Search

Sleep disorders can have harmful consequences in both the short and long term. They can lead to attention deficits, as well as cardiac, neurological and behavioral repercussions. One of the most widely used methods for assessing sleep disorders is polysomnography (PSG). A major challenge associated with this method is all the cables needed to connect the recording devices, making the examination more intrusive and usually requiring a clinical environment. This can have potential consequences on the test results and their accuracy. One simple way to assess the state of the central nervous system (CNS), a well-known indicator of sleep disorder, could be the use of a portable medical device. With this in mind, we implemented a simple model using both the RR interval (RRI) and its second derivative to accurately predict the awake and napping states of a subject using a feature classification model. For training and validation, we used a database providing measurements from nine healthy young adults (six men and three women), in which heart rate variability (HRV) associated with light-on, light-off, sleep onset and sleep offset events. Results show that using a 30 min RRI time series window suffices for this lightweight model to accurately predict whether the patient was awake or napping. [ABSTRACT FROM AUTHOR]

Introduction: Limited data exist on heart rate stabilization in the domiciled nature of phase I clinical studies, particularly when frequent measurements of QT intervals are involved. The present analysis aimed to evaluate heart rate stability in the domiciled nature of, and stabilization after a short exercise. Methods: Fifty‐six healthy male subjects were included in this analysis. Data during a domiciled clinical setting and after a short exercise were analysed. Mean values of 30 s intervals of collected electrocardiographical data (PR, RR, QT and QTcF intervals) during a 10‐min supine resting period in a domiciled nature or after walking up and down three stories (100 steps) were compared to baseline values using paired t‐tests or compared to the intrasubject standard deviation. Results: Stable heart rates and stable QTcF intervals observed immediately upon assuming a supine position in the domiciled clinical setting. After the short exercise, PR interval and RR interval were significantly (p < 0.05) shorter for up to 120 s (mean value −9.8 ± 7.2 ms) and 30 s (−160 ± 165 ms, p < 0.05), respectively. QT and QTcF intervals were significantly (p < 0.05) shorter for up to 90 and 120 s postexercise, respectively. Both QT and QTcF intervals stabilized after 2 min, but QT interval remained prolonged while QTcF interval returned to baseline levels. Conclusion: In a clinical setting, male volunteers do not require a waiting period for electrocardiographic parameter normalization. However, accurate measurement of these parameters following a short exercise necessitates a minimum 2‐min resting interval. [ABSTRACT FROM AUTHOR]

BACKGROUND: A Polar heart rate monitor is a device that measures RR intervals, but has not been correlated to accurately measure the series of RR interval signals between the ECG and the Polar ® Heart Rate Monitor Interface (HRMI) Board at rest. OBJECTIVE: The aim of the study was to evaluate the temporal cross-correlations between the Polar ® HRMI Board and an ECG to measure the series of RR intervals at rest. METHODS: The sample consisted of eighteen healthy male subjects and they were instructed to lie in the supine position at rest while breathing normally and a time window of the last 2 min was recorded to analyse RR intervals were obtained for each subject with a Polar ® HRMI Board and an ECG. Cross-correlation analysis of RR interval signals between methods and reliability was expressed by Bland and Altman analysis. RESULTS: The cross-correlation was excellent, resulting in a mean of 0.98 ± 0.01 and no lag or delay between the signals. The bias was 0.03 ± 0.08 s or 8.0% for MeanRRi from Polar ® HRMI Board and ECG, no significant difference. CONCLUSIONS: The Polar ® HRMI Board is acceptable for assessment of serial RR intervals. The results support the reliability of the Mean RR interval compared to a resting ECG. [ABSTRACT FROM AUTHOR]

Objectives: The Trier social stress test (TSST) is one of the most reliable and widely used laboratory tests for evaluating the physiological stress response. We developed a virtual reality-based TSST (VR-TSST) and investigated the physiological responses to this test in patients with psychosis and healthy controls (HCs). Methods: The participants comprised 60 patients with psychosis and 66 HCs. The VR-TSST consisted of three scenarios: a resting phase (baseline; 2 min), a job interview (5 min), and a mental arithmetic task (5 min). Blood cortisol levels were measured at baseline, during the test, and at 5–10 min and 30 min after the test. The skin conductance level, heart rate, and RR intervals were measured at baseline, during the job interview, and during the arithmetic task. Results: The VR-TSST produced no discernible cortisol response in patients with psychosis compared to the HCs. However, a higher skin conductance level and heart rate and shorter RR intervals were found in the patients than in the HCs at baseline, during the job interview, and during the arithmetic task. Conclusion: These findings suggest that the current version of the VR-TSST induces stronger autonomic and cardiovascular, but not endocrine, responses in patients with psychosis than in HCs. The VR-TSST could be a valuable tool to evaluate or train the stress response in patients with psychosis. [ABSTRACT FROM AUTHOR]

Sleep disorders can have harmful consequences in both the short and long term. They can lead to attention deficits, as well as cardiac, neurological and behavioral repercussions. One of the most widely used methods for assessing sleep disorders is polysomnography (PSG). A major challenge associated with this method is all the cables needed to connect the recording devices, making the examination more intrusive and usually requiring a clinical environment. This can have potential consequences on the test results and their accuracy. One simple way to assess the state of the central nervous system (CNS), a well-known indicator of sleep disorder, could be the use of a portable medical device. With this in mind, we implemented a simple model using both the RR interval (RRI) and its second derivative to accurately predict the awake and napping states of a subject using a feature classification model. For training and validation, we used a database providing measurements from nine healthy young adults (six men and three women), in which heart rate variability (HRV) associated with light-on, light-off, sleep onset and sleep offset events. Results show that using a 30 min RRI time series window suffices for this lightweight model to accurately predict whether the patient was awake or napping.

