Ventricular Flutter Research Articles

Automatic noise detection for ambulatory electrocardiogram in presence of ventricular arrhythmias through a machine learning approach

Noise detection in ambulatory electrocardiography is investigated as a machine learning binary classification problem on a set of twelve noise indices. Ten of these noise indices are replicated from relevant scientific literature. Two novel noise indices are also introduced: the electrocardiogram derivative pattern similarity index (edp) and the number of inversions of the signal’s slope over a minimum amplitude threshold (inv). Noise indices were computed on ex-novo labeled data, which included ventricular arrhythmias such as ventricular tachycardia, flutter, and fibrillation. Signal quality labels were assigned on windows of 2 seconds, from which a set of labels on 10-second windows was also created. Six classification models were trained on 2 s and 10 s window data with a multi-stage optimization procedure. A feature selection stage was performed for each model, probing the usefulness of different noise indices, including noise and ventricular arrhythmias. Hyperparameter selection and model assessment were conducted through nested cross-validation. Final test performance metrics reached values as high as Matthew’s correlation coefficient of 0.854 and balanced accuracy of 0.923. Particular attention was placed on the correct quality classification of records with ventricular arrhythmias, and test specificity on records with ventricular arrhythmias was as high as 0.976. This study provided new insights into the role of different noise indices in a challenging context with ventricular arrhythmias.

Pre-trained Bi-LSTM model for automated classification of ventricular arrhythmias using 1-D and 2-D ECG

Number of cardiac conditions have been associated with abnormal heartbeat (arrhythmia) such as ventricular fibrillation (Vfib), ventricular flutter (Vfl), and ventricular tachycardia (Vta). This is a difficult and essential job for timely clinical assessment and identification of these potentially life-threatening heart arrhythmias. With the aid of a one-dimensional electrocardiogram (ECG) signal and its associated two-dimensional image, the suggested method provides a strategy for the detection of time-frequency interpretation (Vfib, Vfl, and Vta). A four-stage cascaded Savitzky-Golay (SG) filter is used after a 2-stage median filter to preprocess the ECG signal. This technique employs z-score normalisation after brief (2 sec) ECG readings. The classification of these ECG segments (1-D) and associated time-frequency representation pictures (2-D) was explored separately using a bi-directional long short-term memory-based network. Eight distinct categorization scenarios were examined, and then an average accuracy of 99.67% for 1-D ECG and 99.87% for 2-D ECG signal was attained.

Disparities in the implantation of secondary prevention implantable cardioverter defibrillator in the United States.

The annual incidence of sudden cardiac death is over 300,000 in the United States (US). Historically, inpatient implantation of secondary prevention implantable cardioverter defibrillator (ICD) has been variable and subject to healthcare disparities. To evaluate contemporary practice trends of inpatient secondary prevention ICD implants within the US on the basis of race, sex, and socioeconomic status (SES). The study is a retrospective analysis of the National Inpatient Sample from 2016 to 2020 of adult discharges with a primary diagnosis of ventricular tachycardia (VT), ventricular flutter, and fibrillation (VF). Adjusted ICD implantation rates based on race, sex, and SES and associated temporal trends were calculated using multivariate regression. A total of 193,600 primary VT/VF discharges in the NIS were included in the cohort, of which 57,895 (29.9%) had ICD placement. There was a significant racial and ethnic disparity in ICD placement for Black, Hispanic, Asian, and Native American patients as compared to White patients; adjusted odds ratio (aOR): 0.86 [p<.01], 0.90 [p = .03], 0.81[p<.01], 0.45 [p<.01], respectively. Female patients were also less likely to receive an ICD compared to male patients (aOR: 0.75, p<.01). Disparities in ICD placement remained stable over the study period (ptrend ≥.05 in all races, both sexes and income categories). Racial, sex, and SES disparities persisted for secondary prevention ICD implants in the US. An investigation into contributing factors and subsequent approaches are needed to address the modifiable causes of disparities in ICD implantation as these trends have not improved compared to historic data.

