Normal Beats Research Articles

Design of DNN-Based Low-Power VLSI Architecture to Classify Atrial Fibrillation for Wearable Devices

Atrial fibrillation (AF) is a recurrent and life-threatening disease leading to rapid growth in the mortality rate due to cardiac abnormalities. It is challenging to manually diagnose AF using electrocardiogram (ECG) signals due to complex and varied changes in its characteristics. In this article, for the first time, an end-to-end edge-enabled machine learning-based VLSI architecture is proposed to classify ECG excerpts having AF from normal beats. Researchers have found that abnormal atrial activity is confined to the low-frequency range through the decades. Therefore, in the proposed work, this frequency band is directly analyzed for AF detection, which has not previously been discussed. The proposed architecture is implemented using 180-nm bulk CMOS technology consuming <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$11.098~\mu {\mathrm{ W}}$ </tex-math></inline-formula> at <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$25~ {\text {kHz}}$ </tex-math></inline-formula> and exhibits an accuracy of 92.37% for class-oriented classification and 81.60% for subject-oriented classification. The low-power realization of the proposed design, as compared to the state-of-the-art methods, makes it suitable to be used for wearable devices.

Recognizing Patterns on a Resting 12-Lead Electrocardiogram

Scenario: During an annual physical examination, a healthy 55-year-old man who works as a long-haul truck driver had a routine 12-lead electrocardiogram (ECG) recorded. Overall, he had no complaints and was asymptomatic. His body mass index was within normal limits, and he was taking simvastatin for high cholesterol and lisinopril for high blood pressure (current blood pressure, 128/78 mm Hg).Sinus rhythm at 85 beats per minute with first-degree atrioventricular (AV) block and premature ventricular contractions (PVCs) in a trigeminy pattern.Trigeminy is a pattern of PVCs occurring in a series of 3 heart beats, either 2 normal sinus beats followed by a PVC (as in this example) or 1 normal sinus beat followed by 2 PVCs. Trigeminy is not common, is often transient, and can disturb the normal contraction and cardiac output of the heart because a premature impulse interrupts sinus rhythm. In this case, there are more sinus beats than PVCs, most likely supporting normal cardiac output. The PVCs are similar in morphology, or unifocal, suggesting the origin (focus) is at 1 ventricular site. The etiology of trigeminy is not definitive, but some causes include caffeine, medications (eg, antihistamines), alcohol, anxiety, and heart disease. Of note, the PR interval is slightly prolonged (210 milliseconds), meeting criteria for a first-degree AV block. This occurs when electrical conduction through the AV node is slowed but atrial to ventricular conduction is not interrupted. In this case, the continuous rhythm strip at the bottom of the 12-lead ECG is very helpful in capturing the onset and offset of the PVCs. Also, the low R-wave amplitude may be a sign for hypertensive patients requiring further workup with echocardiography.Although this patient is asymptomatic, options to monitor the patient for a long, continuous period include portable monitors like a Holter or event recorder to improve assessment of the prevalence of the PVCs and other dysrhythmias. Potential modifications that should be recommended to this patient to avoid possible triggers include reducing caffeine intake, managing anxiety, monitoring his blood pressure, and exercising (given the sedentary nature of his profession). In general, first-degree AV block is considered benign, is not traditionally treated, and in this case was not new. However, recent epidemiological research from the Framingham study indicates a relationship between first-degree AV block and a higher risk of hospitalization for heart failure, cardiovascular mortality, and all-cause mortality. Although currently asymptomatic, the patient should monitor for potential symptoms of worsening of cardiovascular health, for example, new-onset palpitations. If symptoms develop and evidence suggests more sustained arrhythmia, an echocardiogram may be warranted.

Abstract 13: Circadian Misalignment is Associated With Impaired Heart Rate Variability in Adolescents