Abstract Angina pectoris is associated with adverse cardiovascular events. In this study, a Bi-directional Long Short-Term Memory (Bi-LSTM) prediction model with the Attention layer was established to explore the predictive value of the resting-state RR interval time series on the occurrence of angina pectoris. The data of this cohort study were from the Sleep Heart Health Study database, 2,977 people were included with the follow-up of 15 years. We used the RR interval time series of electrocardiogram signals in the resting state. The outcome variables were any angina events during the follow-up. We randomly divided 2,977 participants into training (n = 2680) and testing sets (n = 297) with a partition ratio of 9:1. The prediction model of Bi-LSTM with Attention layer was developed and the predictive performance was assessed. 1,236 had angina pectoris and 1,741 patients did not have angina pectoris during the follow-up period. The predictive performance of the Bi-LSTM model was great with the value of accuracy = 0.913, area under the curve (AUC) = 0.922, precision = 0.913 in the testing set. RR intervals may be the potential predictors of angina events. It is more and more convenient to obtain heart rate with the development of wearable devices; the Bi-LSTM prediction model established in this study is expected to provide support for the intelligent prediction of angina pectoris events.

Obstructive sleep apnea (OSA) atau sleep apnea adalah gangguan tidur langka yang memerlukan penggunaan sinyal aktivitas listrik, biasa disebut sebagai elektrogram (ECG), untuk dideteksi. Sinyal ECG terdiri dari bentuk gelombang, durasi, ritme bentuk gelombang, dan orientasi sinyal, yang dapat digunakan ahli jantung untuk mengevaluasi kondisi jantung pasien. Tujuan dari penelitian ini adalah untuk mendeteksi sleep apnea menggunakan dataset ECG yang ada. Sistem pendeteksi sleep apnea ini diharapkan mampu mendeteksi gangguan pada pasien secara dini dan membantu dokter mendiagnosis pasien secara lebih akurat dan cepat sehingga dapat memberikan penanganan lebih lanjut. Penelitian ini mengusulkan bagaimana mendeteksi sleep apnea dengan perangkat lunak dengan menggunakan parameter statistik dari sinyal interval RR dalam dataset sinyal ECG dan kemudian mengklasifikasikannya menggunakan metode DecisionTree. Proses deteksi sleep apnea yang peneliti usulkan menggunakan interval RR dan proses decision tree memiliki tingkat akurasi 99,5%.

Objective To explore the effect of the constant and variable nature of RR interval on the position and trend of ECG scatter plot, and to summarize the application and analytic techniques of differential method of constants and variables in rapid analysis of ambulatory electrocardiography (AECG). Methods Combined with the RR interval characteristics of classic cases such as premature ventricular contraction (PVC), consecutive PVC and atrial premature beats, we analyzed the relationship between the position and trend of the characteristic point set, and the constant and variable nature of RR interval. The analytical strategy of differential method of constants and variables were summarized. Results In the time scatter plot, when RR interval is a constant, the trend is horizontal (such as NV, VV layer, etc. ); when RR interval is a variable, the scatter plot is manifested by fluctuating up and down (such as NN, SN, VN layer, etc. ). In the Lorenz scatter plot, when the abscissa is a constant, the characteristic point set is vertically distributed ( such as NVN, VVN point set, etc. ); when the ordinate is a constant, the characteristic point set is horizontally distributed (such as NNV, VNV point set, etc. ); when the abscissa and ordinate are both constants, the distribution of the characteristic point set is localized (such as NVV, VVV point set, etc. ). When the abscissa and ordinate are both variables, the characteristic point set has a oblique distribution (such as VNN, NNN point set, etc. ), and the slope of its principal axis depends on the ratio of the coefficients of the two variables according to the principal of the differential calculus. Conclusion The constant and variable nature of RR interval determines the position and trend of ECG scatter plot. The constant and variable rapidly identified by scatter plot technique can reveal parts of the electrophysiological mechanism of arrhythmia, which is similar to a natural electrophysiological examination. Differential method of constants and variables is an effective method for analyzing ECG scatter plot, and it is also a basic skill to analyze AECG quickly. [ABSTRACT FROM AUTHOR]

Age is an important determinant of heart rate variability (HRV) in healthy individuals. The incidence of arrhythmia is high in patients with mitral valve prolapse (MVP). However, the correlation of HRV in patients with MVP in different age groups is not well established. We presumed that increasing age would be prospectively associated with declining HRV measurement in MVP. Sixty patients with MVP and 120 control individuals were included and underwent 24 h HRV analysis. No significant difference was found in all parameters calculated in the time domain or in the frequency domain between the two groups. However, as patients' age increased, a significant time domain (SDNN, RMSSD, NN50, and pNN50) decline was found in the MVP group, but not in the control group. This suggests that patients with MVP may have autonomic nervous system involvement that increases the risk of arrhythmia and heart disease with increasing age. [ABSTRACT FROM AUTHOR]