A CASE OF PULMONARY HYPERTENSION ASSOCIATED WITH MYELOFIBROSIS: THERAPEUTICAL CHALLENGES FROM ACUTE TO CHRONIC SETTING

Abstract A 85–year–old female was transferred to our ICCU for acute heart failure from one of our spoke hospitals. The patient had a long history of chronic myelofibrosis, treated with fedratinib as a second–line agent after ruxolitinib failure. During a recent hospital admission, transthoracic echocardiography already showed signs of severe pulmonary hypertension (PH) with right ventricular (RV) dysfunction, so diuretic was started. On admission the patient presented showed consistent with acute on chronic kidney injury (serum Cr 3.2 mg/dl), stable anemia (Hb 9.2 mg/dl) and markedly elevated Nt–proBNP. A pulmonary CT–scan excluded acute pulmonary embolism and lung parenchymal alterations, with a clear dilation of main pulmonary artery. Transthoracic echocardiography (figure 1) confirmed precapillary PH phenotype diagnosis. Electrocardiogram (figure 2) showed sinus rhythm; incomplete RBBB, T wave inversion in V2 to V4. The patient was initially treated with high dose furosemide, low flow oxygen; but later she needed multiple cycles of inotropes, vasopressors and combined diuretic therapy (metolazone and acetazolamide) to stabilize the clinical setting. The patient also experienced episodes of paroxysmal high ventricular rate atrial flutter. After resolution of volume overload, a right heart catheterization was performed and findings were consistent with severe precapillary pulmonary hypertension: PA pressure 90/58/40 mmHg, normal PCWP, high PVR, mild cardiac index reduction. Due to critical clinical situation, Sildenafil 20 mg was started as an off–label therapy for PH (group 5). Subsequently, the patient experienced gradual but constant hemodynamic and clinical improvement and was discharged in NYHA class II. At 1 month control, patient was stable, echocardiogram revealed improvement in right ventricle dimension, systolic function and right atrial enlargement. At three months, patient is still in an intermediate risk class for PH, so we are evaluating a combination therapy (either endothelin receptor antagonist or prostanoids), taking into account anemia and thrombocytopenia. Take home message: PH can be a complication of hematological disorders as myelofibrosis, included in “mixed” forms (group 5) of PH. In our patient, after a challenging management for acute right heart failure, an off–label PDE–5 inhibitor stabilized the clinical scenario: more data are needed on PH drugs use in this setting where up to now therapeutic strategies are lacking.

On the heart rhythm analysis using a nonlinear dynamics perspective: analytical study and electronic simulation

Biological systems are highly complex, so understanding them requires extensive analysis. Cardiac rhythms are one such analysis. These rhythms are linked to a complex dynamic system defined on the basis of the electrical activity of cardiac cells. This electrical activity is essential to human physiology, defining numerous behaviours that include normal or pathological rhythms, generally measured by the electrocardiogram (ECG). This article presents a mathematical model to describe the electrical activity of the heart, using a nonlinear dynamics perspective. The stability analysis of this model in its autonomous state, uni-directionally coupled, shows a very rich dynamical behaviour characterized by periodical regions of stability and unstability. The model studied makes it possible to construct synthetic ECGs. These ECGs demonstrate a variety of responses, including normal and pathological rhythms: ventricular flutter, ventricular fibrillation, ventricular tachycardia and ventricular extrasystole. A quantitative analysis of the model is also carried out using bifurcation diagrams and the corresponding maximum Lyapunov exponents. In addition, variations in sinus rhythm are described by a time-dependent frequency (a dynamic variable varying in a disordered manner or following a given law), representing transient disturbances. This type of situation can represent transitions between different pathological behaviours or between normal and pathological physiologies. In this respect, the perspective of nonlinear dynamics is used to describe cardiac rhythms, which makes it possible to represent normal or pathological behaviours. An electronic simulation performed with the OrCAD-Pspice software for a real implementation of the cardiac system is carried out. The results obtained are in agreement with those obtained numerically.

Long-term Rate of Ventricular Arrhythmia in Autoimmune Disease.