Introduction: Adequate sleep has been recognized by AHA as part of Life’s Essential 8 in the prevention of cardiovascular disease (CVD). The circadian system, which governs the sleep-cycle, is also involved in cardiac, metabolic and autonomic regulation. Heart rate variability (HRV), a marker of cardiac autonomic modulation (CAM), is known to predict CVD. As a result, circadian misalignment of the sleep-wake cycle, which is highly prevalent in adolescents, may impact CAM and be a potential risk factor for adverse CVD outcomes in early life. Hypothesis: We hypothesize that deviations in the circadian timing of sleep are associated with blunted HRV in adolescents. Methods: We analyzed data from 337 population-based randomly-selected adolescents from the Penn State Child Cohort (median 16 years; 47% female; 21% racial/ethnic minority) who had at least 3-night at-home actigraphy (ACT), in-lab 9-h polysomnography (PSG) and 24-h Holter-monitoring heart rate variability (HRV) data. ACT-sleep duration and sleep midpoint (SM) were calculated as the intra-individual mean total sleep time and midpoint of the sleep period, respectively. ACT-sleep variability and sleep regularity (SR) were calculated as the intra-individual standard deviation of sleep duration and sleep midpoint across nights, respectively. Frequency and time-domain HRV indices, including HR oscillations at high frequencies (HF), standard deviation between normal heart beats or R-R intervals (SDNN), and root mean square of successive differences between normal heartbeats (RMSSD), were primary outcomes. Linear regression models tested SM and SR as predictors of HRV indices, while accounting for sex, race/ethnicity, age, body mass index, ACT-sleep duration, ACT-sleep variability, and PSG-apnea/hypopnea index. Results: While there were no meaningful associations between SM or SR with daytime HRV, there were significant associations between SM with nighttime HRV. A later SM was associated with lower nighttime Log-HF, SDNN and RMSSD, yet higher nighttime LF/HF (all p&lt;0.03). For each standard deviation increase in SM (i.e., 1.5 hours later), there was a decrease of -5.50ms (1.92) in nighttime RMSSD (p=0.004). More specifically, the nighttime RMSSD of adolescents with a SM at 5:30 (i.e., sleep onset at 2:00, sleep offset at 9:00), was 18.2ms (6.7) lower (p=0.007) than that of adolescents with a SM at 2:30 (i.e., sleep onset at 23:00, sleep offset at 6:00). Conclusions: A delayed sleep phase is associated with impaired CAM in adolescents. These data support that circadian misalignment of the sleep-wake cycle may independently contribute to CVD risk.

The Intracellular Amastigote of Trypanosoma cruzi Maintains an Actively Beating Flagellum.

Throughout its complex life cycle, the uniflagellate parasitic protist, Trypanosoma cruzi, adapts to different host environments by transitioning between elongated motile extracellular stages and a nonmotile intracellular amastigote stage that replicates in the cytoplasm of mammalian host cells. Intracellular T. cruzi amastigotes retain a short flagellum that extends beyond the opening of the flagellar pocket with access to the extracellular milieu. Contrary to the long-held view that the T. cruzi amastigote flagellum is inert, we report that this organelle is motile and displays quasiperiodic beating inside mammalian host cells. Kymograph analysis determined an average flagellar beat frequency of ~0.7 Hz for intracellular amastigotes and similar beat frequencies for extracellular amastigotes following their isolation from host cells. Inhibitor studies reveal that flagellar motility in T. cruzi amastigotes is critically dependent on parasite mitochondrial oxidative phosphorylation. These novel observations reveal that flagellar motility is an intrinsic property of T. cruzi amastigotes and suggest that this organelle may play an active role in the parasite infection process. IMPORTANCE Understanding the interplay between intracellular pathogens and their hosts is vital to the development of new treatments and preventive strategies. The intracellular "amastigote" stage of the Chagas disease parasite, Trypanosoma cruzi, is a critical but understudied parasitic life stage. Previous work established that cytosolically localized T. cruzi amastigotes engage physically and selectively with host mitochondria using their short, single flagellum. The current study was initiated to examine the dynamics of the parasite flagellum-host mitochondrial interaction through live confocal imaging and led to the unexpected discovery that the T. cruzi amastigote flagellum is motile.

A Low-Power Wireless System for Predicting Early Signs of Sudden Cardiac Arrest Incorporating an Optimized CNN Model Implemented on NVIDIA Jetson.

