Heart Rate Variability Features Research Articles

ECG-based epileptic seizure prediction: Challenges of current data-driven models.

Up to a third of patients with epilepsy fail to achieve satisfactory seizure control. A reliable method of predicting seizures would alleviate psychological and physical impact. Dysregulation in heart rate variability (HRV) has been found to precede epileptic seizures and may serve as an extracerebral predictive biomarker. This study aims to identify the preictal HRV dynamics and unveil the factors impeding the clinical application of ECG-based seizure prediction. Thirty-nine adult patients (eight women; median age: 38, [IQR = 31, 56.5]) with 252 seizures were included. Each patient had more than three recorded epileptic seizures, each at least 2 hours apart. For each seizure, one hour of ECG prior to seizure onset was analyzed and 97 HRV features were extracted from overlapping three-minute windows with 10s stride. Two separate patient-specific experiments were performed using a support vector machine (SVM). Firstly, the separability of training data was examined in a non-causal trial. Secondly, the prediction was attempted in pseudo-prospective conditions. Finally, visualized HRV data, clinical metadata, and results were correlated. The mean receiver operating characteristic (ROC) area under the curve (AUC) for the non-causal experiment was 0.823 (±0.12), with 208 (82.5%) seizures achieving an improvement over chance (IoC) classification score (p < 0.05, Hanley & McNeil test). In pseudo-prospective classification, the ROC-AUC was 0.569 (±0.17), and 86 (49.4%) seizures were classified with IoC. Off-sample optimized SVMs failed to improve performance. Major limiting factors identified include non-stationarity, variable preictal duration and dynamics. The latter is expressed as both inter-seizure onset zone (SOZ) and intra-SOZ variability. The pseudo-prospective preictal classification achieving IoC in approximately half of tested seizures suggests the presence of genuine preictal HRV dynamics, but the overall performance does not warrant clinical application at present. The limiting factors identified are often overlooked in non-causal study designs. While current deterministic prediction methods prove inadequate, probabilistic approaches may offer a promising alternative. Many patients with epilepsy suffer from uncontrollable seizures and would greatly benefit from a reliable seizure prediction method. Currently, no such system is available to meet this need. Previous studies suggest that changes in the electrocardiogram (ECG) precede seizures by several minutes. In our work, we evaluated whether variations in heart rate could be used to predict epileptic seizures. Our findings indicate that we are still far from achieving results suitable for clinical application and highlight several limiting factors of present seizure prediction approaches.

A multimodal deep learning-based algorithm for specific fetal heart rate events detection.

This study aims to develop a multimodal deep learning-based algorithm for detecting specific fetal heart rate (FHR) events, to enhance automatic monitoring and intelligent assessment of fetal well-being. We analyzed FHR and uterine contraction signals by combining various feature extraction techniques, including morphological features, heart rate variability features, and nonlinear domain features, with deep learning algorithms. This approach enabled us to classify four specific FHR events (bradycardia, tachycardia, acceleration, and deceleration) as well as four distinct deceleration patterns (early, late, variable, and prolonged deceleration). We proposed a multi-model deep neural network and a pre-fusion deep learning model to accurately classify the multimodal parameters derived from Cardiotocography signals. These accuracy metrics were calculated based on expert-labeled data. The algorithm achieved a classification accuracy of 96.2 % for acceleration, 94.4 % for deceleration, 90.9 % for tachycardia, and 85.8 % for bradycardia. Additionally, it achieved 67.0 % accuracy in classifying the four distinct deceleration patterns, with 80.9 % accuracy for late deceleration and 98.9 % for prolonged deceleration. The proposed multimodal deep learning algorithm serves as a reliable decision support tool for clinicians, significantly improving the detection and assessment of specific FHR events, which are crucial for fetal health monitoring.

Dynamic evolution of high-speed railway driver fatigue across scheduling shifts – a simulator study in China

ABSTRACT Scheduling significantly contributes to fatigue among high-speed rail (HSR) drivers, impacting both driving performance and safety. This study aims to analyse distinctiveness and evolutionary patterns of driver fatigue across different scheduling shifts, leveraging an HSR simulator and wearable devices. Through an extensive statistical examination, differences in most heart rate variability features were identified across shifts. The evolution of self-reported fatigue and physiological fatigue was investigated using a Markov chain and a hidden Markov model (HMM) that is extended using softmax regression, respectively. Results indicated a similarity in the initial fatigue state distribution and evolution trends across shifts, albeit with varying degrees of fluctuation. Morning shifts exhibited a higher likelihood of fatigue accumulation. The study revealed that even adequate pre-rest did not entirely counterbalance the impact of circadian rhythms. These findings may contribute to comprehending the temporal dynamics of driver fatigue evolution and offer insights for optimizing driver scheduling practices.

