Electrocardiogram Recordings Research Articles

Hemodialysis Efficiency Predictor in End-Stage Kidney Disease Using Real-Time Heart Rate Variability.

Autonomic dysfunction as a long-term complication may occur in end-stage kidney disease (ESKD) patients and can be diagnosed using heart rate variability (HRV) analyzed from electrocardiogram (ECG) recordings. There is limited data about HRV using real-time ECG to predict hemodialysis (HD) efficiency in patients with ESKD who are routinely doing HD in the real world. A total of 50 patients (62.1 ± 10.7 years) with ESKD underwent continuous real-time ECG monitoring (237.4 ± 15.3 min) during HD for HRV using remote monitoring system. Their electrolyte levels were checked before and after HD. We compared HRV according to electrolyte levels. During the monitor, we checked the ECG and electrolyte levels simultaneously a total of 2374 times for all of the patients. Both time and frequency domain HRV were higher when the patients had lower K+ level (<0.5 mEq/L) and P+ level change (<2 mEq/L) before and after HD as compared to those with a higher K+ level (≥0.5 mEq/L) and P+ level change (≥2 mEq/L). Additionally, patients with lower K+ and P+ level change groups had higher incidences of arrhythmic events including atrial/ventricular premature complexes, despite no difference of mean heart rate (p < 0.001). Higher HRV was independently associated with a poorly controlled K+ and P+ level during HD in patients with ESKD. This is consistently evidenced by the independent association between higher HRV, K+ and P+ levels in real time, suggesting that low electrolyte changes before and after HD alone may cause cardiac autonomic dysfunction.

Intelligent assessment of atrial fibrillation gradation based on sinus rhythm electrocardiogram and baseline information

BackgroundAtrial fibrillation (AF) is a progressive arrhythmia that significantly affects a patient's quality of life. The 4S-AF scheme is clinically recommended for AF management; however, the evaluation process is complex and time-consuming. This renders its promotion in primary medical institutions challenging. This retrospective study aimed to simplify the evaluation process and present an objective assessment model for AF gradation. MethodsIn total, 189 12-lead electrocardiogram (ECG) recordings from 64 patients were included in this study. The data were annotated into two groups (mild and severe) according to the 4S-AF scheme. Using a preprocessed ECG during the sinus rhythm (SR), we obtained a synthesized vectorcardiogram (VCG). Subsequently, various features were calculated from both signals, and age, sex, and medical history were included as baseline characteristics. Different machine learning models, including support vector machines, random forests (RF), and logistic regression, were finally tested with a combination of feature selection techniques. ResultsThe proposed method demonstrated excellent performance in the classification of AF gradation. With an optimized feature set of VCG and baseline features, the RF model achieved accuracy, sensitivity, and specificity of 83.02 %, 80.56 %, and 88.24 %, respectively, under the inter-patient paradigm. ConclusionOur results demonstrate the value of physiological signals in AF gradation evaluation, and VCG signals were effective in identifying mild and severe AF. Considering its low computational complexity and high assessment performance, the proposed model is expected to serve as a useful prognostic tool for clinical AF management.

Eutectogels as a Semisolid Electrolyte for Organic Electrochemical Transistors.

Organic electrochemical transistors (OECTs) are signal transducers offering high amplification, which makes them particularly advantageous for detecting weak biological signals. While OECTs typically operate with aqueous electrolytes, those employing solid-like gels as the dielectric layer can be excellent candidates for constructing wearable electrophysiology probes. Despite their potential, the impact of the gel electrolyte type and composition on the operation of the OECT and the associated device design considerations for optimal performance with a chosen electrolyte have remained ambiguous. In this work, we investigate the influence of three types of gel electrolytes-hydrogels, eutectogels, and iongels, each with varying compositions on the performance of OECTs. Our findings highlight the superiority of the eutectogel electrolyte, which comprises poly(glycerol 1,3-diglycerolate diacrylate) as the polymer matrix and choline chloride in combination with 1,3-propanediol deep eutectic solvent as the ionic component. This eutectogel electrolyte outperforms hydrogel and iongel counterparts of equivalent dimensions, yielding the most favorable transient and steady-state performance for both p-type depletion and p-type/n-type enhancement mode transistors gated with silver/silver chloride (Ag/AgCl). Furthermore, the eutectogel-integrated enhancement mode OECTs exhibit exceptional operational stability, reflected in the absence of signal-to-noise ratio (SNR) variation in the simulated electrocardiogram (ECG) recordings conducted continuously over a period of 5 h, as well as daily measurements spanning 30 days. Eutectogel-based OECTs also exhibit higher ECG signal amplitudes and SNR than their counterparts, utilizing the commercially available hydrogel, which is the most common electrolyte for cutaneous electrodes. These findings underscore the potential of eutectogels as a semisolid electrolyte for OECTs, particularly in applications demanding robust and prolonged physiological signal monitoring.

