Evaluation of ventricular repolarization dispersion during acute myocardial ischemia: spatial and temporal ECG indices

Reliable Detection of Myocardial Ischemia Using Machine Learning Based on Temporal-Spatial Characteristics of Electrocardiogram and Vectorcardiogram

Background: Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection of myocardial ischemia using computer-aided analysis of electrocardiograms (ECG) provides an important reference for early diagnosis of CVD. The vectorcardiogram (VCG) could improve the performance of ECG-based myocardial ischemia detection by affording temporal-spatial characteristics related to myocardial ischemia and capturing subtle changes in ST-T segment in continuous cardiac cycles. We aim to investigate if the combination of ECG and VCG could improve the performance of machine learning algorithms in automatic myocardial ischemia detection.

Methods: The ST-T segments of 20-second, 12-lead ECGs, and VCGs were extracted from 377 patients with myocardial ischemia and 52 healthy controls. Then, sample entropy (SampEn, of 12 ECG leads and of three VCG leads), spatial heterogeneity index (SHI, of VCG) and temporal heterogeneity index (THI, of VCG) are calculated. Using a grid search, four SampEn and two features are selected as input signal features for ECG-only and VCG-only models based on support vector machine (SVM), respectively. Similarly, three features (S_I, THI, and SHI, where S_I is the SampEn of lead I) are further selected for the ECG + VCG model. 5-fold cross validation was used to assess the performance of ECG-only, VCG-only, and ECG + VCG models. To fully evaluate the algorithmic generalization ability, the model with the best performance was selected and tested on a third independent dataset of 148 patients with myocardial ischemia and 52 healthy controls.

Results: The ECG + VCG model with three features (S_I,THI, and SHI) yields better classifying results than ECG-only and VCG-only models with the average accuracy of 0.903, sensitivity of 0.903, specificity of 0.905, F1 score of 0.942, and AUC of 0.904, which shows better performance with fewer features compared with existing works. On the third independent dataset, the testing showed an AUC of 0.814.

Conclusion: The SVM algorithm based on the ECG + VCG model could reliably detect myocardial ischemia, providing a potential tool to assist cardiologists in the early diagnosis of CVD in routine screening during primary care services.

A New Method for Detecting Myocardial Ischemia Based on ECG T-Wave Area Curve (TWAC)

In recent years, coronary heart disease (CHD) has become one of the main diseases that endanger human health, with a high mortality and disability rate. Myocardial ischemia (MI) is the main symptom in the development of CHD. Continuous and severe myocardial ischemia will lead to myocardial infarction. The clinical manifestations of MI are mainly the changes of ST-T segment of ECG, that is, ST segment and T wave. Nearly one third of patients with CHD, however, has no obvious ECG changes. In this paper, a new method for detecting MI based on the T-wave area curve (TWAC) was proposed. Through observation and analysis of clinical data, it was found that there exist significant correlation between the morphology of TWAC and MI. The TWAC morphology of normal subject is smooth and gentle, while the TWAC morphology of patients with coronary stenosis is mostly jagged, and the curve becomes more severe with more severe stenosis. The preliminary test results show that the sensitivity, specificity, and accuracy of the proposed method for detecting MI are 84.3, 83.6, and 84%, respectively. This study shows that the TWAC based approach may be an effective method for detecting MI, especially for the CHD patients with no obvious ECG changes.

ECG Beat Representation and Delineation by Means of Variable Projection

OBJECTIVE

The electrocardiogram (ECG) follows a characteristic shape, which has led to the development of several mathematical models for extracting clinically important information. Our main objective is to resolve limitations of previous approaches, that means to simultaneously cope with various noise sources, perform exact beat segmentation, and to retain diagnostically important morphological information.

METHODS

We therefore propose a model that is based on Hermite and sigmoid functions combined with piecewise polynomial interpolation for exact segmentation and low-dimensional representation of individual ECG beat segments. Hermite and sigmoidal functions enable reliable extraction of important ECG waveform information while the piecewise polynomial interpolation captures noisy signal features like the baseline wander (BLW). For that we use variable projection, which allows the separation of linear and nonlinear morphological variations of the according ECG waveforms. The resulting ECG model simultaneously performs BLW cancellation, beat segmentation, and low-dimensional waveform representation.

