Effect of ECG filter settings on J-waves

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.

ANMCO/AIIC/SIT Consensus Information Document: definition, precision, and suitability of electrocardiographic signals of electrocardiographs, ergometry, Holter electrocardiogram, telemetry, and bedside monitoring systems

The electrocardiogram (ECG) signal can be derived from different sources. These include systems for surface ECG, Holter monitoring, ergometric stress tests, and telemetry systems and bedside monitoring of vital parameters, which are useful for rhythm and ST-segment analysis and ECG screening of electrical sudden cardiac death predictors. A precise ECG diagnosis is based upon correct recording, elaboration, and presentation of the signal. Several sources of artefacts and potential external causes may influence the quality of the original ECG waveforms. Other factors that may affect the quality of the information presented depend upon the technical solutions employed to improve the signal. The choice of the instrumentations and solutions used to offer a high-quality ECG signal are, therefore, of paramount importance. Some requirements are reported in detail in scientific statements and recommendations. The aim of this consensus document is to give scientific reference for the choice of systems able to offer high quality ECG signal acquisition, processing, and presentation suitable for clinical use.

Impact of the high-frequency cutoff of bandpass filtering on ECG quality and clinical interpretation: A comparison between 40Hz and 150Hz cutoff in a surgical preoperative adult outpatient population

BACKGROUND

In 1990 the American Heart Association (AHA) established a standard 0.05 to 150Hz bandwidth for the routine recording of 12-lead electrocardiograms (ECGs). However, subsequent studies have indicated a very high prevalence of deviations from the recommended cutoffs.

OBJECTIVE

This prospective observational study investigates the impact of 40Hz compared to 150Hz high-frequency cutoffs on ECG quality and clinical interpretation in a single-center surgical outpatient population.

METHODS

1582 consecutive adult patients underwent two standard 12-lead ECG tracings using different high-frequency cutoffs (40Hz and 150Hz). Two blinded cardiologists randomly reviewed and interpreted the recordings according to pre-defined parameters (PR and ST segment, Q and T wave abnormalities). An arbitrary score, ranging from 1 to 3, was established to evaluate the perceived quality of the recordings and the non-interpretable ECGs were noted. The tracings were then matched to compare interpretations between 40 and 150Hz filters.

RESULTS

A 40Hz high-frequency cutoff resulted in an increased rate of optimal quality ECGs compared to the 150Hz cutoff (93.4% vs 54.6%; p<0.001) and a lower rate of non-interpretable traces (0.25% vs 4.80%; p<0.001). Analyzing the morphologic parameters, no significant differences between the filter settings were found, except for a higher incidence of the J-point elevation in the 40Hz high-frequency cutoff (p=0.007) and a higher incidence of left ventricular hypertrophy in the 150Hz high-frequency cutoff (7.4% vs 5.4%, p<0.001). The latter was noted only in ECGs with borderline QRS amplitudes (between 3.3 and 3.7mV; p<0.001).

CONCLUSION

Despite current recommendations, the large deviation from standard high-frequency cutoff in clinical practice does not seem to significantly affect ECG clinical interpretation and a 40Hz high-frequency cutoff of the band-pass filtering may be acceptable in a low risk population, allowing for a better quality of tracings.

The prevalence of the electrocardiographic J wave in the Petit Basset Griffon Vendéen compared to 10 different dog breeds

INTRODUCTION

To investigate the prevalence and amplitudes of the electrocardiographic J wave in the Petit Basset Griffon Vendéen compared to 10 other dog breeds.

ANIMALS

Electrocardiograms from 206 healthy dogs representing 11 dog breeds were included in the study. Besides Petit Basset Griffon Vendéen (PBGV; n = 23) 10 other dog breeds were included.

MATERIALS AND METHODS

An electrocardiogram ruler was used for measuring the amplitudes of the J waves. The definition of a J wave was a positive deflection at the J point of ≥0.1 mV in more than 1 lead of the bipolar standard limb leads (I, II, III) or the unipolar standard limb leads (aVL and aVF).

RESULTS

The prevalence of J waves in the PBGV (n = 23) was 91% (n = 21, standard error (SE) = 5.9%), which was significantly higher compared to seven other dog breeds (p < 0.05). The overall prevalence of J waves in all 11 dog breeds (n = 206) was 43% (n = 89, robust SE = 7.8%). There was no significant difference in the prevalence between male and female dogs (p = 0.79). Neither did age (p = 0.22) nor heart rate (p = 0.25) significantly affect the prevalence of J wave.

CONCLUSIONS

The PBGV had the highest prevalence of J waves and the highest amplitudes compared to 10 other dog breeds. However J waves were also seen in other breeds. Therefore, J waves may be considered a normal variant on the canine electrocardiogram and should not be interpreted as cardiac disease.