Wearable EEG-Based Brain-Computer Interface for Stress Monitoring.

Detecting stress is important for improving human health and potential, because moderate levels of stress may motivate people towards better performance at cognitive tasks, while chronic stress exposure causes impaired performance and health risks. We propose a Brain-Computer Interface (BCI) system to detect stress in the context of high-pressure work environments. The BCI system includes an electroencephalogram (EEG) headband with dry electrodes and an electrocardiogram (ECG) chest belt. We collected EEG and ECG data from 40 participants during two stressful cognitive tasks: the Cognitive Vigilance Task (CVT), and the Multi-Modal Integration Task (MMIT) we designed. We also recorded self-reported stress levels using the Dundee Stress State Questionnaire (DSSQ). The DSSQ results indicated that performing the MMIT led to significant increases in stress, while performing the CVT did not. Subsequently, we trained two different models to classify stress from non-stress states, one using EEG features, and the other using heart rate variability (HRV) features extracted from the ECG. Our EEG-based model achieved an overall accuracy of 81.0% for MMIT and 77.2% for CVT. However, our HRV-based model only achieved 62.1% accuracy for CVT and 56.0% for MMIT. We conclude that EEG is an effective predictor of stress in the context of stressful cognitive tasks. Our proposed BCI system shows promise in evaluating mental stress in high-pressure work environments, particularly when utilizing an EEG-based BCI.

Pilot turning behavior cognitive load analysis in simulated flight.

To identify the cognitive load of different turning tasks in simulated flight, a flight experiment was designed based on real "preliminary screening" training modules for pilots. Heart Rate Variability (HRV) and flight data were collected during the experiments using a flight simulator and a heart rate sensor bracelet. The turning behaviors in flight were classified into climbing turns, descending turns, and level flight turns. A recognition model for the cognitive load associated with these turning behaviors was developed using machine learning and deep learning algorithms. pnni_20, range_nni, rmssd, sdsd, nni_20, sd1, triangular_index indicators are negatively correlated with different turning load. The LSTM-Attention model excelled in recognizing turning tasks with varying cognitive load, achieving an F1 score of 0.9491. Specific HRV characteristics can be used to analyze cognitive load in different turn-ing tasks, and the LSTM-Attention model can provide references for future studies on the selection characteristics of pilot cognitive load, and offer guidance for pilot training, thus having significant implications for pilot training and flight safety.

Screening for moderate to severe obstructive sleep apnea by using heart rate variability features based on random forest algorithm.

More than 80% of patients with moderate to severe obstructive sleep apnea (OSA) are still not diagnosed timely. The prediction model based on random forest (RF) algorithm was established by using heart rate variability (HRV), clinical and demographic features so as to screen for the patients with high risk of moderate and severe obstructive sleep apnea. The sleep monitoring data of 798 patients were randomly divided into training set (n = 558) and test set (n = 240) in 7:3 proportion. Grid search was applied to determine the best parameters of the RF model. 10-fold cross validation was utilized to evaluate the predictive performance of the RF model, which was then compared to the performance of the Logistic regression model. Among the 798 patients, 638 were males and 160 were females, with the average age of 43.51 years old and the mean body mass index (BMI) of 25.92kg/m2. The sensitivity, specificity, accuracy, F1 score and the area under receiver operating characteristic curve for RF model and Logistic regression model were 94.68% vs. 73.94%; 73.08% vs. 86.54%; 90.00% vs. 76.67%; 0.94 vs. 0.83 and 0.83 vs. 0.80 respectively. The RF prediction model can effectively distinguish patients with moderate to severe OSA, which is expected to carry out in a large-scale population in order to screening for high-risk patients, and helps to evaluate the effect of OSA treatment continuously.

ER-GET: Emotion Recognition Based on Global ECG Trajectory.