Although selected autoimmune diseases (AIDs) have been linked to an increased risk of ventricular arrhythmias (VAs), data on the long-term rate of VAs across the spectrum of AIDs are lacking. The aim of our study was to investigate the long-term rate of VAs (a composite of ventricular tachycardia, ventricular fibrillation, ventricular flutter, or cardiac arrest) in individuals with a history of 28 different AIDs. Individuals diagnosed with an AID (2005-2018) were identified through Danish nationwide registries. Each patient with AID was matched with four individuals from the background population by age and sex. Multivariable Cox regression was used to compare the rate of VAs between the AIDs and background population, overall and according to individual AIDs. In total, 186,733 patients diagnosed with AIDs were matched with 746,932 individuals without AIDs (median age 55 years; 63% female; median follow-up 6.0 years). The 5-year cumulative incidence of VAs was 0.5% for patients with AIDs and 0.3% for matched individuals. Patients with any AIDs had a higher associated rate of VAs than matched individuals (HR 1.39 [95% CI, 1.29-1.49]). The highest HR was observed in patients with systemic sclerosis (3.86 [95% CI, 1.92-7.75]). The higher rate of VAs in patients with AIDs, compared with individuals from the background population, was more pronounced in patients without ischemic heart disease or heart failure/cardiomyopathy compared to those with these conditions (Pinteraction < 0.05). Despite a low cumulative incidence, patients with a history of AIDs had a higher relative rate of VAs than matched individuals.

Alcohol and the risk of all-cause death, atrial fibrillation, ventricular arrhythmia, and sudden cardiac arrest

The risk of having atrial fibrillation (AF) is associated with alcohol intake. However, it is not clear whether sudden cardiac arrest (SCA) and ventricular arrhythmia (VA) including ventricular tachycardia, flutter, or fibrillation have similar associations with alcohol. We aimed to evaluate the association of alcohol intake with all-cause death, new-onset AF, VA, and SCA using single cohort with a sufficient sample size. A total of 3,990,373 people without a prior history of AF, VAs, or SCA was enrolled in this study based on nationwide health check-up in 2009. We classified the participants into four groups according to weekly alcohol consumption, and evaluated the association of alcohol consumption with each outcome. We observed a significant association between mild (hazard ratio [HR] = 0.826; 95% confidence interval [CI] = 0.815–0.838) to moderate (HR = 0.930; 95% CI = 0.912–0.947) drinking with decreased risk of all-cause mortality. However heavy drinking (HR = 1.108; 95% CI = 1.087–1.129) was associated with increased all-cause death. The risk of new-onset AF was significantly associated with moderate (HR = 1.129; 95% CI = 1.097–1.161) and heavy (HR = 1.298; 95% CI = 1.261–1.337) drinking. However, the risk of SCA showed negative association with all degrees of alcohol intake: 20% (HR = 0.803; 95% CI = 0.769–0.839), 15% (HR = 0.853; 95% CI = 0.806–0.902), and 8% (HR = 0.918; 95% CI = 0.866–0.974) lower risk for mild, moderate, and heavy drinkers, respectively. Mild drinking was associated with reduced risk of VA with moderate and heavy drinking having no associations. In conclusion, the association between alcohol and various outcomes in this study were heterogeneous. Alcohol might have different influences on various cardiac disorders.

False alarm detection in intensive care unit for monitoring arrhythmia condition using bio-signals

PurposeA novel method has been proposed to reduce the false alarm rate of arrhythmia patients regarding life-threatening conditions in the intensive care unit. In this purpose, the atrial blood pressure, photoplethysmogram (PLETH), electrocardiogram (ECG) and respiratory (RESP) signals are considered as input signals.Design/methodology/approachThree machine learning approaches feed-forward artificial neural network (ANN), ensemble learning method and k-nearest neighbors searching methods are used to detect the false alarm. The proposed method has been implemented using Arduino and MATLAB/SIMULINK for real-time ICU-arrhythmia patients' monitoring data.FindingsThe proposed method detects the false alarm with an accuracy of 99.4 per cent during asystole, 100 per cent during ventricular flutter, 98.5 per cent during ventricular tachycardia, 99.6 per cent during bradycardia and 100 per cent during tachycardia. The proposed framework is adaptive in many scenarios, easy to implement, computationally friendly and highly accurate and robust with overfitting issue.Originality/valueAs ECG signals consisting with PQRST wave, any deviation from the normal pattern may signify some alarming conditions. These deviations can be utilized as input to classifiers for the detection of false alarms; hence, there is no need for other feature extraction techniques. Feed-forward ANN with the Lavenberg–Marquardt algorithm has shown higher rate of convergence than other neural network algorithms which helps provide better accuracy with no overfitting.