An Unsupervised Deep Learning Framework for Retrospective Gating of Catheter-Based Cardiac Imaging

Motion artifacts are a major challenge in the in vivo application of catheter-based cardiac imaging modalities. Gating is a critical tool for suppressing motion artifacts. Electrocardiogram (ECG) gating requires a trigger device or synchronous ECG recordings for retrospective analysis. Existing retrospective software gating methods extract gating signals through separate steps based on changes in vessel morphology or image features, which require a high computational cost and are prone to error accumulation. In this paper, we report on an end-to-end unsupervised learning framework for retrospective image-based gating (IBG) of catheter-based intracoronary images, named IBG Network. It establishes a direct mapping from a continuously acquired image sequence to a gated subsequence. The network was trained on clinical data sets in an unsupervised manner, addressing the difficulty of obtaining the gold standard in deep learning-based motion suppression techniques. Experimental results of in vivo intravascular ultrasound and optical coherence tomography sequences show that the proposed method has better performance in terms of motion artifact suppression and processing efficiency compared with the state-of-the-art nonlearning signal-based and IBG methods.

Investigation of the Antiepileptic Effect of (R)-(-) and (S)-(+) Carvone in Penicillin-Induced Epileptiform Activity Model

Aim: Epilepsy affects approximately 70 million people worldwide. While many drugs can prevent seizures, they have a limited impact on preventing or curing the disease. In this perspective, natural compounds, especially monoterpenes derived from medicinal plants, have been investigated in epilepsy models, such as carvone (CAR). The principal constituent of peppermint oil, (R)-(-)-carvone (R-CAR), and the primary component in cumin and dill seed oils, (S)-(+)-carvone (S-CAR), find diverse applications in cosmetics, food, and pharmaceutical formulations. This study aims to investigate the antiepileptic effects of the natural compounds S-CAR and R-CAR in penicillin (PEN)-induced experimental epilepsy model in rats.&#x0D; Material and Method: In the research, 91 male Wistar rats were used. The rats were grouped into 3 main groups as common groups, pre-penicillin groups and post-penicillin groups. The main groups were divided into a total of 13 subgroups. Electrocardiogram recording was taken from rats. At the end of the experiment, the latency of the first epileptiform activity (EA), spike-wave frequency (SWF), and spike-wave amplitude (SWA) of the EA were analyzed. &#x0D; Results: S-CAR and R-CAR administered before penicillin prolonged the latency to the onset of the first EA. S-CAR and R-CAR administered before penicillin decreased SWF. 100 mg/kg doses of S-CAR and R-CAR injected 30 minutes after penicillin administration decreased SWF. While 200 mg/kg dose of R-CAR administered before penicillin decreased SWA in a time-dependent manner, 100 mg/kg dose of S-CAR administered after penicillin decreased SWA.&#x0D; Conclusion: These findings indicate that carvone could exhibit both protective and therapeutic effects in the management of epilepsy.

Sepsis Trajectory Prediction Using Privileged Information and Continuous Physiological Signals.

The aim of this research is to apply the learning using privileged information paradigm to sepsis prognosis. We used signal processing of electrocardiogram and electronic health record data to construct support vector machines with and without privileged information to predict an increase in a given patient's quick-Sequential Organ Failure Assessment score, using a retrospective dataset. We applied this to both a small, critically ill cohort and a broader cohort of patients in the intensive care unit. Within the smaller cohort, privileged information proved helpful in a signal-informed model, and across both cohorts, electrocardiogram data proved to be informative to creating the prediction. Although learning using privileged information did not significantly improve results in this study, it is a paradigm worth studying further in the context of using signal processing for sepsis prognosis.