In recent years, the recognition of human emotions based on electrocardiogram (ECG) signals has been considered a novel area of study among researchers. Despite the challenge of extracting latent emotion information from ECG signals, existing methods are able to recognize emotions by calculating the heart rate variability (HRV) features. However, such local features have drawbacks, as they do not provide a comprehensive description of ECG signals, leading to suboptimal recognition performance. For the first time, we propose a new strategy to extract hidden emotional information from the global ECG trajectory for emotion recognition. Specifically, a period of ECG signals is decomposed into sub-signals of different frequency bands through ensemble empirical mode decomposition (EEMD), and a series of multi-sequence trajectory graphs is constructed by orthogonally combining these sub-signals to extract latent emotional information. Additionally, to better utilize these graph features, a network has been designed that includes self-supervised graph representation learning and ensemble learning for classification. This approach surpasses recent notable works, achieving outstanding results, with an accuracy of 95.08% in arousal and 95.90% in valence detection. Additionally, this global feature is compared and discussed in relation to HRV features, with the intention of providing inspiration for subsequent research.

Classification of exercise fatigue levels by multi-class SVM from ECG and HRV.

Among the various physiological signals, electrocardiogram (ECG) is a valid criterion for the classification of various exercise fatigue. In this study, we combine features extracted by deep neural networks with linear features from ECG and heart rate variability (HRV) for exercise fatigue classification. First, the ECG signals are converted into 2-D images by using the short-term Fourier transform (STFT), and image features are extracted by the visual geometry group (VGG) . The extracted image and linear features of ECG and HRV are sent to the different types of classifiers to distinguish distinct exercise fatigue level. To validate performance, the proposed methods are tested on (i) an open-source EPHNOGRAM dataset and (ii) a self-collected dataset (n = 51). The results reveal that the classification based on the concatenated features has the highest accuracy, and the calculation time of the system is also significantly reduced. This demonstrates that the proposed novel hybrid approach can be used to assist in improving the accuracy and timeliness of exercise fatigue classification in a real-time exercise environment. The experimental results show that the proposed method outperforms other recent state-of-the-art methods in terms of accuracy 96.90%, sensitivity 96.90%, F1-score of 0.9687 in EPHNOGRAM and accuracy 92.17%, sensitivity 92.63%, F1-score of 0.9213 in self-collected dataset.

Tracking Vigilance Fluctuations in Real-Time: A Sliding-Window HRV-based Machine-Learning Approach.

Heart rate variability (HRV)-based machine learning models hold promise for real-world vigilance evaluation, yet their real-time applicability is limited by lengthy feature extraction times and reliance on subjective benchmarks. This study aimed to improve the objectivity and efficiency of HRV-based vigilance evaluation by associating HRV and behavior metrics through a sliding-window approach. Forty-four healthy adults underwent psychomotor vigilance tasks under both well-rested and sleep-deprived conditions, with simultaneous electrocardiogram recording. A sliding-window approach (30s length, 10s step) was used for HRV feature extraction and behavior assessment. Repeated-measures ANOVA was used to examine how HRV related to objective vigilance levels. Stability selection technique was applied for feature selection, and the vigilance ground truth-high (fastest 40%), intermediate (middle 20%), and low (slowest 40%)-were determined based on each participant's range of performance. Four machine-learning classifiers-k-nearest neighbours, support vector machine (SVM), AdaBoost, and random forest-were trained and tested using cross-validation. Fluctuated vigilance performance indicated pronounced state instability, particularly after sleep deprivation. Temporary decrements in performance were associated with a decrease in heart rate and an increase in time-domain heart rate variability. SVM achieved the best performance, with a cross-validated accuracy of 89% for binary classification of high versus low vigilance epochs. Overall accuracy dropped to 72% for three-class classification in leave-one-participant-out cross-validation, but SVM maintained a precision of 84% in identifying low-vigilance epochs. Sliding-window-based HRV metrics would effectively capture the fluctuations in vigilance during task execution, enabling more timely and accurate detection of performance decrement.

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.

Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals.