An Advance Study of an Efficient CNN-Grounded Deep Learning Classification Technique for the Diagnosis of IoT based Cardiac Arrhythmias

Deep Learning, or DL for short, is an emerging subfield within the larger discipline of machine learning in today's world. The study being conducted in this area is progressing at an immediate stride, and the discoveries are contributing to the progression of technology. Deep learning (DL) methods were developed with the intention of developing a general-purpose learning method that would enable the gradual learning of characteristics at multiple levels without relying on human-engineered features. This was the goal of deep learning. Because of this, the system is able to acquire intricate purposes and directly map input to output by making use of the data that it has acquired which is based on Internet of things (IoTs). This study places an emphasis on the application of CNN (Convolutional Neural Networks), which are a subcategory of DNN (Deep Neural Networks), and it develops an efficient layered CNN for the classification of ECG arrhythmias. Even while FC-ANNs (Fully Connected Artificial Neural Networks), which are sometimes referred to as Multilayer-Perceptron networks, are effective in categorising ECG arrhythmias, the optimization process for many classification networks takes a significant amount of time in terms of computation. In addition, the features extracted by engineers are what define the accuracy of the categorization of ECG arrhythmias. An improved CNN based filtering, feature abstraction, and classification prototypical is established in order to conduct an accurate analysis of an electrocardiogram (ECG). When measured against ANN, the performance was found to have an accuracy rating of 99.6%. Consequently, the CNN model that was suggested is useful to doctors in arriving at the definitive diagnosis of AFL (atrial flutter), AFIB (atrial fibrillation), VFL (ventricular flutter), and VT (ventricular tachycardia). It includes denoising, feature extraction, and categorization as part of its functionality.

Advanced integration of 2DCNN-GRU model for accurate identification of shockable life-threatening cardiac arrhythmias: a deep learning approach.

Cardiovascular diseases remain one of the main threats to human health, significantly affecting the quality and life expectancy. Effective and prompt recognition of these diseases is crucial. This research aims to develop an effective novel hybrid method for automatically detecting dangerous arrhythmias based on cardiac patients' short electrocardiogram (ECG) fragments. This study suggests using a continuous wavelet transform (CWT) to convert ECG signals into images (scalograms) and examining the task of categorizing short 2-s segments of ECG signals into four groups of dangerous arrhythmias that are shockable, including ventricular flutter (C1), ventricular fibrillation (C2), ventricular tachycardia torsade de pointes (C3), and high-rate ventricular tachycardia (C4). We propose developing a novel hybrid neural network with a deep learning architecture to classify dangerous arrhythmias. This work utilizes actual electrocardiogram (ECG) data obtained from the PhysioNet database, alongside artificially generated ECG data produced by the Synthetic Minority Over-sampling Technique (SMOTE) approach, to address the issue of imbalanced class distribution for obtaining an accuracy-trained model. Experimental results demonstrate that the proposed approach achieves high accuracy, sensitivity, specificity, precision, and an F1-score of 97.75%, 97.75%, 99.25%, 97.75%, and 97.75%, respectively, in classifying all the four shockable classes of arrhythmias and are superior to traditional methods. Our work possesses significant clinical value in real-life scenarios since it has the potential to significantly enhance the diagnosis and treatment of life-threatening arrhythmias in individuals with cardiac disease. Furthermore, our model also has demonstrated adaptability and generality for two other datasets.

