Vectorcardiography Research Articles

Monitoring of myocardial injury by serial measurements of QRS area and T area: The MaastrICCht cohort.

Manually derived electrocardiographic (ECG) parameters were not associated with mortality in mechanically ventilated COVID-19 patients in earlier studies, while increased high-sensitivity cardiac troponin-T (hs-cTnT) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) were. To provide evidence for vectorcardiography (VCG) measures as potential cardiac monitoring tool, we investigated VCG trajectories during critical illness. All mechanically ventilated COVID-19 patients were included in the Maastricht Intensive Care Covid Cohort between March 2020 and October 2021. Serum hs-cTnT and NT-proBNP concentrations were measured daily. Conversion of daily 12-lead ECGs to VCGs by a MATLAB-based script provided QRS area, T area, maximal QRS amplitude, and QRS duration. Linear mixed-effect models investigated trajectories in serum and VCG markers over time between non-survivors and survivors, adjusted for confounders. In 322 patients, 5461 hs-cTnT, 5435 NT-proBNP concentrations and 3280 ECGs and VCGs were analyzed. Non-survivors had higher hs-cTnT concentrations at intubation and both hs-cTnT and NT-proBNP significantly increased compared with survivors. In non-survivors, the following VCG parameters decreased more when compared to survivors: QRS area (-0.27 (95% CI) (-0.37 to -0.16, p < .01) μVs per day), T area (-0.39 (-0.62 to -0.16, p < .01) μVs per day), and maximal QRS amplitude (-0.01 (-0.01 to -0.01, p < .01) mV per day). QRS duration did not differ. VCG-derived QRS area and T area decreased in non-survivors compared with survivors, suggesting that an increase in myocardial damage and tissue loss play a role in the course of critical illness and may drive mortality. These VCG markers may be used to monitor critically ill patients.

Vectorcardiography Predicts Heart Failure in Patients Following ST Elevation Myocardial Infarction.

Modeling outcomes, such as onset of heart failure (HF) or mortality, in patients following ST elevation myocardial infarction (STEMI) is challenging but clinically very useful. The acute insult following a myocardial infarction and chronic degeneration seen in HF involve a similar process where a loss of cardiomyocytes and abnormal remodeling lead to pump failure. This process may alter the strength and direction of the heart's net depolarization signal. We hypothesize that changes over time in unique parameters extracted using vectorcardiography (VCG) have the potential to predict outcomes in patients post-STEMI and could eventually be used as a noninvasive and cost-effective surveillance tool for characterizing the severity and progression of HF to guide evidence-based therapies. We identified 162 patients discharged from Michigan Medicine between 2016 and 2021 with a diagnosis of acute STEMI. For each patient, a single 12-lead ECG > 1 week pre-STEMI and > 1 week post-STEMI were collected. A set of unique VCG parameters were derived by analyzing features of the QRS complex. We used LASSO regression analysis incorporating clinical variables and VCG parameters to create a predictive model for HF, mortality, or the composite at 90, 180, and 365 days post-STEMI. The VCG model is most predictive for HF onset at 90 days with a robust AUC. Variables from the HF model mitigating or driving risk, at a p < 0.05, were primarily parameters that assess the area swept by the depolarization vector including the 3D integral and convex hull in select spatial octants and quadrants.

Abnormal QRS-T angles in 5796 women and men aged 50–64: an electrocardiographic analysis providing mechanistic insights