The survival rate for sudden cardiac arrest (SCA) is low, and patients with long-term risks of SCA are not adequately alerted. Understanding SCA's characteristics will be key to developing preventive strategies. Many lives could be saved if SCA's early onset could be detected or predicted. Monitoring heart signals continuously is essential for diagnosing sporadic cardiac dysfunction. An electrocardiogram (ECG) can be used to continuously monitor heart function without having to go to the hospital. A zeolite-based dry electrode can provide safe on-skin ECG acquisition while the subject is out-of-hospital and facilitate long-term monitoring. To the ECG signal, a low-power 1 μW read-out circuit was designed and implemented in our prior work. However, having long-term ECG monitoring outside the hospital, i.e., high battery life, and low power consumption while transmission and reception of ECG signal are crucial. This paper proposes a prototype with a 10-bit resolution ADC and nRF24L01 transceivers placed 5 m apart. The system uses the 2.4 GHz worldwide ISM frequency band with GFSK modulation to wirelessly transmit digitized ECG bits at 250 kbps data rate to a physician's computer (or similar) for continuous monitoring of ECG signals; the power consumption is only 11.2 mW and 4.62 mW during transmission and reception, respectively, with a low bit error rate of ≤0.1%. Additionally, a subject-wise cross-validated, three-fold, optimized convolutional neural network (CNN) model using the Physionet-SCA dataset was implemented on NVIDIA Jetson to identify the irregular heartbeats yielding an accuracy of 89% with a run time of 5.31 s. Normal beat classification has an F1 score of 0.94 and a ROC score of 0.886. Thus, this paper integrates the ECG acquisition and processing unit with low-power wireless transmission and CNN model to detect irregular heartbeats.

Construction noise effects on human health: Evidence from physiological measures

Noise pollution caused by construction activities in urban areas is a serious problem. Construction noise can affect human health and well-being negatively. This study utilised physiological data including heart rate parameters, Respiratory Rate (RR), and Electrodermal Activity (EDA) to explore the effects of construction noise on human health. Different construction noise types (saw, jackhammer, pile driver, bulldozer), levels (55, 65, 75 and 85 dBA), and exposure durations (30, 60, 120, and 180 s) were examined in a lab-based experiment. The noise conditions were reproduced for twenty-three participants through speakers. To statistically analyse the changes in the physiological measures caused by the examined noise conditions, mixed models were utilised. The results revealed significant effects of the construction noise types on heart rate parameters including heart rate (HR), high frequency (HF), and standard deviation of the normal beat intervals (SDNN). In addition, the results showed that exposure duration significantly affects physiological responses, including RR and SDNN. This study will help to identify the non-auditory health effects of exposure to construction noise. The outputs of this research will provide critical inputs to revisit the current environmental noise regulations to protect the community against the negative health effects of construction noise more efficiently.

IoT Based System for Heart Monitoring and Arrhythmia Detection Using Machine Learning.

Internet of Things (IoT) technologies allow building a digital representation of people, objects, or physical phenomena to be available on the Internet. Thus, stakeholders can access this information from remote places or computational systems could analyze this data to find patterns, make decisions, or execute actions. For instance, a doctor could diagnose patients by analyzing the received data from an IoT system even when patients are located in a remote place. This article proposes an IoT system for monitoring electrocardiogram (ECG) signal and processing heart data in order to generate an alert when an arrhythmia is present. This system involves a Polar H10 heart sensor, machine-learning models to classify heart events, and communication technology to share and store patient's information. In the first place, the architecture of the IoT monitoring system and the communication between the components are described by discussing the designing criteria. Second, the experimentation process performs the training and the assessment of three classification algorithms, random forest, convolutional neural network, and k-nearest neighbors. The results show that k-nearest neighbor has the best accuracy percentage classifying the arrhythmias under study (premature ventricular contraction 94%, fusion of ventricular beat 81%, and supraventricular premature beat 82%); also, it is able to discern normal and unclassifiable beats with 93% and 97%, respectively.

Individuals with a previous symptomatic COVID-19 infection have altered heart rate and blood pressure variability during acute exercise.