Long-Term Study of the Synchronization Effect between Geomagnetic Field Variations and Minute-Scale Heart-Rate Oscillations in Healthy People

This study aimed to investigate the effect of human heart-rate synchronization with variations in the geomagnetic field (GMF) (“biogeophysical synchronization effect”). We analyzed 403 electrocardiogram (ECG) recordings of 100 or 120 min that were obtained in 2012–2023 from two middle-aged female volunteers in good health. The minute-value series of the GMF vector from the INTERMAGNET network was used. Each ECG recording was individually examined using cross-correlation and wavelet analysis. The findings from two separate experimental sets (306 recordings from Volunteer A and 97 from Volunteer B) displayed notable similarity in all aspects analyzed: (1) For both participants, the biogeophysical synchronization effect is observed in 40–53% of the recordings as a statistically significant (p &lt; 0.0045) correlation between minute heart-rate (HR) time-series values and at least one of the horizontal components of the GMF, with a time shift between values of [−5, +5] min. (2) Wavelet analysis indicates that the spectra of the HR series and at least one GMF component exhibit similarity in 58–61% of cases. (3) The synchronization is most evident within the period range between 8–13 min. The probability of the synchronization effect manifestation was independent of the geomagnetic activity (GMA) level, which was recorded during the observations.

A Capacitive-Feedback Amplifier with 0.1% THD and 1.18 μVrms Noise for ECG Recording

This paper presents an amplifier with low noise, high gain, low power consumption, and high linearity for electrocardiogram (ECG) recording. The core of this design is a chopper-stabilized capacitive-feedback operational transconductance amplifier (OTA). The proposed OTA has a two-stage structure, with the first stage using a combination of current reuse and cascode techniques to obtain a large gain at low power and the second stage operating in Class A state for better linearity. The amplifier additionally uses a DC servo loop (DSL) to improve the rejection of DC offsets. The amplifier is implemented in a standard 0.13 μm CMOS process, consuming 1.647 μA current from the supply voltage of 1.5 V and occupying an area of 0.97 mm2. The amplifier has a 0.5 Hz to 6.1 kHz bandwidth and 59.7 dB gain while having no less than a 65 dB common-mode rejection ratio (CMRR). The amplifier’s total harmonic distortion (THD) is less than 0.1% at 800 mVpp output. The amplifier can provide a noise level of 1.18 μVrms in the 0.5 Hz to 500 Hz bandwidth that the ECG signal is interested in and has 3.38 μVrms input-referred noise (IRN) over the entire bandwidth, so its noise efficiency factor (NEF) is 2.13.

Accuracy of Smartwatch Electrocardiographic Recording in the Acute Coronary Syndrome Setting: Rationale and Design of the ACS WATCH II Study.

Background: Acute Coronary Syndrome (ACS), with or without ST-segment elevation, is a major contributor to global mortality and morbidity. Swift diagnosis and treatment are vital for mitigating cardiac damage and improving long-term outcomes. The 12-lead electrocardiogram (ECG) currently serves as the gold standard for diagnosis in ACS with ST-segment elevation and may support the diagnosis in ACS without ST-segment elevation. However, the growing prevalence of smartwatches enables the acquisition of electrocardiographic data without traditional ECG equipment. While smaller studies support smartwatch ECG use, larger-scale validation within ACS remains lacking. The ACS WATCH II study aims to validate smartwatch ECG recordings for ACS. Methods: The primary objective is to validate smartwatch-obtained electrocardiographic data in patients presenting with ACS. Two cohorts of 120 patients each, presenting ACS with and without ST-segment elevation, will be assessed. Smartwatches will capture recordings of leads I, III, and V2 alongside standard ECGs. These leads, chosen due to a 97% ACS diagnosis sensitivity in previous studies, will undergo blind evaluation by two experienced external assessors against conventional ECG. Additionally, a control sample of 60 healthy individuals will be included. Conclusions: ACS WATCH II pioneers large-scale prospective validation of smartwatch ECG recordings in ACS patients. Additionally, it indirectly validates a swift diagnostic approach using three leads (I, III, and V2). This could expedite time-critical ACS diagnoses and simplify access through smartwatch-based diagnosis.