RESULTS

We demonstrate its BLW denoising and segmentation performance in two experiments, using synthetic and real data. Compared to state-of-the-art algorithms, the experiments showed less diagnostic distortion in case of denoising and a more robust delineation for the P and T wave.

CONCLUSION

This work suggests a novel concept for ECG beat representation, easily adaptable to other biomedical signals with similar shape characteristics, such as blood pressure and evoked potentials.

SIGNIFICANCE

Our method is able to capture linear and nonlinear wave shape changes. Therefore, it provides a novel methodology to understand the origin of morphological variations caused, for instance, by respiration, medication, and abnormalities.

In Search of an Optimal Subset of ECG Features to Augment the Diagnosis of Acute Coronary Syndrome at the Emergency Department

Background Classical ST-T waveform changes on standard 12-lead ECG have limited sensitivity in detecting acute coronary syndrome (ACS) in the emergency department. Numerous novel ECG features have been previously proposed to augment clinicians' decision during patient evaluation, yet their clinical utility remains unclear. Methods and Results This was an observational study of consecutive patients evaluated for suspected ACS (Cohort 1 n=745, age 59±17, 42% female, 15% ACS; Cohort 2 n=499, age 59±16, 49% female, 18% ACS). Out of 554 temporal-spatial ECG waveform features, we used domain knowledge to select a subset of 65 physiology-driven features that are mechanistically linked to myocardial ischemia and compared their performance to a subset of 229 data-driven features selected by multiple machine learning algorithms. We then used random forest to select a final subset of 73 most important ECG features that had both data- and physiology-driven basis to ACS prediction and compared their performance to clinical experts. On testing set, a regularized logistic regression classifier based on the 73 hybrid features yielded a stable model that outperformed clinical experts in predicting ACS, with 10% to 29% of cases reclassified correctly. Metrics of nondipolar electrical dispersion (ie, circumferential ischemia), ventricular activation time (ie, transmural conduction delays), QRS and T axes and angles (ie, global remodeling), and principal component analysis ratio of ECG waveforms (ie, regional heterogeneity) played an important role in the improved reclassification performance. Conclusions We identified a subset of novel ECG features predictive of ACS with a fully interpretable model highly adaptable to clinical decision support applications. Registration URL: https://www.clinicaltrials.gov; Unique Identifier: NCT04237688.

Deterministic Learning-Based Methodology for Detecting Abnormal Dynamics of Cardiac Repolarization During Ischemia

OBJECTIVE

This study concentrates on subtle electrocardiogram (ECG) spatiotemporal characteristics in the repolarization phase, and describes a deterministic learning-based methodology for the detection of abnormal cardiac dynamics induced by ischemia.

METHODS

ST-T complex of the surface 12-lead ECG signals are identified and extracted. Cardiac dynamics underlying ST-T complex signals is captured using deterministic learning algorithm. This kind of dynamics information represents the beat-to-beat temporal change of electrophysiological modifications in ventricular repolarization, which is shown to be sensitive to the variance during myocardial ischemia. Cardiodynamicsgram (CDG) is proposed as the three-dimensional graphic representation of cardiac dynamics information.

RESULTS

Encouraging evaluation results are achieved on electrocardiograms from public PTB database and hospital patients. Significant correlations are found between the CDG morphology and ischemia.

CONCLUSION

Anormal dynamics of cardiac repolarization during ischemia can be detected using a deterministic learning-based methodology. The extracted cardiac dynamics information within routine ECG is expected to provide early detection for latent ischemia before obvious pathological changes are present in ECG.

SIGNIFICANCE

The proposed techniques can be considered as a complementary tool to the generally accepted ECG method for detection of abnormal dynamics in cardiac repolarization, which are important for identifying patients at risk of myocardial ischemia.