Introduction: As the number of COVID-19 cases begin to diminish it is important to turn our attention to any long-term issues that may be associated with a prior infection. Cardiovascular defects have been noted following prior SARS-CoV-2 infections. However, less is known about how a previous infection alters the cardiovascular response to exercise. Further, differences may exist during exercise between previously SARS-CoV-2 positive individuals who had symptoms (symptomatic) relative to those who did not have symptoms (asymptomatic). We hypothesized that previously symptomatic (S) COVID-19 recoveries have an altered cardiovascular response to acute exercise relative to both control (CON; never infected), and previously COVID-19 positive asymptomatic (AS) individuals. Methods: Twenty-seven subjects (CON = 9; AS = 9; S = 9) underwent 30min of submaximal treadmill exercise. During exercise, blood pressure was recorded on the brachial artery every 5min and 3-lead electrocardiography was measured continuously. Indirect indicators of autonomic nervous system health: heart rate variability and blood pressure variability were measured during each session. Baseline mean arterial pressure (MAP) was taken prior to exercise in seated, standing and supine positions. Results: Blood pressure was similar (p > 0.05) amongst all three groups. There were no differences between average heart rate (HR; CON = 104 ± 4 BPM vs AS = 118 ± 6 BPM vs. S = 112 ± 3 BPM), mean arterial pressure (MAP; CON = 108 ± 4mmHg vs. AS = 105 ± 13mmHg vs. S = 108 ± 7mmHg) or oxygen consumption (VO2) between groups during a bout of exercise. However, the standard deviation of the inter beat intervals of normal sinus beats, a measure of heart rate variability (HRV) (CON = 138 ± 2.8m vs. AS = 156 ± 6m vs. S = 77.7 ± 11m; p < 0.05) and blood pressure variability (BPV; CON = 5.18 ± 1.1 vs. AS = 12.1 ± 0.88mmHg vs. S = 10.2 ± 10.7mmHg; p < 0.05) were different in our S group. Further, when HRV was assessed in the frequency domain the very low frequency was different during exercise in the S group relative to the other groups. Discussion: Collectively, these data suggest that a previous symptomatic SARS-CoV-2 infection may alter heart rate and blood pressure regulation during exercise.

Syncope After Transcatheter Aortic Valve Implantation: Pace or Not?

Syncope After Transcatheter Aortic Valve Implantation: Pace or Not?

A nonlinear analysis of cardiovascular diseases using multi-scale analysis and generalized hurst exponent

Congestive heart failure (CHF) and arrhythmia (ARR) are common heart diseases that affect a growing population of patients worldwide. In this work, we employ multi-scale analysis (MSA) to estimate generalized Hurst exponent (GHE) from electrocardiogram (ECG) records under CHF, ARR, and normal sinus rhythm (NSR). As a result, fractal correlations in short and long fluctuations of CHF, ARR, and NSR are measured. Then, a set of six statistical tests are applied to GHE estimates to check how they are different at each time scale between two different ECG conditions. Particularly, the goal is verify if two different ECG conditions can be statistically differentiated by short or by long fluctuations. The battery of statistical tests includes Kolmogorov–Smirnov, Kruskal–Wallis, Wilcoxon rank sum, Student t-test, Ansari–Bradley, and F-test. The results from MSA show evidence that CHF, ARR, and NSR all exhibit multi-fractal properties. Besides, the results from statistical tests revealed that long fluctuations statistically differentiate CHF and ARR, ARR and NSR, and CHF and NSR. Therefore, long fluctuations account most for the characterization of CHF, ARR, and NSR. Our findings are helpful to better understand the mechanics of heart disease and normal heart beats, and also promising to eventually designing computer-aided diagnosis systems for CHF and ARR classification.

Heart Rate Variability and Cortisol Levels Before and After a Brief Anaerobic Exercise in Handball Players.

Kayacan, Y, Makaracı, Y, Ucar, C, Amonette, WE, and Yıldız, S. Heart rate variability and cortisol levels before and after a brief anaerobic exercise in handball players. J Strength Cond Res 37(7): 1479-1485, 2023-Evaluating stress in athletes is important for monitoring overall physiologic load and is a core practice for sport performance teams. This study examined relationships between 2 metrics of training stress, heart rate variability (HRV) and cortisol, before and after intense anaerobic power testing. Electrocardiogram recordings and saliva samples were collected before and immediately after a Wingate anaerobic power test (WAnT-30) from professional handball players ( n = 20) and sedentary controls ( n = 18). Between-group differences and correlations were computed to assess study hypotheses. No differences were observed in HRV frequency-dependent parameters between groups, but in athletes, Min. R-R ( p < 0.01) and Avg.R-R ( p = 0.03) before WAnT-30 and the percentage of successive normal cardiac beat intervals greater than 50 milliseconds (i.e., pNN50; p = 0.03) after WAnT-30 were elevated. A high positive correlation was detected between the pretest and post-test cortisol levels in athletes ( p = 0.0001; r = 0.87) but not in sedentary individuals. No correlations were observed between the cortisol levels and WAnT-30 power parameters in either group. Relationships were evident in the standard deviation of RR intervals ( p = 0.02, r = -0.53), square root of the mean squared difference of successive RR intervals ( p = 0.043, r = -0.46), very low frequency ( p = 0.032; r = -0.480), high-frequency ( p = 0.02; r = -0.52) variables, and pretesting cortisol in athletes. These findings suggest that HRV analysis is a valuable tool for examining cardiovascular regulation, independent of cortisol; the data may provide valuable information for performance teams in evaluating acute stress.