Arrhythmias in patients with acute ST-elevation myocardial infarction induced by various risk factors during the first day after myocardial reperfusion by primary percutaneous coronary intervention

Introduction. Acute coronary syndrome, in particular acute ST-elevation myocardial infarction (STEMI), is often accompanied by complex hemodynamically significant arrhythmias and conduction disorders. Such patients have a worse prognosis compared to patients with sinus rhythm. Arrhythmias in patients with STEMI are facilitated by the presence of comorbidities such as arterial hypertension, diabetes mellitus, obesity, and post-COVID-19 syndrome. The aim of the study. To elucidate the nature of arrhythmias in patients with acute STEMI induced by various risk factors during the first day after myocardial reperfusion by primary percutaneous coronary intervention. Materials and methods. The study involved 50 patients aged 45 to 83 years (average age – 63,4 ± 9,6 years; men – 70,97 %, women – 29,03 %), who were treated during 2021-2023 at the cardiology and reperfusion therapy department of Cardio-vascular center of ʺSaint Panteleimon Hospital in Lvivʺ and the infarction department of ʺLviv Regional Clinical Cardiological Centerʺ. The patients under investigation were subjected to daily electrocardiogram (ECG) monitoring for 24 hours after stenting of the infarct-related coronary artery, using a 7-channel ECG recorder Solvaig 06000.7 with computer processing of the recording using the DiaCard2 software. The obtained material was further subjected to software packages Microsoft Excel 2022, Statistica 10. Results. It was established that among supraventricular rhythm disturbances the most common were premature contractions, the average number of which per patient was significantly higher in the presence of obesity. Similarly high it was in post COVID-19 patients, as well as in those with hypertension. In post-coronavirus infection and in hypertension cases, extrasystoles were often in the form of pairs, triplets, bigemia, and trigemia; paroxysms of supraventricular tachycardia were also recorded in these patients. Among the ventricular arrhythmias also the most frequent were premature cardiac contractions, significantly more oftenly recorded in patients with hypertension and those experienced COVID-19; only in these patients were documented extrasystoles in the form of pairs, triplets, bigeminy, trigeminy, runs of ʺR to Tʺ, which are currently considered as harbingers of life-threatening ventricular arrhythmias. In the presence of hypertension and post-COVID-19, episodes of unstable ventricular tachycardia were also observed. Conclusions. In patients with STEMI, both supraventricular and ventricular premature contractions and episodes of supraventricular and unstable ventricular tachycardia are quite common during the first day after primary percutaneous coronary intervention with infarct-related coronary artery stenting, which is evidence of myocardial electrical instability. The nature of rhythm disturbances in the presence of hypertension and post-COVID-19 is prognostically unfavorable and indicates a higher risk of lifethreatening arrhythmias in these patients. Myocardial revascularization should be supplemented with optimal medical treatment in order to prevent the adverse cardiovascular events in post-STEMI patients. Further research should be directed toward elucidation of predictive value of detected arrhythmias with respect to the occurrence of unfavorable cardiovascular events in the early and long-term post-infarction period.

Real-time notification with 12-lead wearable electrocardiogram recordings

Real-time notification with 12-lead wearable electrocardiogram recordings

Heart Rate Variability Measured from Wearable Devices as a Marker of Disease Severity in Tetanus.

Tetanus is a disease associated with significant morbidity and mortality. Heart rate variability (HRV) is an objective clinical marker with potential value in tetanus. This study aimed to investigate the use of wearable devices to collect HRV data and the relationship between HRV and tetanus severity. Data were collected from 110 patients admitted to the intensive care unit in a tertiary hospital in Vietnam. HRV indices were calculated from 5-minute segments of 24-hour electrocardiogram recordings collected using wearable devices. HRV was found to be inversely related to disease severity. The standard deviation of NN intervals and interquartile range of RR intervals (IRRR) were significantly associated with the presence of muscle spasms; low frequency (LF) and high frequency (HF) indices were significantly associated with severe respiratory compromise; and the standard deviation of differences between adjacent NN intervals, root mean square of successive differences between normal heartbeats, LF to HF ratio, total frequency power, and IRRR, were significantly associated with autonomic nervous system dysfunction. The findings support the potential value of HRV as a marker for tetanus severity, identifying specific indices associated with clinical severity thresholds. Data were recorded using wearable devices, demonstrating this approach in resource-limited settings where most tetanus occurs.