IntroductionAbnormal QRS-T angles are prognostic markers for cardiovascular deaths including sudden cardiac death. They occur in ∼5–6% of population-based cohorts but in ∼20% of patients with diabetes. The mechanistic background, electrical activation and/or recovery disturbances, is not known and the topic of this study. MethodsApplying Frank vectorcardiography (VCG) and simultaneously recorded scalar 12‑lead ECG, electrical activation and recovery of abnormal QRS-T angles were studied in 311 participants (5.4%) from a population-based cohort of 5796 women and men in the main Swedish CArdio-Pulmonary bio-Imaging Study (SCAPIS) in Gothenburg. Cut-off values for the peak and mean QRS-T angles were > 124° and > 119°, based on the >95th percentile among all 1080 participants in the pilot SCAPIS and reference values for normal directions (Q1-Q3) from 319 apparently healthy (30%) of them. ResultsOf 311 cases 17% had known cardiac disease. Deviations of QRS and QRSarea-vectors from reference limits (90%) were significantly more common than deviations of T- and Tarea-vectors (65%). Standard ECG signs suggested pathophysiology in 20%; left bundle branch block (LBBB) and voltage criteria for left ventricular hypertrophy being most frequent (9–10%) each. Sub-group analysis of the 30 with LBBB showed very large variability in vector directions. ConclusionsOur observations provide mechanistic insights about abnormal QRS-T angles of potential value for future prognostic and interventional studies. The results also have potential implications for LBB area pacing and the approach to left ventricular hypertrophy.

Computational vectorelectrocardiography: comparison of representations according to McPhee-Parungao and Frank

Aim: to compare amplitude-temporal and vectorcardiographic (VCG) parameters calculated through most commonly used matrix transformations.Materials and methods. Preliminary literature search revealed Kors and inverse Dower transformation to be the most commonly used matrices for converting ECG‑12 into Frank VCG. Trunov-Aidu matrix appeared to be the only one for deriving VCG in the McFee-Parungao lead system.The study included 1250 ECGs of patients at the National Medical Research Center of Cardiology with various cardiovascular diseases: arterial hypertension, coronary heart disease, post-infarction cardiosclerosis, aortic stenosis. For each patient, using the above transformations, three VCGs with an intact and three VCGs with an inverted direction of the Z axis (according to Ozol) were obtained. The comparison was carried out based on the main amplitude-temporal indicators of P-QRS-T, as well as on VCG parameters: spatial QRS-T angle, QRS loop area, QRS integral vector, fractional integrals P and QRS. A total of 9 pairwise comparisons of 134 indicators were carried out for each synthesized VCGResults. The strongest (r &gt; 0.9 or r &lt; -0.9) significant (p &lt; 0.001) linear correlation was found between the spatial metrics: P, QRS, T wave loop lengths, QRS loop area, QRS-T angle, ventricular gradient, and QRS shared integrals. Significant relationship between projection parameters and P-QRS-T amplitude and duration was observed in some cases. The largest number of correlations was noted between parameters calculated in McFee-Parungao and Frank lead system derived by Kors.Conclusions. Strong linear relationship was found between the VCG parameters determined through Kors, Dower and Trunov-Aidu matrix transformations, which indicates the equivalence of the results obtained through these matrices.

Prediction of the success of electrical cardioversion in patients with atrial fibrillation using parameters obtained by spectral and vectorcardiographic analysis of the ECG