Heart Rate Variability Impairment Is Associated with Right Ventricular Overload and Early Mortality Risk in Patients with Acute Pulmonary Embolism.

The association between heart rate variability (HRV) and mortality risk of acute pulmonary embolism (APE), as well as its association with right ventricular (RV) overload is not well established. We performed an observational study on consecutive patients with confirmed APE. In the first 48 h after admission, 24 h Holter monitoring with assessment of time-domain HRV, echocardiography and NT-proBNP (N-terminal pro-B-type natriuretic peptide) measurement were performed in all participants. We pre-examined 166 patients: 32 (20%) with low risk of early mortality, 65 (40%) with intermediate-low, 65 (40%) with intermediate-high, and 4 (0.02%) in the high risk category. The last group was excluded from further analysis due to sample size, and finally, 162 patients aged 56.3 ± 18.5 years were examined. We observed significant correlations between HRV parameters and echocardiographic signs of RV overload. SDNN (standard deviation of intervals of all normal beats) correlated with echocardiography-derived RVSP (right ventricular systolic pressure; r = -0.31, p = 0.001), TAPSE (tricuspid annulus plane systolic excursion; r = 0.21, p = 0.033), IVC (inferior vena cava diameter; r = -0.27, p = 0.002) and also with NT-proBNP concentration (r = -0.30, p = 0.004). HRV indices were also associated with APE risk stratification, especially in the low-risk category (r = 0.30, p = 0.004 for SDNN). Univariate and multivariate analyses confirmed that SDNN values were associated with signs of RV overload. In conclusion, we observed a significant association between time-domain HRV parameters and echocardiographic and biochemical signs of RV overload. Impaired HRV parameters were also associated with worse a clinical risk status of APE.

Heart rate variability responses to cognitive stress in fibromyalgia are characterised by inadequate autonomous system stress responses: a clinical trial

Fibromyalgia (FM) is associated with sympathetically dominant dysautonomia, but the connection between dysautonomia and FM symptoms is unclear. Dysautonomia can be analysed with heart rate variability (HRV) and it has been proposed that FM patients comprise subgroups with differing profiles of symptom severity. In our study, 51 female FM patients aged 18 to 65 years and 31 age-matched healthy female controls followed a 20-min protocol of alternating relaxation and cognitive stress (mental arithmetic). Heart rates and electrocardiograms were registered. The HRV measures of heart rate (HR), mean interval between heart beats (RRmean), root mean squared interval differences of successive beats (RMSSD), and the standard deviation of intervals between normal heart beats (SDNN) were analysed with generalized linear modelling. Features in HRV reactivity which differed between FM patients and controls were used to cluster the FM patients and cluster characteristics were analysed. FM patients had higher baseline HR (72.3 [SD 12.7] vs 64.5 [7.80], p < 0.001) and lower RRmean (0.844 [0.134] vs 0.934 [0.118], p = 0.002), compared with controls. They also reacted to repeated cognitive stress with an attenuated rise in HR (− 4.41 [95% CI − 7.88 to − 0.93], p = 0.013) and attenuated decrease of RRmean (0.06 [95 CI 0.03 to 0.09], p < 0.001), compared with controls. Clustering of FM patients by HRV reactivity resulted in three clusters characterised by (1) normal levels of HRV and HRV reactivity with low levels of depressive mood and anxiety, (2) reduced levels of HRV and impaired HRV reactivity with increased levels of depressive mood and high levels of anxiety, and (3) lowest HRV and most impaired HRV reactivity with the highest scores for depressive mood and anxiety. Our results show that FM patients have lower HRV than healthy controls and their autonomous reactions to cognitive stress are attenuated. Dysautonomia in FM associates with mood disturbance.Trial registration ClinicalTrials.gov (NCT03300635). Registered October 3 2017—Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT03300635.

Enhanced electrocardiogram machine learning-based classification with emphasis on fusion and unknown heartbeat classes.