A Novel Deep Ensemble Method for Selective Classification of Electrocardiograms.

Telehealth paradigms are essential for remotely managing patients with chronic conditions. To assist clinicians in handling the large volumes of data collected through these systems, clinical decision support systems (CDSSs) have been developed. However, the effectiveness of CDSSs depends on the quality of remotely recorded physiological data and the reliability of the algorithms used for processing this data. This study aims to reliably detect atrial fibrillation (AF) from short-term single-lead (STSL) electrocardiogram (ECG) recordings obtained in unsupervised telehealth environments. A novel deep ensemble-based method was developed for detecting AF from STSL ECG recordings. Following this, a postprocessing algorithm was created to assess uncertainty in classified STSL ECGs and to refrain from interpretation when confidence is low. The proposed method was validated through a 5-fold cross-validation on the Cardiology Challenge 2017 (CinC2017) dataset. The deep ensemble method achieved 83.5 ± 1.5% sensitivity, 98.4 ± 0.2% specificity, and an F 1-score of 0.847 ± 0.016in AF detection. Implementing the selective classification algorithm resulted in significant improvements, with sensitivity increasing to 92.8 ± 2.2%, specificity to 99.7 ± 0.0%, and an F 1-score of 0.919 ± 0.016. The proposed method demonstrates the feasibility of accurately detecting AF from STSL ECG recordings. The selective classification approach offers a substantial enhancement to automated ECG interpretation algorithms in telehealth solutions. These findings highlight the potential for improving the utility of telehealth systems by integrating advanced CDSSs capable of managing uncertainty and ensuring higher accuracy, thereby improving patient outcomes in remote healthcare settings.

Heart rate variability and fasting plasma glucose as trait marker of psychosis: A comparative study between drug naive patients with psychosis and healthy volunteers

Abstract: BACKGROUND: To date, mixed results have been obtained regarding the metabolic and cardiovascular changes in drug-naïve psychotic patients. Moreover, very few Indian studies are available on this subject. The current study adds to the Indian research on metabolic and cardiovascular factors associated with psychotic disorders. AIM: The aim of the study is to determine that metabolic abnormalities such as “impaired glucose tolerance, abnormal lipid profile, and cardiovascular risks are associated with the pathophysiology of the disease itself, i.e., psychosis. MATERIALS AND METHODS: The present study was a hospital-based cross-sectional study conducted over 2 years that included 30 drug-naïve psychotic patients as per ICD-10 DCR and 20 healthy volunteers. Purposive sampling was done. The patients and matched healthy volunteers fulfilling the inclusion and exclusion criteria were assessed to obtain the sociodemographic data, and a mental state examination was done. Positive and Negative Syndrome Scale was applied to patients only. The required investigations, such as lipid profile, sugar profile, body mass index, and electrocardiogram (ECG) for root mean square standard deviation (RMSSD) (heart rate variability [HRV]-time domain), heart rate, and corrected QT interval, were done in both the groups after obtaining written informed consent. The ECGs of all subjects in both groups were obtained mostly in the morning between 10 am and 12 am. The subjects were asked to avoid coffee and nicotine for 1 h before the ECG recording. The patient was asked to rest for 10 min before the recording and 1 min 6-lead ECG recording was obtained in a supine position at complete rest. RMSSD was calculated from the reading of lead II on 1 min resting ECG. RESULTS: Most of the metabolic and cardiovascular factors showed no statistically significant difference between the two groups except fasting blood sugar (FBS) (t = 0.843, P = 0.033), and median value of HRV (P = 0.008). Mean FBS was higher in the patient group compared to the control, and mean HRV was lower in the patient group compared to the control. CONCLUSION: The findings of the current study, in conjunction with the findings from other methodologically similar studies, suggest that lower HRV and abnormal fasting glucose may be associated with the psychopathology of psychotic illnesses.

Epilepsy's effect on cardiac rhythm and the autonomic nervous system.