Abstract Introduction Electrical cardioversion (ECV) still presents a treatment option for atrial fibrillation (AF). Despite the great success rate in the acute setting, its long-term success rate is low. The aim of the study was to find predictors of SR maintenance after ECV using spectral and vectorcardiographic (VCG) analysis of the ECG curve. Methods Consecutive patients with AF referred for elective ECV were prospectively enrolled. The digital ECG recording obtained before the ECV was analyzed using spectral and VCG analysis. All patients had Holter monitoring and clinical follow-up three months after cardioversion to assess SR maintenance. Atrial fibrillation activity was analyzed by spectral analysis, determining the dominant frequency (DF), RI (regularity index) and OI (organization index). QRS complexes were analyzed by vectorcardiography and dXmean, dYmean and dZmean (derivation of VCG signals) parameters were determined. Using logistic regression (LR) with backward parameter reduction, separate and combined predictive models of SR maintenance were calculated based on both the analysis from the VCG data and the spectral analysis data. Additional models with a forward selection of clinical variables were also calculated. The efficiency of the models was evaluated on a separate test subset of the data (N=32). Results A total of 80 patients were enrolled (age 70+10 years, 48 (64%) men, CHADSVASc 3.17+1.5, BMI 29.75kg/m2). At the 3-month follow-up, AF recurrence was present in 36 patients (45%). Using only vectorcardiographic parameters, dXmean (OR 3.07, 95 %CI 1.14- 8.63), p=0.001) and dYmean (OR 0.26, 95% CI 0.09-0.72), p &amp;lt;0.001) best predicted the SR maintenance (AUC of 0.72). Using only spectral analysis parameters, the best predictor was DF (OR 3.07, 95%CI 1.14-8.63), p=0.012) with AUC of 0.66. By combining the results of spectral analysis and vectorcardiography, an AUC of 0.78 was achieved. Among the clinical parameters, the most significant predictors were insufficiently controlled arterial hypertension and previous history of stroke. Conclusion Digital analysis of ECG curves using deeper mathematical models provides a better predictive model than classical clinical and echocardiographic models. The combination of spectral analysis of fibrillation atrial activity and vectorocardiographic analysis of QRS complexes revealed more accurate predictive information compared to both analyses alone.

The electrical substrate of vectorcardiographic QRS area in cardiac resynchronization therapy: insights from ECG-imaging

Abstract Background The QRS area shows promise as a vectorcardiographic (VCG) marker for electrical dyssynchrony in patient selection for cardiac resynchronization therapy (CRT). Nevertheless, little information is known about the underlying cardiac electrical substrate it may reflect. Purpose The aim of this study was to compare the VCG QRS area with measures of cardiac electrical dyssynchrony derived from electrocardiographic imaging (ECG-imaging). Methods QRS area from the synthesized VCG (Kors transformation matrix from the 12-lead ECG) was computed for 27 patients who underwent ECG-imaging (11 patients with no history of structural heart disease and 16 consecutive CRT patients). ECG-imaging measures for electrical dyssynchrony analyzed were: ventricular electrical uncoupling (VEU) computed as the difference between the average LV and RV activation times from ECG-imaging, standard deviation of activation times from the left ventricle (LV SDAT, and the maximal activation (Max AT). Pearson correlation analyses between VCG QRS area and ECG-imaging measures of dyssynchrony were carried out for the entire cohort and for patients with a wide-QRS only. Results ECG-imaging measures of dyssynchrony compared with QRS area in 11 patients with no structural heart disease with narrow-QRS (blue) and 16 candidates for CRT with heart failure (HF) and predominantly wide-QRS (LBBB [n=6], IVCD [n=8], RVpaced [n=1], and nQRS-HF [n=1]) are provided in Figure 1. QRS area were associated with all ECG-imaging measures of dyssynchrony. However, sub-analysis in only the wide-QRS patients revealed that QRS area exhibited the strongest association with VEU. Conclusion Vectorcardiographic QRS area is associated with cardiac electrical dyssynchrony on ECG-imaging, exhibiting a particularly strong association with ventricular electrical uncoupling.

Vectorcardiography signs of a failing Fontan: Heart rate, PR interval, RtQRSvm, QRSvm and SPQRS-T angle as noninvasive markers of late Fontan complications and mortality