Malignant arrhythmias detection using a synthesis-by-analysis modeling method of arterial blood pressure signal

Extreme bradycardia, extreme tachycardia, ventricular flutter fib, and ventricular tachycardia are four malignant arrhythmias (MAs) that lead to sudden cardiac death. It is very important to detect them in daily life. The arterial blood pressure (ABP) signal contains abundant pathological information about four MAs and is easy to be recorded under domestic conditions. Thus, a synthesis-by-analysis (SA) modeling method for ABP signal was proposed to detect the four MAs in this study. The average models of MAs and healthy subjects were obtained by SA modeling, and the change of each ABP wave was quantitively described by twelve parameters of wave models. Then, the probabilistic neural network (PNN) and random forest (RF) are trained to detect the MAs. The experimental data were employed from Fantasia and the 2015 PhysioNet/CinC Challenge databases. The SA modeling results show that some pathological and physiological changes could be extracted from the average models. The two-sample ks-test results between different groups are markedly different (h = 1, p < 0.05). The detection results show that the performances of PPN classifiers are less than that of RF. The kappa coefficients (KC) for the RF classifiers are 97.167 ± 1.46 %, 97.888 ± 0.808 %, 99.895 ± 0.545 %, 98.575 ± 1.683 % and 92.241 ± 1.517 %, respectively. The mean KC is 97.083 ± 0.67 %. Compared to the performance of some existing studies, the proposed method has better performance and is potential to diagnose MAs in m-health.

Heart Rhythm Analysis Using Nonlinear Oscillators with Duffing-Type Connections

Heartbeat rhythms are related to a complex dynamical system based on electrical activity of the cardiac cells usually measured by the electrocardiogram (ECG). This paper presents a mathematical model to describe the electrical activity of the heart that consists of three nonlinear oscillators coupled by delayed Duffing-type connections. Coupling alterations and external stimuli are responsible for different cardiac rhythms. The proposed model is employed to build synthetic ECGs representing a variety of responses including normal and pathological rhythms: ventricular flutter, torsade de pointes, atrial flutter, atrial fibrillation, ventricular fibrillation, polymorphic ventricular tachycardia and supraventricular extrasystole. Moreover, the sinoatrial rhythm variations are described by time-dependent frequency, representing transient disturbances. This kind of situation can represent transitions between different pathological behaviors or between normal and pathological physiologies. In this regard, a nonlinear dynamics perspective is employed to describe cardiac rhythms, being able to represent either normal or pathological behaviors.

Incidence of cardiac events in on-pump elective surgical interventions on the aorta and heart valves

Aim. To determine the incidence and predictors of cardiovascular events in onpump cardiac operations in modern practice.Material and methods. The study included 200 patients who underwent various elective cardiac surgical interventions. Cardiovascular events (CVEs) were determined within 30 days from the operation, according to medical records and autopsy protocols. We identified major CVEs (cardiovascular death, stroke, myocardial infarction) and minor CVEs (angina pectoris, significant ventricular arrhythmias, atrial fibrillation or flutter episodes, AV conduction disorders, etc.). A comprehensive preoperative examination was performed, including an extended echocardiography protocol and coronary angiography.Results. In 101 patients (50,05%), various CVEs were identified: 4,0% had major CVEs and 46,05% had minor CVEs and various non-cardiac complications, while perioperative mortality was 2,0%. Most ischemic CVEs, as well as most intracardiac conduction disorders, were registered during the first 3 days after surgery. In contrast, episodes of atrial fibrillation/flutter occurred 2-7 days after the intervention. There were following preoperative examination parameters with the highest prognostic value: history of heart failure, age &gt;65 years, history of myocardial infarction, occlusion of at least one coronary artery, and diabetes.Conclusion. The data obtained indicate the high efficiency of current surgical and anesthetic technologies, which lead to relatively low risk of severe and fatal events. The parameters of the preoperative examination, which determine the increased risk of intervention, are highlighted.

Trends in ventricular fibrillation/flutter mortality in US population, 1999 to 2019.