Classification of interbeat interval time-series which fluctuates in an irregular and complex manner is very challenging. Typically, entropy methods are employed to quantify the complexity of the time-series for classifying. Traditional entropy methods focus on the frequency distribution of all the observations in a time-series. This requires a relatively long time-series with at least a couple of thousands of data points, which limits their usages in practical applications. The methods are also sensitive to the parameter settings. In this paper, we propose a conceptually new approach called attention entropy, which pays attention only to the key observations. Instead of counting the frequency of all observations, it analyzes the frequency distribution of the intervals between the key observations in a time-series. Attention entropy does not need any parameter to tune, it is robust to the time-series length, and requires only linear time to compute. Experiments show that it outperforms fourteen state-of-the-art entropy methods evaluated by real-world datasets. It achieves average classification accuracy of AUC = 0.71 while the second-best method, multiscale entropy, achieves AUC = 0.62 when classifying four groups of people with a time-series length of 100. [ABSTRACT FROM AUTHOR]

Background: Wearable technologies for monitoring cardiovascular parameters, including electrocardiography (ECG) and impedance cardiography (ICG), propose a challenging research subject. The expectancy for wearable devices to be unobtrusive and miniaturized sets a goal to develop smarter devices and better methods for signal acquisition, processing, and decision-making. Methods: In this work, non-standard electrode placement configurations (EPC) on the thoracic area and single arm were experimented for ECG signal acquisition. The locations were selected for joint acquisition of ECG and ICG, targeted to suitability for integrating into wearable devices. The methodology for comparing the detected signals of ECG was developed, presented, and applied to determine the R, S, and T waves and RR interval. An algorithm was proposed to distinguish the R waves in the case of large T waves. Results: Results show the feasibility of using non-standard EPCs, manifesting in recognizable signal waveforms with reasonable quality for post-processing. A considerably lower median sensitivity of R wave was verified (27.3%) compared with T wave (49%) and S wave (44.9%) throughout the used data. The proposed algorithm for distinguishing R wave from large T wave shows satisfactory results. Conclusions: The most suitable non-standard locations for ECG monitoring in conjunction with ICG were determined and proposed. [ABSTRACT FROM AUTHOR]

A sharp deterioration of the patient’s condition against the backdrop of the development of life-threatening arrhythmias with symptoms of acute heart failure (AHF), multiple organ dysfunction syndrome (MODS) or cerebral edema (CE) can lead to the death of the patient. Since the known methods of automated diagnostics currently cannot accurately and promptly determine that the patient is in a life-threatening condition leading to the fatal outcome caused by AHF, MODS or CE, there is a need to develop appropriate methods. One of the ways to identify predictors of such a state is to apply machine learning methods to the collected datasets. In this article, we consider using data analysis methods to test the hypothesis that there is a predictor of death risk assessment, which can be derived from the previously obtained values of the ECG intervals, which gives a statistically significant difference for the ECG of the two groups of patients: those who suffered deterioration leading to the fatal outcome caused be MODS, AHF or CE, and those with favorable outcome. A method for unifying ECG data was proposed, which allow, based on the sequence of RR and QT intervals, to the construct of a number that is a characteristic of the patient's heart condition. Based on this characteristic, the patients are classified into groups: the main (patients with fatal outcome) and control (patients with favorable outcome). The resulting classification method lays the potential for the development of methods for identifying the patient's health condition, which will automate the detection of its deterioration. The novelty of the result lies in the confirmation of the hypothesis stated above, as well as the proposed classification criteria that allow solving the urgent problem of an automatic detection of the deterioration of the patient's condition.

Aritmia merupakan salah satu gangguan jantung, yang mungkin tidak berbahaya dalam waktu dekat, tetapi dapat mengakibatkan abnormalitas jangka panjang. Meskipun tidak berbahaya, harus ada penanganan medis yang segera dilakukan dan perubahan lifestyle menjadi lebih baik. Deteksi aritmia umumnya dilakukan dengan elektrokardiograf (EKG) long recording menggunakan monitor Holter dan kemudian dianalisis ritmenya. Perekaman dengan Holter yang memerlukan waktu beberapa hari dapat mengganggu fisiologis pasien. Banyak penelitian telah dilakukan untuk membangun algoritme pendeteksian aritmia, dengan beragam sumber data, fitur, dan juga metode pendeteksian. Namun, permasalahan yang umum dihadapi oleh banyak peneliti adalah masalah waktu komputasi dan kompleksnya fitur yang dideteksi. Studi ini dilakukan untuk melakukan review terhadap penelitian yang sudah dilakukan terkait dengan penggunaan data, fitur, dan juga metode deep learning yang dapat menyelesaikan masalah waktu komputasi dan memungkinkan implementasi pada wearable devices. Studi diawali dengan pencarian literatur terkait, kemudian melihat basis data yang digunakan untuk membangun model deteksi. Selanjutnya, review dilanjutkan dengan menelaah fitur EKG yang digunakan dan juga metode deep learning yang diimplementasikan. Dari hasil review yang dilakukan, data yang umum digunakan adalah data yang bersumber dari dataset MIT-BIH, meskipun penggunaan data dinilai masih perlu pre-processing yang cukup rumit. Convolutional neural network (CNN) merupakan metode yang banyak digunakan, walaupun waktu komputasi menjadi salah satu pertimbangan. Analisis yang paling tepat untuk pendeteksian gangguan ritme dan memiliki waktu komputasi yang rendah adalah fitur interval sinyal EKG dengan analisis di domain waktu. Fitur tersebut nantinya akan digunakan sebagai masukan deep learning. Dengan begitu, waktu komputasi akan dapat banyak dikurangi, terutama ketika diterapkan pada wearable devices.