BackgroundLimited data exists on interpreting vectorcardiography (VCG) parameters in the Fontan population. ObjectiveThe purpose of this study was to demonstrate the associations between ECG/VCG parameters and Fontan failure (FF). Methods/results107 patients with a Fontan operation after 1990 and without significant ventricular pacing were included. FF and Fontan survival (FS) groups were compared. The average follow-up after Fontan operation was 11.8 years ±7.1 years. 14 patients had FF (13.1%) which was defined as having protein-losing-enteropathy (1.9%), plastic bronchitis (2.8%), Fontan takedown (1.9%), heart transplant (5.6%), NYHA class III-IV (2.8%) or death (0.9%). A 12‑lead ECG at last follow up or prior to FF was assessed for heart rate, PR interval, QRS duration, Qtc and left/right sided precordial measures (P-wave, QRS and T-wave vector magnitudes, spatial P-R and QRS-T angles). Transthoracic echocardiogram evaluated atrioventricular valve regurgitation and ventricular dysfunction at FF or last follow up. A cox multivariate regression analysis adjusted for LV dominance, ventricular dysfunction, HR, PR, QTc, Pvm, QRSvm, SPQRST-angle, RtPvm, RtQRSvm and RtTvm. Ventricular dysfunction, increased heart rate and prolonged PR interval were significantly associated to FF at the multivariate analysis. ROC analysis and Kaplan-meier analysis revealed an increased total mortality associated with a heart rate > 93 bpm, PR interval > 155 mv, QRSvm >1.91 mV, RtQRSvm >1.8 mV and SPQRST angle >92.3 mV with p values <0.001 to 0.018. ConclusionWe demonstrate the importance of ECG/VCG monitoring in the Fontan population and suggest specific indicators of late complications and mortality.

The association between coronary artery calcification and vectorcardiography in mechanically ventilated COVID-19 patients: the Maastricht Intensive Care COVID cohort

BackgroundCoronary artery calcification (CAC) is associated with poor outcome in critically ill patients. A deterioration in cardiac conduction and loss of myocardial tissue could be an underlying cause. Vectorcardiography (VCG) and cardiac biomarkers provide insight into these underlying causes. The aim of this study was to investigate whether a high degree of CAC is associated with VCG-derived variables and biomarkers, including high-sensitivity troponin-T (hs-cTnT) and N-terminal pro-B-type natriuretic peptide (NT-proBNP).MethodsMechanically ventilated coronavirus-19 (COVID-19) patients with an available chest computed tomography (CT) and 12-lead electrocardiogram (ECG) were studied. CAC scores were determined using chest CT scans. Patients were categorized into 3 sex-specific tertiles: low, intermediate, and high CAC. Daily 12 leads-ECGs were converted to VCGs. Daily hs-cTnT and NT-proBNP levels were determined. Linear mixed-effects regression models examined the associations between CAC tertiles and VCG variables, and between CAC tertiles and hs-cTnT or NT-proBNP levels.ResultsIn this study, 205 patients (73.2% men, median age 65 years [IQR 57.0; 71.0]) were included. Compared to the lowest CAC tertile, the highest CAC tertile had a larger QRS area at baseline (6.65 µVs larger [1.50; 11.81], p = 0.012), which decreased during admission (− 0.27 µVs per day [− 0.43; − 0.11], p = 0.001). Patients with the highest CAC tertile also had a longer QRS duration (12.02 ms longer [4.74; 19.30], p = 0.001), higher levels of log hs-cTnT (0.79 ng/L higher [0.40; 1.19], p < 0.001) and log NT-proBNP (0.83 pmol/L higher [0.30; 1.37], p = 0.002).ConclusionPatients with a high degree of CAC had the largest QRS area and higher QRS amplitude, which decreased more over time when compared to patients with a low degree of CAC. These results suggest that CAC might contribute to loss of myocardial tissue during critical illness. These insights could improve risk stratification and prognostication of patients with critical illness.

Enrollment of Vector in Cardiology and Study of Cardiac Cadence

We have analyzed the application of vectors in cardiology and the way cardiac vector theory analyzes the heartbeat and can explain the entire cardiac conduction vector relationship and the Enthoven equilateral triangle hypothesis. This sheet explains the principles of the electrocardiogram and the interpretation of the waveforms. ECG can be called an electrocardiogram, which is a process of producing electrical activity through repetitive cycles. This diagram shows the voltage and duration of electrical activity by placing electrodes on the skin. Vector cardiography ( VCG) is a procedure that creates a 2D image of the heart's electrical activity by monitoring the spatial location of ECG waves at each successive point in their period. Even in the 21st century, coronary heart disease still represents a serious threat to humans and a major challenge to the scientific community. The most important elements for understanding and interpreting the ECG are the Enthoven triangle and the cardiac vector hypothesis, which have the potential , saving millions of lives when used quickly and appropriately to treat patients.