Building an electrocardiogram (ECG) heartbeat classification model is essential for early arrhythmia detection. This research aims to build a reliable model that can classify heartbeats into five heartbeat types: normal beat (N), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), fusion beat (F), and unknown beat (Q), with a focus on enhancing the predictions of the uncommon Q and F heartbeats. The base dataset used is the MIT-BIH SupraVentricular Database, which was used to train and compare the performance of five machine learning models: logistic regression, Random Forest (RF), K-nearest neighbor, linear support vector machine, and linear discriminant analysis. In addition to using the synthetic minority oversampling technique, data extracted from multiple databases for the F and Q classes were combined with the original base dataset. These methods resulted in significant improvement in the recall for the rare F and Q classes when compared to the literature. The RF algorithm produced the best performance with an accuracy of 97% and recall values equal to 97%, 93%, 95%, 95%, and 30% for N, SVEB, VEB, F, and Q, respectively.

Clinical Validation of a Capacitive Electrocardiogram Cushion Utilized for Arrhythmias Monitoring

Textile capacitively-coupled (CC) electrodes have the potential of being integrated into home textiles to realize long-term cardiac surveillance, since they are more comfortable and convenient than conventional contact electrodes. Previous study mainly focused on the measurement performance of CC-based electrocardiogram (ECG) devices, but the diagnostic value of these novel devices, such as capability of supporting preliminary arrhythmia diagnosis, has not been investigated comprehensively. In this study, we proposed a CC-based ECG cushion and assessed measurement performance and diagnostic value by a clinical test on 4 healthy people and 7 arrhythmia patients. In addition to precise measurement of critical ECG structures (true positive rate of R waves: 0.994±0.006, mean absolute error of RR intervals: 1.690±1.331 ms), the proposed cushion can provide valuable information, comparable with the Holter, for cardiologists to distinguish the normal beats, ventricular beats and premature supraventricular contractions during long-term monitoring. In conclusion, the proposed cushion is verified to provide enough signal details for preliminary diagnosis of arrhythmia, as a promising system for disease screen and danger alarm of arrhythmia in certain scenario of long-term cardiac surveillance at home.

Interpatient Heartbeat Classification Using Modified Residual Attention Network With Two-Phase Training and Assistant Decision

State-of-the-art studies on automatic heartbeat classification have made efforts to improve supraventricular ectopic beat (SVEB) detection, but resulted in a low positive predictive value (PPV) of SVEB and poor performance of other categories under the interpatient paradigm. This article proposes a novel algorithm for heartbeat classification by the means of deep learning combined with feature extraction, which enhances the performance and can be applied to an automatic electrocardiogram (ECG) analysis. It is an improved residual attention network (IraNet) that combines attention module, residual inception block, and bidirectional long short-term memory (BiLSTM) layer to process single heartbeat segments directly. A two-phase training method is presented to change the weights in a planned way to deal with the imbalance of distinguishable features. An assistant decision for the deep learning-based model enhances the PPV of SVEB effectively. Under the interpatient paradigm on the Massachusetts Institute of Technology and Beth Israel Hosipital (MIT-BIH) arrhythmia database, the overall accuracy (Acc) of four classes achieves 0.9548. For SVEB class, the PPV is significantly improved to 0.7557 with the sensitivity (Sen) and an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score of 0.7392 and 0.7474, respectively. For ventricular ectopic beat (VEB) class, the Sen, PPV, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score achieve 0.9575, 0.8500, and 0.9005, respectively, and the numbers are 0.9663, 0.9873, and 0.9767 for normal beat class. For fusion beat class, the numbers are 0.7964, 0.3597, and 0.4954, respectively. The proposed algorithm gets competitive results with the state-of-the-art studies, and there is a notable improvement in the detection of SVEB

Simple, efficient, and generalized ECG signal quality assessment method for telemedicine applications

Electrocardiogram (ECG) signals recorded by paramedics in an unsupervised environment are prone to errors and noise due to factors such as electrode misplacements and daily activities during prolonged monitoring. Signal Quality Assessment (SQA) systems can prevent false diagnoses by automated arrhythmia detection systems and reduce the workload of cardiologists. However, current SQA methods are quite complex and/or exhibit poor performances in presence of certain arrhythmias. This study proposed a novel SQA method consisting of three main steps: (1) feasibility conditions check, (2) average beat correlation algorithm, and (3) beat clustering algorithm. The system uses empirical probability functions to automatically adapt the quality score according to the presence of pathological beats and/or noises. We evaluated the proposed method on three datasets and considered both three-quality classes ('Bad', 'HR' and 'Diagnostic') and two-quality classes ('Acceptable' and 'Unacceptable'). For the three-class classification, we obtained an average accuracy of 81.42 % while for the two-class, our algorithm achieved an average sensitivity of 94.59 %, a specificity of 98.38 %, and an accuracy of 97.10 %. The results show that our method achieves high accuracy, specificity and generalizability, outperforming the simple heuristic rule, machine learning, and deep learning methods. Additionally, the algorithm requires less computational time, making it suitable for telemedicine applications.