The effects of thermotherapy on autonomic nervous system activity and subjective sensations of fatigue and arousal are unclear. This study compared the effects of capacitive and resistive electric transfer (Cret) interventions (deep thermotherapy) and hot packs (superficial thermotherapy) on autonomic nervous system activity in healthy young women (n = 16). Heart rate and RR interval were measured using electrocardiography, and the coefficient of variation (CV) of the RR interval was used to evaluate autonomic nervous system activity. The subjective relaxation effect was evaluated using the Roken Arousal Scale (RAS) - a fatigue arousal index. The intervention was performed on the lumbar region for 20 minutes for both Cret and hot pack. After each intervention, the CV values increased only in the Cret condition, whereas the heart rate decreased in both conditions. This suggests that parasympathetic activity was enhanced in the Cret condition. In contrast, the subjective relaxation evaluation observed a psychological relaxation effect under both conditions. Our results suggest that Cret application in the lumbar region has greater relaxation effects than hot pack application in the same region. [ABSTRACT FROM AUTHOR]

This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluated on the test set. Optimal DenseNet architectures with the number of neurons in sequential [1st, 2nd, 3rd] hidden layers were assessed for sensitivity and specificity: DenseNet [16,16,0] with primary leads (I or II) had 87.9–88.3 and 90.5–91.5%; DenseNet [32,32,32] with six limb leads had 90.7 and 94.2%; DenseNet [32,32,4] with six chest leads had 92.1 and 93.2%; and DenseNet [128,8,8] with all 12 leads had 91.8 and 95.8%, indicating sensitivity and specificity values, respectively. Mean SHAP values on the entire test set highlighted the importance of RRi-mean (100%), RR-std (84%), and atrial synchronization (40–60%) for the PQa-mean (aVR, I), PQi-std (V2, aVF, II), and PQi-mean (aVL, aVR). Our focus on finding the strongest AV synchronization predictors of AF in 12-lead ECGs would lead to a comprehensive understanding of the decision-making process in advanced neural network classifiers. DenseNet self-learned to rely on a few ECG behavioral characteristics: first, characteristics usually associated with AF conduction such as rapid heart rate, enhanced heart rate variability, and large PQ-interval deviation in V2 and inferior leads (aVF, II); second, characteristics related to a typical P-wave pattern in sinus rhythm, which is best distinguished from AF by the earliest negative P-peak deflection of the right atrium in the lead (aVR) and late positive left atrial deflection in lateral leads (I, aVL). Our results on lead-selection and feature-selection practices for AF detection should be considered for one- to twelve-lead ECG signal processing settings, particularly those measuring heart rate, AV conduction times, and P-/f-wave amplitudes. Performances are limited to the AF diagnostic potential of these three metrics. SHAP value importance can be used in combination with a human expert's ECG interpretation to change the focus from a broad observation of 12-lead ECG morphology to focusing on the few AV synchronization findings strongly predictive of AF or non-AF arrhythmias. Our results are representative of AV synchronization findings across a broad taxonomy of cardiac arrhythmias in large 12-lead ECG databases. [ABSTRACT FROM AUTHOR]

BackgroundIncreased heart rate and a prolonged QT interval are important risk factors for cardiovascular morbidity and mortality, and can be influenced by the use of various medications, including tricyclic/tetracyclic antidepressants (TCAs). We aim to identify genetic loci that modify the association between TCA use and RR and QT intervals.Methods and resultsWe conducted race/ethnic-specific genome-wide interaction analyses (with HapMap phase II imputed reference panel imputation) of TCAs and resting RR and QT intervals in cohorts of European (n=45 706; n=1417 TCA users), African (n=10 235; n=296 TCA users) and Hispanic/Latino (n=13 808; n=147 TCA users) ancestry, adjusted for clinical covariates. Among the populations of European ancestry, two genome-wide significant loci were identified for RR interval: rs6737205 in BRE (β=56.3, pinteraction=3.9e-9) and rs9830388 in UBE2E2 (β=25.2, pinteraction=1.7e-8). In Hispanic/Latino cohorts, rs2291477 in TGFBR3 significantly modified the association between TCAs and QT intervals (β=9.3, pinteraction=2.55e-8). In the meta-analyses of the other ethnicities, these loci either were excluded from the meta-analyses (as part of quality control), or their effects did not reach the level of nominal statistical significance (pinteraction>0.05). No new variants were identified in these ethnicities. No additional loci were identified after inverse-variance-weighted meta-analysis of the three ancestries.ConclusionsAmong Europeans, TCA interactions with variants in BRE and UBE2E2 were identified in relation to RR intervals. Among Hispanic/Latinos, variants in TGFBR3 modified the relation between TCAs and QT intervals. Future studies are required to confirm our results.