Early Detection of Coronary Microvascular Dysfunction Using Machine Learning Algorithm Based on Vectorcardiography and Cardiodynamicsgram Features

PurposeAs a main etiology of myocardial ischemia, coronary microvascular dysfunction (CMD) can occur in patients with or without obstructive coronary artery disease. Currently, there is a lack of a non-invasive approach for early detection of CMD. AimWe aim to develop a multilayer perceptron (MLP) algorithm to achieve non-invasive early detection of CMD based on vectorcardiography (VCG) and cardiodynamicsgram (CDG) features. MethodsElectrocardiograms of 82 CMD patients and 107 healthy controls were collected and synthesized into VCGs. The VCGs' ST-T segments were extracted and fed into a deterministic learning algorithm to develop CDGs. Temporal heterogeneity index, spatial heterogeneity index, sample entropy, approximate entropy, and complexity index were extracted from VCGs' ST-T segments and CDGs, entitled as STT- and CDG-based features, respectively. The most effective feature subsets were determined from CDG-based, STT-based, and the combined features (i.e., all features) via the sequential backward selection algorithm as inputs for CDG-, STT-, and CDG-STT-based MLP models optimized with an improved sparrow search algorithm, respectively. Finally, the classification capacity of the corresponding models was evaluated via five-fold cross-validations and tested on a testing dataset to verify the optimal one. ResultsThe CDG-STT-based MLP model had significantly higher evaluated metrics than CDG- and STT-based ones on the validation dataset, with the accuracy, sensitivity, specificity, F1 score, and AUC of 0.904, 0.925, 0.870, 0.870, and 0.897 on the testing dataset respectively. ConclusionsThe MLP model based on VCG and CDG features showed high efficiency in identifying CMD. The CDG-STT-based MLP model may afford a potential computer-aided tool for non-invasive detection of CMD.

BRAVEHEART: Open-source software for automated electrocardiographic and vectorcardiographic analysis

Background and ObjectivesElectrocardiographic (ECG) and vectorcardiographic (VCG) analyses are used to diagnose current cardiovascular disease and for risk stratification for future adverse cardiovascular events. With increasing use of digital ECGs, research into novel ECG/VCG parameters has increased, but widespread computer-based ECG/VCG analysis is limited because there are no currently available, open-source, and easily customizable software packages designed for automated and reproducible analysis. Methods and ResultsWe present BRAVEHEART, an open-source, modular, customizable, and easy to use software package implemented in the MATLAB programming language, for scientific analysis of standard 12-lead ECGs acquired in a digital format. BRAVEHEART accepts a wide variety of digital ECG formats and provides complete and automatic ECG/VCG processing with signal denoising to remove high- and low-frequency artifact, non-dominant beat identification and removal, accurate fiducial point annotation, VCG construction, median beat construction, customizable measurements on median beats, and output of measurements and results in numeric and graphical formats. ConclusionsThe BRAVEHEART software package provides easily customizable scientific analysis of ECGs and VCGs. We hope that making BRAVEHART available will allow other researchers to further the field of ECG/VCG analysis without having to spend significant time and resources developing their own ECG/VCG analysis software and will improve the reproducibility of future studies. Source code, compiled executables, and a detailed user guide can be found at http://github.com/BIVectors/BRAVEHEART. The source code is distributed under the GNU General Public License version 3.