Sudden unexpected death in epilepsy is the most common cause of death in young patients with epilepsy. The aim of this study was to evaluate changes in interictal electrocardiogram parameters and sympathetic skin responses as markers of autonomic dysfunction in patients with epilepsy and to determine their effects on the type and duration of epilepsy, frequency of seizures, and responses to treatment. A total of 97 patients with epilepsy and 94 healthy controls were recruited. We recorded their clinical and demographic characteristics and analyzed sympathetic skin response latency and amplitude, electrocardiogram recordings, and seven cardiac rhythm parameters: P-wave duration, PR segment, QRS duration, QT interval, QT interval distribution, Tpe duration, and Tpe/QT interval ratio. P-wave durations, T-wave durations, QT and QT interval durations, and Tpe and sympathetic skin response latency were significantly longer among patients with epilepsy than the controls, and their heart rate was significantly lower. However, sympathetic skin response latency and heart rate were negatively correlated, and T-wave duration, QT duration, QT interval duration, and Tpe were positively correlated. Our results from interictal electrocardiograms indicate clinically significant arrhythmias among patients with epilepsy and the correlation of such arrhythmias with sympathetic skin responses. Thus, noninvasive tests that evaluate the autonomic system should be used to predict the risk of sudden unexpected death in epilepsy among patients with epilepsy.

Removal of power line interference from ECG signal

Electrocardiogram (ECG) signals are vital for diagnosing cardiac abnormalities, but they are corrupted by powerline interference noise, which can obscure critical features and compromise diagnostic accuracy. This paper investigates various filtration techniques aimed at effectively removing powerline interference noise from ECG signals. Different approaches, including average filters and moving average filters, are explored and compared to determine their efficacy in noise reduction while preserving important signal characteristics. Experimental evaluations are conducted using synthetic ECG signals contaminated with simulated powerline interference noise and real-world ECG recordings corrupted by actual powerline interference. The performance of each filtration technique is assessed based on metrics such as Root Mean Square Error (RMSE) and Percentage Root Mean Square Difference (PRD). The trade-offs between noise reduction effectiveness and preservation of ECG signal fidelity are analyzed to identify the most suitable approach for clinical applications. This paper provides valuable insights into the selection and implementation of filtration techniques for mitigating powerline interference noise in ECG signals. The findings contribute to the development of robust signal processing methods for improving the reliability and accuracy of ECG-based diagnostic systems.

AI driven ECG arrhythmia diagnosis

The accurate and timely diagnosis of cardiac arrhythmias is crucial for effective patient management and improved health outcomes. However, the precise identification of arrhythmias in electrocardiogram (ECG) data often requires specialized medical expertise, leading to potential delays and errors in diagnosis. To address these challenges, this project introduces an AI-driven system for ECG arrhythmia diagnosis. Employing advanced deep learning techniques, the proposed system leverages a comprehensive dataset of annotated ECG recordings to train a robust model capable of detecting and classifying various types of arrhythmias. The model is designed to process raw ECG signals, extract relevant features, and generate clinically meaningful insights, enabling automated and rapid identification of arrhythmic patterns. Through a user-friendly interface, medical professionals can upload ECG data for real-time analysis, allowing for prompt decision-making and personalized patient care. Furthermore, the system offers interpretable results, highlighting key indicators and providing detailed explanations to aid clinicians in understanding the diagnostic outcomes.

The Influence of Autonomic Nervous System during Resting State on the Peripheral Pulse Wave Velocity in Young Adult Males

Abstract Background: The association between the activity of autonomic nervous systems (ANS) and pulse wave velocity (PWV) was commonly deduced after adjusting for confounding factors. The relationship between the ANS and PWV was either maintained, but attenuated, or no longer statistically connected after controlling for confounding variables. Research in young healthy individuals showed that the ANS does not control aortic stiffness (indexed by PWV) in a pressure-independent manner. Therefore, the role of the ANS in controlling PWV is debatable. Objectives: The objective of this study was to examine the possibility that ANS directly affects PWV independent of blood pressure (BP) and heart rate (HR). Subjects and Methods: Thirty-four healthy male volunteers (19 years old) were recruited. Stable brachial systolic BP (SBP)/diastolic BP (DBP) and HR were measured in semi-supine position after a 15-min rest. During the last 5 min, fingertip digital pulse wave (DPW) and lead II electrocardiogram (ECG) signals were recorded. The pulse transit time, and consequently PWV, was calculated by measuring the duration between the ECG R wave climax and a reference point on the DPW in the same cardiac cycle. The ANS activity was assessed by calculating the HR variability (HRV) indices obtained from the ECG record of 5-min R-R intervals (RRIs). Results: HRV indices low-frequency (LF)/high-frequency (HF) (LF band power measured in the 0.04–0.15 Hz)/the HF band power measured in the 0.15–0.4 Hz band) and SD2/SD1 ratios (SD1 and SD2 represent the dispersion along the minor and major axis of the fitted ellipse of the Poincaré plot) (sympathovagal balance) were significantly and positively correlated with PWV. In addition, the standard deviation of RRI, or normal-to-normal “NN” (SDNN) interval, after excluding ectopic beats, the square root of the mean squared differences of successive NN intervals (RMSSD) were significantly and negatively correlated with the PWV. No correlation was obtained between PWV and HR, SBP, or DBP. Conclusion: Peripheral PWV during rest or inactivity is affected directly by the sympathovagal balance independent of BP.