Heart rate is a vital sign that holds important information about cardiac signals. The measurement of heart rate is of particular interest since it reflects the dynamic changes of cardiac functions. Close examination of electrocardiogram (ECG) morphology is used to determine the specific value of heart rate as well as to distinguish between normal or abnormal heart functioning. Since ECG signal is contaminated by various noise components and artifacts like baseline wandering (BLW), power line interference (PLI), motion artifacts and electrode motion. Therefore, it is an immense task to separate the preferred signal from these noise contents and to measure physiological heart rate. Hence, this paper firstly presents wavelet transform based method to remove PLI and BLW noises, the major sources affecting recorded ECG. Furthermore for analyzing ECG signals and identifying characteristics features two methods have been proposed to calculate heart rate. They are: (i) temporal characteristics-based timing intervals between two consecutive R-peaks and (ii) local frequency-based ECG signal analysis used to identify number of R-peaks. At last according to the standard range of heart beats per minute, classification of normal and abnormal ECG is done and results obtained from both methods are compared. It includes simulation of 35 ECG records, out of which 24 are normal and 11 are abnormal, which are further classified in 4 fast heart beats and 7 slow heart beats called tachycardia and bradycardia respectively. The efficiency of proposed work is validated from MIT BIH arrhythmia database. [ABSTRACT FROM AUTHOR]

Recently, as interest in electrocardiogram monitoring has increased, research on real-time ECG signal analysis in daily life using lightweight embedded devices has increased. Abnormal beat detections in ECG signal analysis are an important research area to reduce processing time and cost for cardiac arrhythmia diagnosis. Abnormal beat detections can be divided into feature-based detection and shape-based detection. Feature-based detection finds it difficult to detect reliable fiducial points, and shape-based detection has difficulty detecting abnormal beats that are similar to normal beats. In this paper, we propose template cluster generation and abnormal beat detection using both detection methods. The proposed method shows robust detection of distorted normal beats by generating a template cluster rather than a single template. Moreover, abnormal beats that have normal shape can be detected using the RR interval, which is a highly reliable feature. Experiment results using the MIT-BIH arrhythmia database, provided by Physionet, showed the average processing times to generate a template cluster and detect abnormal beats for the 30-minute signal length were 1.21 seconds and 0.14 seconds, respectively. With manually adjusted thresholds, the specificity and accuracy achieved 93.00% and 97.94%, respectively. In the case of group 1 records obtained relatively stably, the specificity and accuracy achieved 99.27% and 99.44%.

Sleep apnea (SA) is a sleep-breathing disorder accompanied by multiple complications. The SA detection method based on a single-lead electrocardiogram (ECG) has the characteristics of low power consumption and is desirable for the development of wearable equipment. This study proposed a dual-model deep learning method to perform representation learning and introduce long-term temporal dependence. First, the Christov algorithm was used to obtain the RR interval (RRI) of each 1-minute ECG segment, and the adaptive synthetic (ADASYN) sampling method was employed to synthesize the RRI series of the minority class to address the imbalanced learning problem. Then, a representation learning model based on the one-dimensional convolutional neural network (1DCNN-RLM) was built to extract the feature vector of the RRI series. Eventually, a temporal dependence model based on the bidirectional gated recurrent unit (BiGRU-TDM) was constructed to learn the state (SA/normal) transition pattern between the segments and complete the classification task. We employed the apnea-ECG database for experiments. For per-segment detection results, the accuracy, sensitivity, and specificity of this method were 91.1%, 88.9%, and 92.4%, respectively. The per-recording detection accuracy reached 100%. ADASYN alleviates the imbalance of sensitivity and specificity in classification results. The 1DCNN-RLM with powerful representation learning ability has extracted discriminative features. The BiGRU-TDM introduces the long-term time dependence of SA and improves classification performance. The results of this study substantiate that the proposed method is robust and has good transferability. This method provides a reference for the diagnosis of other diseases. [ABSTRACT FROM AUTHOR]

Background: Wearable technologies for monitoring cardiovascular parameters, including electrocardiography (ECG) and impedance cardiography (ICG), propose a challenging research subject. The expectancy for wearable devices to be unobtrusive and miniaturized sets a goal to develop smarter devices and better methods for signal acquisition, processing, and decision-making. Methods: In this work, non-standard electrode placement configurations (EPC) on the thoracic area and single arm were experimented for ECG signal acquisition. The locations were selected for joint acquisition of ECG and ICG, targeted to suitability for integrating into wearable devices. The methodology for comparing the detected signals of ECG was developed, presented, and applied to determine the R, S, and T waves and RR interval. An algorithm was proposed to distinguish the R waves in the case of large T waves. Results: Results show the feasibility of using non-standard EPCs, manifesting in recognizable signal waveforms with reasonable quality for post-processing. A considerably lower median sensitivity of R wave was verified (27.3%) compared with T wave (49%) and S wave (44.9%) throughout the used data. The proposed algorithm for distinguishing R wave from large T wave shows satisfactory results. Conclusions: The most suitable non-standard locations for ECG monitoring in conjunction with ICG were determined and proposed.

Arterial baroreflex assessment using vasoactive substances enables investigators to collect data pairs over a wide range of blood pressures and reflex reactions. These data pairs relate intervals between heartbeats or sympathetic neural activity to blood pressure values. In an X-Y plot the data points scatter around a sigmoidal curve. After fitting the parameters of a sigmoidal function to the data, the graph's characteristics represent a rather comprehensive quantitative reflex description. Variants of the 4-parameter Boltzmann sigmoidal equation are widely used for curve fitting. Unfortunately, their 'slope parameters' do not correspond to the graph's actual slope which complicates the analysis and bears the risk of misreporting. We propose a modified Boltzmann sigmoidal function with preserved goodness of fit whose parameters are one-to-one equivalent to the sigmoidal curve's characteristics. [ABSTRACT FROM AUTHOR]