A Comparison of Personalized and Generalized LSTM Neural Networks for Deriving VCG from 12-Lead ECG

Vectorcardiography (VCG) is a valuable diagnostic tool that complements the standard 12-lead ECG by offering additional spatiotemporal information to clinicians. However, due to the need for additional measurement hardware and too many electrodes in a clinical scenario if performed along with a standard 12-lead, there is a need to find methods to derive the VCG from the ECG. We have evaluated the use of Long Short-term Memory (LSTM) neural networks to learn the transformation from 12-lead ECG to VCG that is applicable across subjects and for each subject. We refer to these networks as generalized and personalized, respectively. We calculated the Root Mean Square Error (RMSE), R2, and Pearson correlation coefficient to compare waveforms of derived and actual VCG. We also extracted and compared diagnostic parameters from VCG, namely the QRS-loop magnitude, T-loop magnitude, and QRS-T spatial angle, from actual and derived VCGs using the Pearson correlation coefficient and Bland Altman limits of agreement. The personalized models performed better than generalized models in waveform comparisons and in the error of extracted diagnostic parameters from VCG waveforms. The use of personalized transformations for the derivation of VCG from standard 12-lead has the potential to improve and augment the diagnostic yield and accuracy of a standard 12-lead interpretation.

MP-453088-9 THE SPATIAL VENTRICULAR GRADIENT IS ASSOCIATED WITH CARDIAC MAGNETIC RESONANCE MARKERS OF OF DIFFUSE MYOCARDIAL FIBROSIS

Cardiac MRI (CMR) markers of diffuse myocardial fibrosis are of prognostic importance in cardiomyopathies. However, CMR is expensive, time-consuming, and not readily available. An ECG correlate for diffuse fibrosis, via its effect on myocardial electrical heterogeneity, would be useful. The spatial ventricular gradient (SVG), a vectorcardiographic (VCG) measurement of myocardial electrical heterogeneity, is a promising ECG correlate of CMR detected diffuse fibrosis. To assess the relationship of the SVG to extracellular volume (ECV) and native T1 values in patients referred for CMR. Retrospective cohort study of all patients referred for CMR from 2015 to 2022 at a single academic medical center who had ECG(s) performed within 30 days of CMR. Median VCGs were constructed from the 12-lead ECGs, and SVG was calculated as the area under the X, Y, and Z median beats. ECV and native T1 values were regressed on SVG vector magnitude, QT interval, and QRS duration using linear regression. Median values were compared using the rank-sum test. We evaluated 679 patients who underwent CMR and had ECV and T1 measurements and a recent ECG. The sample was 60% male and the mean age was 55 +/- 16 years. The figure shows how SVG vector magnitude was inversely correlated with both T1 and ECV (p<0.001 for both). In the lowest and highest quartiles of both ECV (0.03-0.28 vs 0.35-0.68) and T1 (1041-1227 vs 1315-1535 ms), the median SVG magnitude was significantly lower: 48.7 vs 32.3 mv*ms for ECV, and 48.5 vs 30 mv*ms for T1 (p<0.001 for both). In a multivariable model, the SVG remained independently associated with ECV and T1 after adjustment for QT interval, QRS duration, age, and sex (p<0.001). SVG magnitude is independently associated with CMR measures of extracellular fibrosis. Patients with higher SVG magnitude are unlikely to have a significant burden of diffuse fibrosis.

Entropy-based reliable non-invasive detection of coronary microvascular dysfunction using machine learning algorithm.

Coronary microvascular dysfunction (CMD) is emerging as an important cause of myocardial ischemia, but there is a lack of a non-invasive method for reliable early detection of CMD. To develop an electrocardiogram (ECG)-based machine learning algorithm for CMD detection that will lay the groundwork for patient-specific non-invasive early detection of CMD. Vectorcardiography (VCG) was calculated from each 10-second ECG of CMD patients and healthy controls. Sample entropy (SampEn), approximate entropy (ApEn), and complexity index (CI) derived from multiscale entropy were extracted from ST-T segments of each lead in ECGs and VCGs. The most effective entropy subset was determined using the sequential backward selection algorithm under the intra-patient and inter-patient schemes, separately. Then, the corresponding optimal model was selected from eight machine learning models for each entropy feature based on five-fold cross-validations. Finally, the classification performance of SampEn-based, ApEn-based, and CI-based models was comprehensively evaluated and tested on a testing dataset to investigate the best one under each scheme. ApEn-based SVM model was validated as the optimal one under the intra-patient scheme, with all testing evaluation metrics over 0.8. Similarly, ApEn-based SVM model was selected as the best one under the intra-patient scheme, with major evaluation metrics over 0.8. Entropies derived from ECGs and VCGs can effectively detect CMD under both intra-patient and inter-patient schemes. Our proposed models may provide the possibility of an ECG-based tool for non-invasive detection of CMD.