The Ventricular fibrillation and flutter (VF/VFL)-related mortality trends in the United States (US) population have not yet been investigated. We aimed to assess the trends of VT/VFL-related mortality from 1999 to 2019 among subjects aged more than 15 years old in the US. Data derived from the Centers for Disease Control and Prevention's (CDC) WONDER were analyzed between 1999 and 2019 for VF/VFL-related mortality in subjects aged more than 15 years of age. Adjusted mortality rates (AAMRs) per 100,000 people by year, sex, race and urban-rural status with relative confidence intervals (CIs) were determined. Both the average annual percent change (AAPC) and the annual percent change (APC) with 95% Cis were calculated. Between 1999 and 2019, 242,125 VT/VFL-related deaths occurred in the US. The overall AAMR steadily declined [AAPC -4.4% (95% CI: -4.7 to -4.0, p < .0001)]. Women showed a more pronounced AAMRs decline [AAPC: -4.8% (95% CI: -5.3 to -4.3, p < .0001). AAMR steadily declined in white subjects and in those of other races [AAPC: -4.5 (95% CI: -4.7 to -4.2, p < .0001) and AAPC: -4.3 (95% CI: -5.1 to -3.5, p < .001), respectively]. Conversely, African Americans showed a steadily AMMR decline between 1999 and 2007 [APC: -8.3 (95% CI: -9.2 to -7.3, p < .0001)], followed by a period of stability from 2007 to 2019 (p = .73). A similar decline was observed for the AAMR among subjects living in urban and rural areas. VT/VFL-related mortality steadily decreased between 1999 and 2019 in US. Despite the encouraging results, further efforts are needed to prevent VF/VFL-related mortality in US subjects.

Impact of mineralocorticoid receptor gene NRC2 on the prediction of arrhythmia after acute myocardial infarction

Abstract Funding Acknowledgements Type of funding sources: None. Introduction Patients with acute myocardial infarction (AMI) suffer from distress that causes a rise in cortisol (stress hormone) which acts through glucocorticoid receptors (GR) and mineralocorticoid receptors (MR). Both receptors are present in cardiomyocyte nuclei (1-4). The animal model study in 2017 showed that activated MR increases cardiomyocyte oxidative stress leading to adverse electrophysiological remodelling that causes arrhythmias. 1.4% of tachyarrhythmias which is the main cause of cardiac death occur within the first month in AMI patients. MR are encoded by the human gene NR3C2 (nuclear receptor subfamily 3 group C member (5-6). Thus, we hypothesized that NR3C2 rs2070950, rs4635799 and rs5522 gene polymorphisms might have an extensive impact on rhythm disorders that occur in a cohort of AMI patients. Aim The aim is to evaluate the impact of the NR3C2 rs2070950, rs4635799 and rs5522 genes polymorphism in patients that developed rhythm and conduction disorders after suffering AMI. Methods The study included 301 patients treated at our hospital after suffering from AMI; all study subjects underwent primary percutaneous coronary intervention (PCI) and guideline-directed medical treatment (1). Patients' blood samples that were collected upon arrival had cortisol and troponin I levels checked and SNPs of the NR3C2 gene (rs2070950, rs4635799 and rs5522) assessed. To avoid inaccuracies all patients with a previous history of coronary syndrome or PCI were excluded. Rhythm conduction disorders and NR3C2 gene polymorphism were analyzed using the exact Fisher’s test. All the statistical analyses were performed with SPSS 27.0 software. The value of p &amp;lt; 0.05 was considered statistically significant. Results Patients with ventricular and atrial events in the early phase of AMI had higher levels of serum cortisol than the patients that did not have rhythm disorders (p=0.001) (Table 1). Rhythm disorders such as ventricular tachycardia (VT), ventricular flutter (VF) and atrial flutter or atrial fibrillation (AF/AFL) that occurred during hospitalization for AMI were notably associated with rs5522 gene polymorphism. During a hospital stay for AMI higher rs5522 TT genotype frequency was noticed in patients with AF/AFL than in patients without. C allele recurrence was 19.6%. Moreover, the protective effect was detected for AF/AFL there is also a protective effect in VA. (Table 2). Despite this, the gene polymorphism and high-grade atrioventricular block (HAVB) were unrelated. Genes rs2070950 and rs4635799 were not found significant to rhythm and conduction disorders. Conclusions Patients with the rs5522 TT allele are more prone to experience a higher frequency of arrhythmias. However, if at least one rs5522 C is found it associates with a smaller risk of arrhythmias post-AMI, meaning that this gene possibly limits damaging effects on cardiomyocytes that are caused by cortisol.

