of cardiovascular diseases.

Comparison of the five-electrode-derived EASI electrocardiogram to the Mason Likar electrocardiogram in the prehospital setting

This study compared the 5-electrode-derived EASI electrocardiogram (ECG) with the conventional Mason-Likar ECG in 200 consecutive patients with chest pain transported to 3 hospitals by 2 different emergency medical services. No significant differences were observed between the 2 systems for the detection of relevant electrocardiographic abnormalities. A questionnaire administered to participating emergency medical personnel revealed a high degree of acceptability of the EASI ECG, with some participants commenting that the sternal and mid-axillary locations of the EASI electrodes made them easier to apply, especially to women, than conventional precordial electrodes.

New Holter Monitoring Analysis System-Synthesizing 12-Lead Electrocardiograms Using a Calculation of the Lead Vectors-

BACKGROUND

A new system of synthesizing a 12-lead electrocardiogram (Syn-ECG) with practically identical waveforms to the standard 12-lead ECG (Stn-ECG) from 3-channel ECGs recorded by Holter monitoring has been developed.

METHODS AND RESULTS

The study group comprised 16 healthy individuals and 13 patients with abnormal ECGs. The bipolar eV1, eV5 and eVF leads were recorded using digital Holter monitoring and nine Syn-ECGs, corresponding to each lead of the Stn-ECG, were synthesized. The 9 ECGs consisted of a theoretical Syn-ECG and 8 Syn-ECGs positioned around the theoretical Syn-ECG at 3 cm intervals on the Frank's image surface. Of the 9 ECGs, the Syn-ECG with the maximum product of the cross-correlation coefficient of the QRS wave and that of the T wave, was automatically selected as the optimal Syn-ECG. The amplitude data from the QRS wave, R wave, T wave, and ST level, and also the amplitude ratio of the R wave, T wave to the QRS wave, were significantly well correlated between the Syn-ECG and Stn-ECG.

CONCLUSIONS

A practically identical ECG morphology, comparable with a Stn-ECG, was successfully created using this system.

QT dispersion, T-wave projection, and heterogeneity of repolarization in patients with coronary artery disease

The clinically useful prognostic value of precordial QT dispersion in patients with heart disease is generally attributed to its measurement of regional heterogeneity of ventricular repolarization. However, when repolarization is abnormal, differences in measured QT intervals might result simply from variation in projection of the T-wave loop. To provide insight into the mechanism of QT dispersion, we used an analog device to transform conventional 12-lead electrocardiograms (ECGs) of 78 patients to derived 12-lead ECGs based on the heart vector. Because the electrical activity of the heart is represented by a single dipole, all QT dispersion in the transformed ECGs results from variation in projection of the T-wave loop and cannot be due to local heterogeneity of repolarization. Measured as the difference between the longest and shortest precordial QT intervals, QT dispersion in the derived ECGs, with no local heterogeneity of repolarization, was 53 +/- 49 ms (mean +/- SD). QT dispersion in these derived ECGs was similar in magnitude to that measured from the original standard 12-lead ECGs in these patients (49 +/- 23 ms, p = NS). Therefore, the precordial QT dispersion measured from standard ECGs of patients with coronary artery disease can be explained by interlead variation in precordial projection of the T-wave loop. Although regional heterogeneity might still contribute to precordial repolarization findings and to prognosis, this is not required to explain the QT dispersion observed in patients with coronary artery disease. Therefore, QT interval dispersion is not equivalent to heterogeneity of repolarization.

Determinants of precordial QT dispersion in normal subjects

Dispersion of precordial QT intervals has been attributed to delay in the recovery process in the myocardium under the exploring electrode, a local effect. However, the phenomenon also could be explained by different projections of the heart vector, in which case the 12-lead electrocardiogram (ECG) derived from the heart vector would show similar dispersion that could not be local in nature because the electrical activity of the heart is represented by a single dipole. Using an analog device that switched between the two, conventional and derived ECGs were obtained from 129 normal subjects. Measured as the difference between the longest and shortest precordial QT intervals, QT dispersion from the derived ECGs (mean +/- SD, 40 +/- 20 ms) was nearly identical in magnitude to that from the standard ECGs (41 +/- 18 ms, P = NS). Further analysis of the derived ECGs revealed nonuniform distributions of both the maximal and minimal QT intervals across the precordial leads. In addition, a weak correlation was found between the QT interval and the T wave amplitude in the two precordial leads with the lowest T-wave amplitudes (r = -0.303 in V1, P = .001, and r = 0.253 in V6, P = .005). While findings in patients with disease or with abnormal ECGs may differ and require separate examination, these data suggest that the observed magnitude of precordial QT dispersion in normal subjects can be explained by differences in precordial projection of the end of the T wave rather than by local effect.

Morphologic characteristics of nonsustained ventricular tachycardia detected during Holter monitoring associated with atherosclerotic coronary artery disease

Nonsustained ventricular tachycardia (VT) is an important prognostic indicator of outcome in patients with organic heart disease. The morphologic features of nonsustained VT were examined by obtaining a derived 12-lead electrocardiogram (ECGD) from a 24-hour Holter recording in 22 patients with nonsustained VT associated with coronary artery disease. A total of 60 nonsustained VT episodes were recorded. Of these, 20 were uniform and 40 were multiform. The mean rate of uniform episodes was faster (140 +/- 32 vs 124 +/- 16 beats/min; p < 0.01) and the duration longer (5.3 +/- 2.0 vs 4.0 +/- 1.0 beats; p < 0.02) than the multiform episodes. The majority (87%) of multiform episodes had only 2 different QRS configurations on the ECGD. Four distinct patterns of QRS configurations were seen within individual multiform nonsustained VT runs: type I--the initial QRS complex has 1 morphology and all subsequent complexes have another configuration; type II--the initial and terminal QRS complex has similar configuration; type III--the first 2 QRS complexes have similar configuration and all subsequent complexes have another morphology; and type IV--the QRS complexes have alternating morphologic features. These 4 different patterns may be related to the mechanism of nonsustained VT (reentry versus automaticity). Patients with multiple episodes of nonsustained VT frequently had differing patterns and morphologic features between episodes. Further studies are needed to evaluate the clinical importance of these findings.