A unique cardiac electrocardiographic 3D model. Toward interpretable AI diagnosis.

Mathematical models of cardiac electrical activity are one of the most important tools for elucidating information about heart diagnostics. In this paper, we present an efficient mathematical formulation for this modeling simple enough to be easily parameterized and rich enough to provide realistic signals. It relies on a five dipole representation of the cardiac electric source, each one associated with the well-known waves of the electrocardiogram signal. Beyond the physical basis of the model, the parameters are physiologically interpretable as they characterize the wave shape, similar to what a physician would look for in signals, thus making them very useful in diagnosis. The model accurately reproduces the electrocardiogram signals of any diseased or healthy heart. This new discovery represents a significant advance in electrocardiography research. It is especially useful for diagnosis, patient follow-up or decision-making on new therapies; is also a promising tool for well-performing, transparent and interpretable AI approaches.

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.

Cardiac Arrhythmia classification based on 3D recurrence plot analysis and deep learning.

Artificial intelligence (AI) aided cardiac arrhythmia (CA) classification has been an emerging research topic. Existing AI-based classification methods commonly analyze electrocardiogram (ECG) signals in lower dimensions, using one-dimensional (1D) temporal signals or two-dimensional (2D) images, which, however, may have limited capability in characterizing lead-wise spatiotemporal correlations, which are critical to the classification accuracy. In addition, existing methods mostly assume that the ECG data are linear temporal signals. This assumption may not accurately represent the nonlinear, nonstationary nature of the cardiac electrophysiological process. In this work, we have developed a three-dimensional (3D) recurrence plot (RP)-based deep learning algorithm to explore the nonlinear recurrent features of ECG and Vectorcardiography (VCG) signals, aiming to improve the arrhythmia classification performance. The 3D ECG/VCG images are generated from standard 12 lead ECG and 3 lead VCG signals for neural network training, validation, and testing. The superiority and effectiveness of the proposed method are validated by various experiments. Based on the PTB-XL dataset, the proposed method achieved an average F1 score of 0.9254 for the 3D ECG-based case and 0.9350 for the 3D VCG-based case. In contrast, recently published 1D and 2D ECG-based CA classification methods yielded lower average F1 scores of 0.843 and 0.9015, respectively. Thus, the improved performance and visual interpretability make the proposed 3D RP-based method appealing for practical CA classification.

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.

An Exploratory Study on Vectorcardiographic Identification of the Site of Origin of Focally Induced Premature Depolarizations in Horses, Part II: The Ventricles.