Although atrial fibrillation (AF) Arrhythmia is highly prevalent within a wide range of populations with major associated risks and due to its episodic occurrence, its recognition remains a challenge for doctors. This paper aims to present and experimentally validate a new efficient approach for the detection and classification of this cardiac anomaly using multiple Electrocardiogram (ECG) signals. This work consists of applying Stockwell transform (ST) with compact support kernel (ST-CSK) for ECG time-frequency analysis. The estimation of the atrial activity (AA) is then achieved after analyzing P-waves of the ECG signals for each heartbeat. ECG signals segmentation allows characterizing the AA by making use of its (t, f) flatness, (t, f) flux, energy concentration and heart rate variability. The features matrix is employed as an input of the support vector machines (SVM) working in binary and asymmetrical mode with an embedded reject option. The proposed algorithm is trained and then tested using different ECG sources namely two databases provided by PhysionNet (MIT-BIH Arrhythmia, MIT-BIH Atrial Fibrillation) and recorded ECG signals using MySignals HW development platform with raspberry Pi 3 model B + . The used method has achieved 98.46 % and 97.81 % as sensitivity and specificity, respectively. The obtained results confirm that the proposed approach represents a promising tool for Atrial Fibrillation Episodes (AFE) recognition with significant separability between Normal atrial activity and atrial activity with AF even under real and clinical conditions. [ABSTRACT FROM AUTHOR]

Arterial baroreflex assessment using vasoactive substances enables investigators to collect data pairs over a wide range of blood pressures and reflex reactions. These data pairs relate intervals between heartbeats or sympathetic neural activity to blood pressure values. In an X-Y plot the data points scatter around a sigmoidal curve. After fitting the parameters of a sigmoidal function to the data, the graph’s characteristics represent a rather comprehensive quantitative reflex description. Variants of the 4-parameter Boltzmann sigmoidal equation are widely used for curve fitting. Unfortunately, their ‘slope parameters’ do not correspond to the graph’s actual slope which complicates the analysis and bears the risk of misreporting. We propose a modified Boltzmann sigmoidal function with preserved goodness of fit whose parameters are one-to-one equivalent to the sigmoidal curve’s characteristics.

Cardiac arrhythmias that can lead to sudden cardiac death are common. Electrocardiograms (ECGs) offer valuable information about cardiac status and play a crucial role in evaluating patients with arrhythmia in clinical diagnosis. The development of machine learning technologies has made the computer-aided diagnosis of cardiac arrhythmias possible, which can improve the efficiency and quality of medical treatment. In this study, a new method for the automatic classification of heartbeats is developed. This paper presents a novel approach to detect arrhythmias in the inter-patient paradigm using a convolutional neural network (CNN) that integrates multiscale convolutional blocks, frequency convolutional block attention (FCBA) modules, and RR interval features. The proposed method also includes oversampling for the heartbeats of the minority class and the addition of random noise to increase training samples and alleviate the problem of data imbalance. We used the MIT-BIH-AR arrhythmia database , which is a globally recognized ECG database, to evaluate the classification performance of the proposed model in this paper. Based on the experiments, the sensitivities of the normal beats (N), supraventricular ectopic beats (SVEB), and ventricular ectopic beats (VEB) were 96.9%, 89.3%, and 93.3%, respectively. In the inter-patient heartbeat classification paradigm, the overall accuracy of the proposed method is 95.60% in classifying heartbeats. The study shows that the proposed scheme outperforms other published schemes in terms of classification results. • A heartbeat classification method combining deep neural networks and medical features is proposed. • The use of multiscale convolutional fusion allows the network to extract richer electrocardiogram (ECG) features. • A frequency convolutional block attention (FCBA) module is proposed to adjust the wight relationships. • Medical features, namely RR intervals, are embedded into our deep model to further improve the performance of heartbeat classification. • Accuracy of 95.6% was achieved under inter-patient scheme. [ABSTRACT FROM AUTHOR]

This paper is targeted in the area of biometric data enabled security by using machine learning for the digital health. The traditional authentication systems are vulnerable to the risks of forgetfulness, loss, and theft. Biometric authentication is has been improved and become the part of daily life. The Electrocardiogram (ECG) based authentication method has been introduced as a biometric security system suitable to check the identification for entering a building and this research provides for studying ECG-based biometric authentication techniques to reshape input data by slicing based on the RR-interval. The Overall Performance (OP) as a newly proposed performance measure is the combined performance metric of multiple authentication measures in this study. The performance of the proposed system using a confusion matrix has been evaluated and it has achieved up to 95% accuracy by compact data analysis. The Amang ECG (amgecg) toolbox in MATLAB is applied to the mean square error (MSE) based upper-range control limit (UCL) which directly affects three authentication performance metrics: the number of accepted samples, the accuracy and the OP. Based on this approach, it is found that the OP could be maximized by applying a UCL of 0.0028, which indicates 61 accepted samples within 70 samples and ensures that the proposed authentication system achieves 95% accuracy.