Comparison of a vectorcardiographically derived 12-lead electrocardiogram with the conventional electrocardiogram during wide QRS complex tachycardia, and its potential application for continuous bedside monitoring

Previous investigators published conflicting reports comparing a vectorcardiographically derived electrocardiogram (ECGD) with the conventional 12-lead one (ECG). Prior comparisons were obtained in adults during sinus rhythm, but never in patients with wide QRS complex tachycardia. The ECGD was evaluated during baseline rhythms in patients with varying cardiac diagnoses, and the diagnostic accuracy of the 2 methods was compared during 64 episodes of wide QRS complex tachycardia in 49 patients during cardiac electrophysiologic study. All leads of the 12-lead ECGD closely resembled the conventional ECG in baseline and tachycardia tracings, except leads V3 and V4. QRS voltages were less in the ECGD, resulting in an inability to detect left ventricular hypertrophy in one third of patients with that diagnosis. There was excellent agreement between the ECGD and ECG in diagnosing prior myocardial infarction (92%), ventricular preexcitation patterns (100%), bundle branch and fascicular blocks (100%), and axis deviation. The ECGD was equally as valuable as the ECG in the diagnosis of wide QRS complex tachycardia. There was perfect agreement between the 2 lead systems in application of the morphologic criteria differentiating supraventricular tachycardia with aberration from ventricular tachycardia in leads V1, V2 and V6, and for criteria requiring axis determination and measurement of RS intervals in the precordial leads. The ECGD tracings contained less muscle artifact during body movements (e.g., after direct-current defibrillation). In conclusion, the ECGD's close correlation with the ECG, and its technical superiority and simple 5 torso-positioned electrode configuration make it worth pursuing as an option for continuous bedside monitoring.

Deriving the 12-lead electrocardiogram from four (EASI) electrodes

Computerized interpretation of the electrocardiogram has now advanced to computerization of the electrocardiograph, resulting in greatly increased versatility, including the capacity for adapting to a variety of lead systems rather than being tethered to the old Einthoven-Wilson-Goldberger (EWG) system. Many varieties of display beyond the 12-lead ECG are also available in software. To date, these new and interesting capabilities have scarcely been exploited. The EASI lead system uses the E, A, and I electrode positions of the Frank lead system, plus an electrode, S, positioned over the upper end of the sternum and, if necessary, ground (anywhere convenient). Its outputs form quasi-xyz signals, x'y'z', that can be approximately transformed into xyz signals by means of a matrix derived from the EASI lead vectors. The result forms a good basis for deriving the 12-lead ECG, using previously published coefficients for the Frank lead system. The match with the conventional ECG can then be improved by statistical means. The results are surprisingly good, and certainly of clinical value. Recent widespread interest in silent ischemia and its detection through Holter monitoring suggests an immediate application which has been rendered practical by the recent introduction of three-channel recorders. The EASI electrode positions give technically satisfactory Holter recordings. Very compact three-channel, multiplexed, radio telemetry equipment is now commercially available and provides another application for the EASI 12-lead ECG.(ABSTRACT TRUNCATED AT 250 WORDS)

Comparative accuracy of computerized spatial vectorcardiography and standard electrocardiography for detection of myocardial infarction

New computerized spatial vectorcardiographic variables were analyzed by discriminant analyses for group classification of 94 patients with acute myocardial infarction and 79 normal subjects. Using the integral of the sequential magnitudes of the spatial vectors during the period of initial abnormal depolarization (IAD) of the QRS at a discriminating value of 3 mv X msec., 87% of the subjects were correctly classified with a sensitivity of 85%; specificity of 88%; and an overall predictive accuracy of 87%, p less than .00001. The period of initial abnormal depolarization in which the vectors were integrated was determined by the first derivative of the sequential magnitudes of the spatial vectors of the QRS waveform (dm/dt). The mean value of dm/dt during the period of abnormal depolarization was a poor discriminating variable. The predictive accuracy of this new electrocardiographic criterion for diagnosis of myocardial infarction compared favorably with other computerized methods such as vectorcardiography, polarcardiography, Aitoff spatial trajectory, the 12-lead ECG derived by the Frank XYZ leads as well as the standard 12-lead ECG.

Comprehensive evaluation of electrocardiographic methods for detection of myocardial infarction

In two groups of patients the detection of myocardial infarction (MI) by analysis of four different electrocardiographic methods was evaluated. The various methods included the conventional 12 lead ECG (CV-ECG), the 12 lead ECG derived from Frank XYZ lead system signals (D-ECG), the polarcardiogram (PCG) and the vectorcardiogram (VCG). An invasive group consisted of 137 patients who had undergone cardiac catheterization. An MI was defined as a regional wall motion abnormality in the distribution of a coronary artery with at least 70% diameter reduction. The noninvasive group consisted of 116 patients in whom independent clinical information was limited to noninvasive assessments. In this group, Telemed Computer Systems' interpretation of the conventional (TC-ECG) and derived (TD-ECG) electrocardiogram was also available for comparison. An MI was defined in this group as either a compatible history with documented cardiac enzyme elevations, a resting defect on thallium scan, or a regional wall motion abnormality in a resting, radionuclide isotope ventriculogram. In this study the other methods of ECG evaluation demonstrated no advantage over the electrocardiographer's reading of the conventional ECG.