COMPUTATIONAL FRAMEWORK FOR PREDICTION OF CARDIAC DISORDERS BY ANALYZING ECG SIGNALS USING MACHINE LEARNING TECHNIQUE

The clinical diagnosis of heart disorders relies heavily on electrocardiograms (ECGs). Numerous abnormalities in heart are being identified with a record of heart signal throughout intervals. Monitoring and diagnosing ECGs signals in daily life are appearing recently due to an increase in healthcare equipment. This paper presents a novel computational framework for detecting heart disorders by analyzing the ECG signals using machine learning technology. The manual interpretation of ECGs by medical experts is time-consuming and subject to human error. This study presents a comprehensive review and implementation of an automated ECG classification system utilizing artificial neural networks (ANNs) for efficient and accurate cardiac condition identification. The proposed ECG classifier employs a multilayered ANN architecture, trained and validated using a diverse dataset of annotated ECG recordings. Preprocessing techniques, including signal denoising, feature extraction, and data augmentation, enhance the quality and relevance of input data for the ANN. The selected features encompass morphological and temporal attributes, essential for distinguishing normal and abnormal ECG patterns. In this paper, noise removal from input ECG dataset is performed by adaptive filter technique and baseline wander is also removed. Machine learning in ECG classification is done by ANN that allows to use less energy while still providing accurate classification. MATLAB software is employed to carry out this work and corresponding outputs are obtained for ECG classification.

Data Analysis of Heart Rate Variability and Arrhythmia in Patients with Paroxysmal Atrial Fibrillation.

Atrial fibrillation (AF) is the most common type of arrhythmia. Heart rate variability (HRV) may be associated with AF risk. The aim of this study was to test HRV indices and arrhythmias as predictors of paroxysmal AF based on 24-hour dynamic electrocardiogram recordings of patients. A total of 199 patients with paroxysmal AF (AF group) and 204 elderly volunteers over 60 years old (Control group) who underwent a 24-hour dynamic electrocardiogram from August 2022 to March 2023 were included. Time-domain indices, frequency-domain indices, and arrhythmia data of the two groups were classified and measured. Binary logistic regression analysis was performed on variables with significant differences to identify independent risk factors. A nomogram prediction model was established, and the sum of individual scores of each variable was calculated. Gender, age, body mass index and low-density lipoprotein (LDL) did not differ significantly between AF and Control groups (p > 0.05), whereas significant group differences were found for smoking, hypertension, diabetes, and high-density lipoprotein (HDL) (p < 0.05). The standard deviation of all normal to normal (NN) R-R intervals (SDNN), standard deviation of 5-minute average NN intervals (SDANN), root mean square of successive NN interval differences (rMSSD), 50 ms from the preceding interval (pNN50), low-frequency/high-frequency (LF/HF), LF, premature atrial contractions (PACs), atrial tachycardia (AT), T-wave index, and ST-segment index differed significantly between the two groups. Logistic regression analysis identified rMSSD, PACs, and AT as independent predictors of AF. For each unit increase in rMSSD and PACs, the odds of developing AF increased by 1.0357 and 1.0005 times, respectively. For each unit increase in AT, the odds of developing AF decreased by 0.9976 times. The total score of the nomogram prediction model ranged from 0 to 110. The autonomic nervous system (ANS) plays a pivotal role in the occurrence and development of AF. The individualized nomogram prediction model of AF occurrence contributes to the early identification of high-risk patients with AF.