Spatial indices of repolarization correlate with non-ST elevation myocardial ischemia in patients with chest pain

Mild-to-moderate ischemia does not result in ST segment elevation on the electrocardiogram (ECG), but rather non-specific changes in the T wave, which are frequently labeled as non-diagnostic for ischemia. Robust methods to quantify such T wave heterogeneity can have immediate clinical applications. We sought to evaluate the effects of spontaneous ischemia on the evolution of spatial T wave changes, based on the eigenvalues of the spatial correlation matrix of the ECG, in patients undergoing nuclear cardiac imaging for evaluating intermittent chest pain. We computed T wave complexity (TWC), the ratio of the second to the first eigenvalue of repolarization, from 5-min baseline and 5-min peak-stress Holter ECG recordings. Our sample included 30 males and 20 females aged 63 ± 11 years. Compared to baseline, significant changes in TWC were only seen in patients with ischemia (n = 10) during stress testing, but not among others. The absolute changes in TWC were significantly larger in the ischemia group compared to others, with a pattern that seemed to depend on the severity or anatomic distribution of ischemia. Our results demonstrate that ischemia-induced changes in T wave morphology can be meaningfully quantified from the surface 12-lead ECG, suggesting an important opportunity for improving diagnostics in patients with chest pain.

Cardiodynamicsgram as a New Diagnostic Tool in Coronary Artery Disease Patients With Nondiagnostic Electrocardiograms

Cardiodynamicsgram (CDG) has emerged recently as a noninvasive spatiotemporal electrocardiographic method for subtle cardiac dynamics information analysis within electrocardiogram (ECG). This study sought to evaluate the clinical utility of CDG for early coronary artery disease (CAD) detection in suspected patients with CAD presenting with nondiagnostic ECGs. A total of 421 suspected patients with CAD presenting with nondiagnostic ECG were enrolled. Standard 12-lead ECG and CDG were performed simultaneously, 1 day before invasive coronary angiography. Diagnostic accuracy of CDG for early CAD detection was assessed with reference to coronary angiography as the gold standard. Coronary angiography showed ≥1 coronary arteries stenosis of >50% in 347 patients. Of these 347 patients with CAD, 294 patients were positive in CDG. Of 74 non-CAD controls, 63 patients were negative in CDG. Diagnostic accuracy of CDG at presentation for CAD was 84.6%, sensitivity 84.7%, and specificity 83.7%. In patients presenting with nondiagnostic ECGs, an abnormal status can be detected early through noninvasive CDG. CDG is highly sensitive for the early diagnosis of CAD. Underlying causes of false-negative CDG findings included number of diseased coronary arteries and collateral circulation. Subtle myocardial damage that was not detectable on coronary angiography might be the major cause of false-positive findings.

Wavelet Based Method for Congestive Heart Failure Recognition by Three Confirmation Functions

An investigation of the electrocardiogram (ECG) signals and arrhythmia characterization by wavelet energy is proposed. This study employs a wavelet based feature extraction method for congestive heart failure (CHF) obtained from the percentage energy (PE) of terminal wavelet packet transform (WPT) subsignals. In addition, the average framing percentage energy (AFE) technique is proposed, termed WAFE. A new classification method is introduced by three confirmation functions. The confirmation methods are based on three concepts: percentage root mean square difference error (PRD), logarithmic difference signal ratio (LDSR), and correlation coefficient (CC). The proposed method showed to be a potential effective discriminator in recognizing such clinical syndrome. ECG signals taken from MIT-BIH arrhythmia dataset and other databases are utilized to analyze different arrhythmias and normal ECGs. Several known methods were studied for comparison. The best recognition rate selection obtained was for WAFE. The recognition performance was accomplished as 92.60% accurate. The Receiver Operating Characteristic curve as a common tool for evaluating the diagnostic accuracy was illustrated, which indicated that the tests are reliable. The performance of the presented system was investigated in additive white Gaussian noise (AWGN) environment, where the recognition rate was 81.48% for 5 dB.

Rationale, development, and implementation of the Electrocardiographic Methods for the Prehospital Identification of Non-ST Elevation Myocardial Infarction Events (EMPIRE)

BACKGROUND

The serum rise of cardiac troponin remains the gold standard for diagnosing non-ST elevation (NSTE) myocardial infarction (MI) despite its delayed response. Novel methods for real-time detection of NSTEMI would result in more immediate initiation of definitive medical therapy and faster transport to facilities that can provide specialized cardiac care.