Acute Severe Heart Failure Reduces Heart Rate Variability: An Experimental Study in a Porcine Model.

There are substantial differences in autonomic nervous system activation among heart (cardiac) failure (CF) patients. The effect of acute CF on autonomic function has not been well explored. The aim of our study was to assess the effect of experimental acute CF on heart rate variability (HRV). Twenty-four female pigs with a mean body weight of 45 kg were used. Acute severe CF was induced by global myocardial hypoxia. In each subject, two 5-min electrocardiogram segments were analyzed and compared: before the induction of myocardial hypoxia and >60 min after the development of severe CF. HRV was assessed by time-domain, frequency-domain and nonlinear analytic methods. The induction of acute CF led to a significant decrease in cardiac output, left ventricular ejection fraction and an increase in heart rate. The development of acute CF was associated with a significant reduction in the standard deviation of intervals between normal beats (50.8 [20.5−88.1] ms versus 5.9 [2.4−11.7] ms, p < 0.001). Uniform HRV reduction was also observed in other time-domain and major nonlinear analytic methods. Similarly, frequency-domain HRV parameters were significantly changed. Acute severe CF induced by global myocardial hypoxia is associated with a significant reduction in HRV.

Ultra Short Heart Rate Variability Predicts Clinical Outcomes in Patients with a Clinical Presentation Consistent with Myocarditis: A Derivation Cohort Analysis.

Myocarditis prognosis varies substantially, hence identification of novel prognostic factors is crucial. The prognostic role of ultra-short heart-rate variability (HRV) in myocarditis remains unknown. In a retrospective study, adult patients admitted to a tertiary hospital due to clinically suspected myocarditis were included. Clinical, laboratory and HRV parameters were assessed as predictors of severe short term complications (heart failure (HF), dilated cardiomyopathy—DCM, ventricular arrhythmia—VA and death), utilizing logistic regression (LR). Accuracy was evaluated with receiver operating characteristic (ROC) curve area under the curve (AUC). HRV indices included standard deviation of normal beat intervals (SDNN) and root mean square of successive differences (RMSSD). 115 patients, aged 34 (±13) years old, were examined. Six patients (5%) developed severe HFrEF. RMSSD was included in a multivariate LR model (RMSSD < 10.72 ms adjusted odds ratio (AOR) 14.056, p-value 0.024). Model classification accuracy was very good, with an AUC of 86%. Eight patients (7%) developed DCM. RMSSD < 10.72 ms was included in a multivariate classification model (AOR 8.826, p-value 0.013); model classification AUC of 82%. HRV did not predict development of VA or death. SDNN and especially RMSSD may be prognostic indicators in myocarditis.

Automated Detection of Abnormalities in ECG signals using Deep Neural Network

The electrocardiogram (ECG) is a diagnostic procedure that uses a skin electrode to record the heart's electrical activity. Heart diseases are the leading cause of mortality globally, and they have significant monetary cost. In the clinic, automated detection and classification technology of abnormalities in heart beats can assist physicians in making prompt and accurate medical diagnoses. This paper concentrates on two proposed models: Model A: 1-D 8-Layer CNN Model and Model B: 1- D CNN and the LSTM model to characterise ECG data into five categories: normal beat, right bundle branch block beat, left bundle branch block beat, premature ventricular contraction beat, and atrial premature beat. The data used to create and validate the models is obtained from the MIT-BIH Dataset, which comprises of 48 half-hour samples of two-lead continuous ECG signals obtained from 48 individuals. The dataset is divided into two files-.csv and.txt. For each sample, the.csv files include the readings collected from both leads. The experimental results show that Model A has an Accuracy = 99.68%, Precision = 99.23%, and a F1 score = 99.22%. And Model B has an Accuracy= 99.51%, Precision = 98.76%, and a F1 score = 98.76%. Our study aims to assist the medical sector by reducing the diagnoses time by automating the process of detecting arrythmias.