This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluated on the test set. Optimal DenseNet architectures with the number of neurons in sequential [1st, 2nd, 3rd] hidden layers were assessed for sensitivity and specificity: DenseNet [16,16,0] with primary leads (I or II) had 87.9–88.3 and 90.5–91.5%; DenseNet [32,32,32] with six limb leads had 90.7 and 94.2%; DenseNet [32,32,4] with six chest leads had 92.1 and 93.2%; and DenseNet [128,8,8] with all 12 leads had 91.8 and 95.8%, indicating sensitivity and specificity values, respectively. Mean SHAP values on the entire test set highlighted the importance of RRi-mean (100%), RR-std (84%), and atrial synchronization (40–60%) for the PQa-mean (aVR, I), PQi-std (V2, aVF, II), and PQi-mean (aVL, aVR). Our focus on finding the strongest AV synchronization predictors of AF in 12-lead ECGs would lead to a comprehensive understanding of the decision-making process in advanced neural network classifiers. DenseNet self-learned to rely on a few ECG behavioral characteristics: first, characteristics usually associated with AF conduction such as rapid heart rate, enhanced heart rate variability, and large PQ-interval deviation in V2 and inferior leads (aVF, II); second, characteristics related to a typical P-wave pattern in sinus rhythm, which is best distinguished from AF by the earliest negative P-peak deflection of the right atrium in the lead (aVR) and late positive left atrial deflection in lateral leads (I, aVL). Our results on lead-selection and feature-selection practices for AF detection should be considered for one- to twelve-lead ECG signal processing settings, particularly those measuring heart rate, AV conduction times, and P-/f-wave amplitudes. Performances are limited to the AF diagnostic potential of these three metrics. SHAP value importance can be used in combination with a human expert’s ECG interpretation to change the focus from a broad observation of 12-lead ECG morphology to focusing on the few AV synchronization findings strongly predictive of AF or non-AF arrhythmias. Our results are representative of AV synchronization findings across a broad taxonomy of cardiac arrhythmias in large 12-lead ECG databases.

Accurate and early detection of cardiac arrhythmia present in an electrocardiogram (ECG) can prevent many premature deaths. Cardiac arrhythmia arises due to the improper conduction of electrical impulses throughout the heart. In this paper, we propose an improved RR interval-based cardiac arrhythmia classification approach. The Discrete Wavelet Transform (DWT) and median filters were used to remove high-frequency noise and baseline wander from the raw ECG. Next, the processed ECG was segmented after the determination of the QRS region. We extracted the primary feature RR interval and other statistical features from the beats to classify the Normal, Premature Ventricular Contraction (PVC), and Premature Atrial Contraction (PAC). The K-Nearest Neighbour (k-NN), Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayes (NB), and Random Forest (RF) classifier were utilised for classification. Overall performance of SVM with Gaussian kernel achieved Se % = 99.28, Sp % = 99.63, +P % = 99.28, and Acc % = 99.51, which is better than the other classifiers used in this method. The obtained results of the proposed method are significantly better and more accurate. [ABSTRACT FROM AUTHOR]

Background. Prediction of sudden cardiac death remains a significant challenge. There is some evidence that ventricular ectopic activity could be regarded as a predictive marker. Objectives. We carried out an analysis to explore whether premature ventricular complexes (PVCs) are a risk factor in implantable cardioverter-defibrillator (ICD) interventions. Materials and methods. The study method was a RR interval series analysis (n = 184) of arrhythmic events and controls from the ICD. Study group consisted of patients with a mean age of 55 ±27 years; 74% of them were male, 85% were secondary prevention patients, 62% had coronary artery disease (CAD), 15% hypertropic cardiomyopathy (HCM), 15% dilated cardiomyopathy (DCM), and 8% diseases of other etiology. The mean follow-up time was 64 months (range: 3-126 months). The study population was divide into patients with at least 1 appropriate intervention ventricular tachycardia/ventricular fibrillation (VT/VF) (group A, n = 101) and controls without interventions (group B, n = 83). The number of PVC/4000 RR cycles, the shortest coupling intervals between a PVC and preceding R as well as the number of PVCs of very short (180-220 ms), short (220-280 ms) and different cycle lengths (CL) as well as the incidence of short-longshort (SLS) sequences were compared. Results. The number of PVCs/4000 RR cycles was significantly higher in group A (263 ±32 compared to 43 ±17, p < 0.0001). The mean shortest PVC CL was significantly shorter in group A (320 ±13 compared to 400 ±38, p = 0.029). The number of PVCs with a very short CL was 1 ±0.4 compared to 0.1 ±0.1 (p = 0.028). The number of PVCs with a short CL was 5 ±1.2 compared to 0.6 ±0.4 (p = 0.0007) in groups A and B, respectively. The incidence of SLS sequences was significantly higher in group A than in group B (67 (94% of patients) and 4 (33% of patients) respectively (p < 0.0001)). Conclusions. Significant differences were found in the characteristics of PVCs and SLS sequences between patients with appropriate ICD interventions and controls. A newly developed basic computer program called PCRR was applied for RR interval analysis. This simple method could be a predictor of PVC burden and lifethreatening arrhythmias in different populations. [ABSTRACT FROM AUTHOR]

Mental Workload (MW) has become an important problem in the design of man-machine systems, so its related detection and analysis technology has aroused extensive interest and concern. Researches show electrocardiogram (ECG) physiological signals can be an appropriate indicator to reflect the level of human MW. When the operator is in the state of high MW, the cardiac load will increase, and the period and shape of ECG signals accordingly change. Heart Rate Variability (HRV) is the most widely used ECG feature to assess the MW. However, its classification precision is not high enough. In order to improve this, multiple features of ECG signals are extracted to classify the MW in this paper. Besides the RR interval feature of HRV, the other three features, T and P wave power, QRS complex power and Sample Entropy (SampEn) of ECG waveform, are further extracted and applied to assess MW. The Support Vector Machine (SVM) is used to establish the classification model, and the grid search and cross-validation algorithm are used to optimize its parameters. The results show the MW classifier based on multiple features of ECG signals can evidently improve the classification accuracy. This will be helpful to realize a real time and online MW classification using ECG data.