Dynamical behavior analysis of the heart system by the bifurcation structures

The functioning of the heart rhythm can exhibit a wide variety of dynamic behaviours under certain conditions. In the case of rhythm disorders or cardiac arrhythmias, the natural rhythm of the heart is usually involved in the sinoatrial node, the atrioventricular node, the atria of the carotid sinus, etc. The study of heart related disorders requires an important analysis of its rhythm because the regularity of cardiac activity is conditioned by a large number of factors. The cardiac system is made up of a combination of nodes ranging from the sinus node, the atrioventricular node to its Purkinje bundles, which interact with each other via communicative aspects. Due to the nature of their respective dynamics, the above are treated as self-oscillating elements and modelled by nonlinear oscillators. By modelling the cardiac conduction system as a model of three nonlinear oscillators coupled by delayed connections and subjected to external stimuli depicting the behavior of a pacemaker, its dynamic behavior is studied in this paper by nonlinear analysis tools. From an electrocardiogram (ECG) assessment, the heart rhythm reveals normal and pathological rhythms. Three forms of ventricular fibrillation, ventricular flutter, ventricular tachycardia and atrial fibrillation are observed. The results are confirmed by the respective maximum Lyapunov exponents. Considering the cardiac nodes as microchips, using microcontroller simulation technology, the cardiac conduction system was modelled as a network of four ATmega 328P microcontrollers. A similarity with the results obtained numerically can be observed.

Распространенность, анатомо-топографические особенности и клиническое значение миокардиальных «мостиков»: ретроспективное исследование

Aim. To analyze the prevalence and anatomic-topographic features of myocardial bridges (MBs) and evaluate their role in the development of cardiovascular complications. Design. А retrospective study. Materials and methods. The study was conducted in two stages. In the first stage, to assess the prevalence and anatomic-topographic features of MBs, was retrospectively analyzed a registry of 883 coronary computed tomographic angiography (CCTA) results performed at the S.M. Kirov Military Medical Academy from 2011 to 2021. From the remaining 811 results after the initial review, 117 CCTA with MBs were selected and subjected to further detailed study. In 6 cases the CCTA was supplemented with stress-CT myocardial perfusion. In the second stage, a retrospective analysis of medical histories of 20 patients with MBs who were treated at the S.M. Kirov Military Medical Academy from 2017 to 2021 was performed for assessment the clinical significance of MBs and their role in the development of cardiovascular complications. Results. According to CCTA MBs were visualized in 14.4% of cases, in the left anterior descending artery (LAD) they were diagnosed in 84.6% of them with predominant localization in the middle segment — 94.9%. The mean length of the MBs in the LAD was 23 [17; 31] mm, depth — 1 [1; 2] mm. Atherosclerotic lesion according to classification of Coronary Artery Disease Reporting and Data System (CAD-RADS) of the LAD was detected in 58.6% of cases, of which in the proximal segment — 84.5%. According to stress-CT myocardial perfusion in asymptomatic patients, hypoperfusion was detected in 3 (50%) cases in the segments of the left ventricle, the blood supply of which comes from the LAD and its branches. Among 20 patients with dyslipidemia was detected in 80% of patients with MBs, stable angina was diagnosed in 5 (25%) cases, unstable angina and myocardial infarction — 3 (15%) patients in each cases. The assessment of the lipid spectrum revealed the elevations of total cholesterol to 5.47 ± 1.25 mmol/l and low-density lipoprotein to 3.52 ± 1.04 mmol/l, other fractions remained within normal values. In addition, various heart arrhythmias and conduction disorders were detected by 24-hour electrocardiography monitoring in patients with MBs, including supraventricular and ventricular extrasystoles, supraventricular and ventricular tachycardia, A-V blockade, atrial fibrillation and flutter and pauses greater than 2.5 seconds. Conclusion. The study confirmed the predominant character of MBs localization in the LAD and its middle segment. In addition, frequent atherosclerotic lesion of proximal segments of LAD by CAD-RADS classification was detected. The presence of association of MBs with symptoms of myocardial ischemia, dyslipidemia, as well as various arrhythmias requires searching of new approaches to early visualization of MBs, especially in the group of asymptomatic patients, in order to diagnose the pathology on time and prevent cardiovascular complications associated with it. Keywords: myocardial bridge, developmental abnormality, coronary computed tomographic angiography, dyslipidemia, myocardial ischemia, heart arrhythmias and conduction disorders.