METHODS

EMPIRE is an ongoing prospective, observational cohort study designed to quantify the magnitude of ischemia-induced repolarization dispersion for the early detection of NSTEMI. In this ongoing study, prehospital ECG data is gathered from patients who call 9-1-1 with a chief complaint of non-traumatic chest pain. This data is then analyzed using the principal component analysis (PCA) technique of 12-lead ECGs to fully characterize the spatial and temporal qualities of STT waveforms.

RESULTS

Between May and December of 2013, Pittsburgh EMS obtained and transmitted 351 prehospital ECGs of the 1149 patients with chest pain-related emergency dispatches transported to participating hospitals. After excluding those with poor ECG signal (n=40, 11%) and those with pacing or LBBB (n=50, 14%), there were 261 eligible patients (age 57±16years, 45% female, 45% Black). In this preliminary sample, there were 19 STEMI (7%) and 33 NSTEMI (12%). More than 50% of those with infarction (STEMI or NSTEMI) had initially negative troponin values upon presentation. We present ECG data of such NSTEMI case that was identified correctly using our methods.

CONCLUSIONS

Concrete ECG algorithms that can quantify NSTE ischemia and allow differential treatment based on such ECG changes could have an immediate clinical impact on patient outcomes. We describe the rationale, development, design, and potential usefulness of the EMPIRE study. The findings may provide insights that can influence guidelines revisions and improve public health.

Clinical Utility of Ventricular Repolarization Dispersion for Real-Time Detection of Non-ST Elevation Myocardial Infarction in Emergency Departments

BACKGROUND

A specific electrocardiographic (ECG) marker of ischemia would greatly improve the speed and accuracy of detecting and treating non-ST elevation myocardial infarction (NSTEMI). We hypothesize that ischemia induces ventricular repolarization dispersion (VRD), altering the T-wave before any ST segment deviation. We sought to evaluate the clinical utility of VRD to (1) detect NSTEMI cases in the emergency department (ED) and (2) identify NSTEMI cases at high risk for in-hospital major adverse cardiac events (MACEs).

METHODS AND RESULTS

We continuously recorded 12-lead Holter ECGs from chest pain patients upon their arrival to the ED. VRD was quantified using principal component analysis of the 12-lead ECG to compute a T-wave complexity ratio (ie, ratio of second to first eigenvectors of repolarization). Clinical outcomes were obtained from hospital records. The sample was composed mainly of older males (n=369; ages 63±12 years; 63% males), and 92 (25%) had NSTEMI and 26 (7%) had MACEs. Baseline T-wave complexity ratio modestly correlated with peak troponin levels (r=0.41; P<0.001) and was a good classifier of NSTEMI events (area under the curve=0.70). An increased T-wave complexity ratio on the presenting ECG was strongly associated with NSTEMI (odds ratio [OR]=3.8 [2.1 to 5.8]) and in-hospital MACE (OR=8.2 [3.1 to 21.5]).

CONCLUSIONS

A simple measure of global VRD on the presenting 12-lead ECG correlates with ischemic myocardial injury and can discriminate NSTEMI cases very early during evaluation. Prospective studies should validate these findings and test whether VRD can guide therapy.

Improved robust T-wave alternans detectors

New statistical and spectral detectors, the modified matched pairs t test, the extended spectral method and the modified spectral method, were proposed for T-wave alternans (TWA) detection gaining robustness according to trend and single-frequency interferences. They were compared to classic detectors such as matched pairs t test, unpaired t test, spectral method, generalized likelihood ratio test and estimated TWA amplitude within a simulation framework and applied to real data. The optimal detection threshold was selected by using a full Monte-Carlo simulation where signals, with and without alternans episodes, were corrupted by Gaussian noise with different power and single-frequency interferences with different tones. All the combinations of noise and frequency were selected and repeated 500 times in order to compute probability of detection ([Formula: see text]) and the false alarm probability ([Formula: see text]), providing ROC curves. The study group consisted of 50 patients with implantable cardioverter-defibrillator (age: [Formula: see text]; LVEF: [Formula: see text]), who were paced (ventricular pacing) at 100 bpm. Two-minute recordings were analyzed. The XYZ orthogonal lead system was used. The best performance was reached by using the modified matched pairs t test (in comparison with the spectral method and other reference methods).