Simple SummaryVentricular arrhythmias occur commonly in horses. Knowledge on the origin of ventricular arrhythmias is essential for proper treatment. Former studies in horses showed contradictory results regarding the diagnostic value of 12-lead electrocardiography and vectorcardiography due to the anatomical differences in horses compared to humans and small animals. As a consequence, no standardized approach is available for electrocardiography electrode configurations in horses. The current study investigated whether the anatomical origin of experimentally induced ventricular premature depolarizations in horses could be differentiated based upon spherical statistics of the vectorcardiography characteristics. Vectorcardiography shows the magnitude and direction of the cardiac electrical forces in three dimensions. The vectorcardiogram was recorded in seven horses under general anesthesia while right and left ventricular pacing was performed from inside the heart. Using spherical statistics, it could be shown that pacing induces significantly different initial and maximum electrical axes between different locations and between pacing and normal sinus rhythm. The current approach could be used in clinical patients to identify the origin of ventricular arrhythmias without the need for invasive studies. The technique could also be used in other species for which a standardized electrocardiogram electrode configuration is not available.In human cardiology, the anatomical origin of ventricular premature depolarizations (VPDs) is determined by the characteristics of a 12-lead electrocardiogram (ECG). Former studies in horses had contradictory results regarding the diagnostic value of the 12-lead ECG and vectorcardiography (VCG), which results were attributed to the different cardiac conduction system in this species. The objective of this study was to determine if the anatomical origin of pacing-induced VPDs could be differentiated in horses based upon VCG characteristics. A 12-lead ECG was recorded in seven horses under general anesthesia while right and left ventricular endomyocardial pacing was performed (800–1000 ms cycle length) at the apex, mid and high septum and mid and high free wall, and at the right ventricular outflow tract. Catheter positioning was guided by 3D electro-anatomical mapping and echocardiography. A median complex, obtained from four consecutive complexes, was calculated for each pacing location and sinus rhythm. The VCG was calculated from the 12-lead ECG-derived median complexes using custom-made algorithms and was used to determine the initial and maximum electrical axes of the QRS complex. An ANOVA for spherical data was used to test if VCGs between each paced location and between pacing and sinus rhythm were significantly (p < 0.05) different. The model included the radius, azimuth and elevation of each electrical axis. Pacing induced significantly different initial and maximum electrical axes between different locations and between pacing and sinus rhythm. The current results suggest that VCG is a useful technique to identify the anatomical origin of ventricular ectopy in horses.

An Exploratory Study on Vectorcardiographic Identification of the Site of Origin of Focally Induced Premature Depolarizations in Horses, Part I: The Atria.

Simple SummaryArrhythmias are common in horses, but in order to offer adequate treatment, the anatomical location from where the arrhythmia originates must first be known. The objective of this study was to differentiate between the various anatomical origins of atrial premature depolarizations and to further differentiate these from normal sinus rhythm based upon the vectorcardiography characteristics of seven horses without cardiovascular disease. With vectorcardiography, the magnitude and direction of the cardiac electrical forces were derived from an electrocardiographic recording and were plotted in three dimensions. The three directions were represented by the right–left axis, head–tail axis, and dorsoventral axis. Under general anaesthesia, atrial premature depolarizations were induced by pacing inside the heart, guided by a 3D mapping system that allowed us to see the 3D position of the pacing catheter inside the heart in real-time. An adapted statistical test optimized for spherical data was used to demonstrate that the maximal directions of the first and second half of the P wave showed significant differences between the paced locations and between the paced complexes and sinus rhythm. The current study provides a practical approach to identifying the approximate site of origin of an atrial arrhythmia using a custom 12-lead ECG.In human cardiology, the anatomical origin of atrial premature depolarizations (APDs) is derived from P wave characteristics on a 12-lead electrocardiogram (ECG) and from vectorcardiography (VCG). The objective of this study is to differentiate between anatomical locations of APDs and to differentiate APDs from sinus rhythm (SR) based upon VCG characteristics in seven horses without cardiovascular disease. A 12-lead ECG was recorded under general anaesthesia while endomyocardial atrial pacing was performed (800–1000 ms cycle length) at the left atrial free wall and septum, right atrial free wall, intervenous tubercle, as well as at the junction with the cranial and caudal vena cava. Catheter positioning was guided by 3D electro-anatomical mapping and transthoracic ultrasound. The VCG was calculated from the 12-lead ECG using custom-made algorithms and was used to determine the mean electrical axis of the first and second half of the P wave. An ANOVA for spherical data was used to test if the maximal directions between each paced location and the maximal directions between every paced location and SR were significantly (p < 0.05) different. Atrial pacing data were not available from the LA septum in three horses, the intervenous tubercle in two horses, and from the LA free wall in one horse. The directions of the maximal electrical axes showed significant differences between all paced locations and between the paced locations and SR. The current results suggest that VCG is useful for identifying the anatomical origin of an atrial ectopy.