A life-threatening arrhythmia detection method based on pulse rate variability analysis and decision tree.

Extreme bradycardia (EB), extreme tachycardia (ET), ventricular tachycardia (VT), and ventricular flutter (VF) are the four types of life-threatening arrhythmias, which are symptoms of cardiovascular diseases. Therefore, in this study, a method of life-threatening arrhythmia recognition is proposed based on pulse rate variability (PRV). First, noise and interference are wiped out from the arterial blood pressure (ABP), and the PRV signal is extracted. Then, 19 features are extracted from the PRV signal, and 15 features with highly important and significant variation were selected by random forest (RF). Finally, the back-propagation neural network (BPNN), extreme learning machine (ELM), and decision tree (DT) are used to build, train, and test classifiers to detect life-threatening arrhythmias. The experimental data are obtained from the MIMIC/Fantasia and the 2015 Physiology Net/CinC Challenge databases. The experimental results show that the DT classifier has the best average performance with accuracy and kappa coefficient (kappa) of 98.76 ± 0.08% and 97.59 ± 0.15%, which are higher than those of the BPNN (accuracy = 94.85 ± 1.33% and kappa = 89.95 ± 2.62%) and ELM (accuracy = 95.05 ± 0.14% and kappa = 90.28 ± 0.28%) classifiers. The proposed method shows better performance in identifying four life-threatening arrhythmias compared to existing methods and has potential to be used for home monitoring of patients with life-threatening arrhythmias.

DELAYED LEAD PERFORATION OF THE RIGHT ATRIUM IN THE PRESENCE OF PERSISTENT LEFT SUPERIOR VENA CAVA: A RARE COINCIDENCE

DELAYED LEAD PERFORATION OF THE RIGHT ATRIUM IN THE PRESENCE OF PERSISTENT LEFT SUPERIOR VENA CAVA: A RARE COINCIDENCE

DE-PNN: Differential Evolution-Based Feature Optimization with Probabilistic Neural Network for Imbalanced Arrhythmia Classification

In this research, a heartbeat classification method is presented based on evolutionary feature optimization using differential evolution (DE) and classification using a probabilistic neural network (PNN) to discriminate between normal and arrhythmic heartbeats. The proposed method follows four steps: (1) preprocessing, (2) heartbeat segmentation, (3) DE feature optimization, and (4) PNN classification. In this method, we have employed direct signal amplitude points constituting the heartbeat acquired from the ECG holter device with no secondary feature extraction step usually used in case of hand-crafted, frequency transformation or other features. The heartbeat types include normal, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature, ventricular escape, ventricular flutter and paced beat. Using ECG records from the MIT-BIH, heartbeats are identified to start at 250 ms before and end at 450 ms after the respective R-peak positions. In the next step, the DE method is applied to reduce and optimize the direct heartbeat features. Although complex and highly computational ECG heartbeat classification algorithms have been proposed in the literature, they failed to achieve high performance in detecting some minority heartbeat categories, especially for imbalanced datasets. To overcome this challenge, we propose an optimization step for the deep CNN model using a novel classification metric called the Matthews correlation coefficient (MCC). This function focuses on arrhythmia (minority) heartbeat classes by increasing their importance. Maximum MCC is used as a fitness function to identify the optimum combination of features for the uncorrelated and non-uniformly distributed eight beat class samples. The proposed DE-PNN scheme can provide better classification accuracy considering 8 classes with only 36 features optimized from a 253 element feature set implying an 85.77% reduction in direct amplitude features. Our proposed method achieved overall 99.33% accuracy, 94.56% F1, 93.84% sensitivity, and 99.21% specificity.