The repolarization and depolarization in heart generate electrical signals in the form of an ECG wave. The condition of the heart can be indicated by using Heart Rate Variability (HRV) features. In this work, FIR filter is used at the pre-processing phase for denoising, and then statistical analysis is applied for time-domain HRV feature extraction and selection. This algorithm is evaluated on different records of MIT/BIH Normal Sinus Rhythm and Arrhythmia database. The t -test implementation in both databases shows that there are significant variations in HRV features, where meanRR and HR have suggestive significant (0. 0 5 < p ≤ 0. 1 0) changes, while maxRR, minRR, maxminRR, and SDNN have strongly significant (p ≤ 0. 0 1) changes. To validate the statistical analysis of HRV, feature classification has been done using SVM and kNN classifiers. A significant improvement of 2% and 14.02% has been observed in the overall accuracy of SVM and kNN classifiers after feature selection, respectively. These HRV features can be used for the early prediction of various Cardio-Vascular Diseases (CVD). [ABSTRACT FROM AUTHOR]

In recent years, the number of cardiac disease patients has been increasing. Modern medical research has shown that the complexity of electrocardiogram (ECG) signals is related to cardiovascular diseases. This paper investigates the difference in complexity of ECG data from the people with different cardiovascular diseases, such as atrial fibrillation (AF), ventricular arrhythmia (VA) and congestive heart failure (CHF). The empirical mode decomposition (EMD) and multiscale entropy method are used to analyze the ECG data, and a mathematical model established by a support vector machine is used to identify different diseases. The accuracy recognition rate of the AF recognition is 96.25%, and that of the CHF and VA reach 90.26% and 92.20%, respectively. The experimental results show that the recognition method proposed in this paper is successful. [ABSTRACT FROM AUTHOR]

In the past years, several QRS complex (Q, R and S wave) detecting algorithms have been implemented in software, but they are not applicable for real-time operation due to their mathematical complexity. Hence, this paper focuses on developing an algorithm which enables detection of QRS complex in real time. Here, Integer Haar Wavelet Transform is employed which is used for the purpose of filtering ECG signal and detecting the R-peak frequency of QRS complex. Various blocks of the proposed architecture are implemented in a Digilent Nexys 4 double data rate field-programmable gate array board with only 501 flip-flops and 557 look-up tables utilized which makes it suitable for directly installing it into medical equipment or further developing a smart internet of things system for bio-medical applications. To make the designed system more generic, several similar blocks or components have been used. At first, the principle of using wavelet to detect QRS complex is explored theoretically and accordingly used for developing our system. An efficient hardware architecture is implemented incorporating many simplifications, a significant one being approximation of floating point arithmetic to integer arithmetic, required for wavelets. The architecture of the designed system is represented with demonstration in behavioral simulation as well as hardware testing. In the end, the system is analyzed and results are obtained with an error percentage in RR interval computation of less than 1.4% and QRS detection accuracy of 98.76%. The proposed architecture is also synthesized using 130 nm technology which produces 0.717% of leakage power. The developed architecture can be used for analysis of other bio-medical signals where the operation of wavelet transform in hardware is required. [ABSTRACT FROM AUTHOR]

Legacy studies for classifying arrhythmia have been studied to improve the accuracy of classification, Neural Network, Fuzzy, etc. Deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose optimal parameter extraction method based on a deep learning. For this purpose, R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 97.84% in PVC classification. [ABSTRACT FROM AUTHOR]

An unconstrained visual display terminal (VDT) visual fatigue monitoring method based on BCG is studied. A VDT visual fatigue test is designed and implemented in this study, also acceleration signals are obtained by using an acceleration sensor, which is installed on the seat back. Then, BCG is obtained by adaptive threshold wavelet denoising, FFT, frequency domain filtering in the range of heart rate, and IFFT. Low frequency (LF) is extracted after the RR interval and JJ interval are calculated by the wavelet algorithm. Curves of two kinds of LF with the usage of VDT were obtained and were identical. Thus, the authors can draw conclusions that BCG can replace ECG to achieve unconstrained monitoring of VDT visual fatigue and LF gradually increases with VDT visual fatigue becoming more and more serious. Finally, we compare LF curves of BCG and ECG during use VDT to draw a conclusion that BCG can replace ECG to monitor VDT visual fatigue in an unconstrained way. Also, the confidence interval is used to verify the reliability of SD subjective evaluation, and the conclusion is reliable. [ABSTRACT FROM AUTHOR]

Abnormal heart rhythms, also known as arrhythmias, can be life-threatening. AFIB and AFL are examples of arrhythmia that affect a growing number of patients. This paper describes a method that can support clinicians during arrhythmia diagnosis. We propose a deep learning algorithm to discriminate AFIB, AFL, and NSR RR interval signals. The algorithm was designed with data from 4051 subjects. With 10-fold cross-validation, the algorithm achieved the following results: ACC = 99.98%, SEN = 100.00%, and SPE = 99.94%. These results are significant because they show that it is possible to automate arrhythmia detection in RR interval signals. Such a detection method makes economic sense because RR interval signals are cost-effective to measure, communicate, and process. Having such a cost-effective solution might lead to widespread long-term monitoring, which can help detecting arrhythmia earlier. Detection can lead to treatment, which improves outcomes for patients.