Heart Rate Variability (HRV) refers to the capability of the heart rhythm to vary at different times, typically reflecting the regulation of the heart by the autonomic nervous system. In recent years, with advancements in Electrocardiogram (ECG) signal processing technology, HRV features reflect various aspects of cardiac activity, such as variability in heart rate, cardiac health status, and responses. We extracted key features of HRV and used them to develop and evaluate an automatic recognition model for cardiac diseases. Consequently, we proposed the HRV Heart Disease Recognition (HHDR) method, employing the Spectral Magnitude Quantification (SMQ) technique for feature extraction. Firstly, the HRV signals are extracted through electrocardiogram signal processing. Then, by analyzing parts of the HRV signal within various frequency ranges, the SMQ method extracts rich features of partial information. Finally, the Random Forest (RF) classification computational method is employed to classify the extracted information, achieving efficient and accurate cardiac disease recognition. Experimental results indicate that this method surpasses current technologies in recognizing cardiac diseases, with an average accuracy rate of 95.1% for normal/diseased classification, and an average accuracy of 84.8% in classifying five different disease categories. Thus, the proposed HHDR method effectively utilizes the local information of HRV signals for efficient and accurate cardiac disease recognition, providing strong support for cardiac disease research in the medical field.

Increased heart rate fragmentation in those with Williams-Beuren syndrome suggests nonautonomic mechanistic contributors to sudden death risk.

Williams-Beuren syndrome (WBS) is a rare genetic condition caused by a chromosomal microdeletion at 7q11.23. It is a multisystem disorder characterized by distinct facies, intellectual disability, and supravalvar aortic stenosis (SVAS). Those with WBS are at increased risk of sudden death, but mechanisms underlying this remain poorly understood. We recently demonstrated autonomic abnormalities in those with WBS that are associated with increased susceptibility to arrhythmia and sudden cardiac death (SCD). A recently introduced method for heart rate variability (HRV) analysis called "heart rate fragmentation" (HRF) correlates with adverse cardiovascular events (CVEs) and death in studies where heart rate variability (HRV) failed to identify high-risk subjects. Some argue that HRF quantifies nonautonomic cardiovascular modulators. We, therefore, sought to apply HRF analysis to a WBS cohort to determine 1) if those with WBS show differences in HRF compared with healthy controls and 2) if HRF helps characterize HRV abnormalities in those with WBS. Similar to studies of those with coronary artery disease (CAD) and atherosclerosis, we found significantly higher HRF (4 out of 7 metrics) in those with WBS compared with healthy controls. Multivariable analyses showed a weak-to-moderate association between HRF and HRV, suggesting that HRF may reflect HRV characteristics not fully captured by traditional HRV metrics (autonomic markers). We also introduce a new metric inspired by HRF methodology, significant acute rate drop (SARD), which may detect vagal activity more directly. HRF and SARD may improve on traditional HRV measures to identify those at greatest risk for SCD both in those with WBS and in other populations.NEW & NOTEWORTHY This work is the first to apply heart rate fragmentation analyses to individuals with Williams syndrome and posits that the heart rate fragmentation parameter W3 may enable detection and investigation of phenomena underlying the proarrhythmic short-long-short RR interval sequences paradigm known to precede ventricular fibrillation and ventricular tachycardia. It also forwards a novel method for quantifying sinus arrhythmia and sinus pauses that likely correlate with parasympathetic activity.

Driver Fatigue Detection Using Heart Rate Variability Features from 2-Minute Electrocardiogram Signals While Accounting for Sex Differences.

Traffic accidents due to fatigue account for a large proportion of road fatalities. Based on simulated driving experiments with drivers recruited from college students, this paper investigates the use of heart rate variability (HRV) features to detect driver fatigue while considering sex differences. Sex-independent and sex-specific differences in HRV features between alert and fatigued states derived from 2 min electrocardiogram (ECG) signals were determined. Then, decision trees were used for driver fatigue detection using the HRV features of either all subjects or those of only males or females. Nineteen, eighteen, and thirteen HRV features were significantly different (Mann-Whitney U test, p < 0.01) between the two mental states for all subjects, males, and females, respectively. The fatigue detection models for all subjects, males, and females achieved classification accuracies of 86.3%, 94.8%, and 92.0%, respectively. In conclusion, sex differences in HRV features between drivers' mental states were found according to both the statistical analysis and classification results. By considering sex differences, precise HRV feature-based driver fatigue detection systems can be developed. Moreover, in contrast to conventional methods using HRV features from 5 min ECG signals, our method uses HRV features from 2 min ECG signals, thus enabling more rapid driver fatigue detection.

MDDBranchNet: A Deep Learning Model for Detecting Major Depressive Disorder Using ECG Signal.

Major depressive disorder (MDD) is a chronic mental illness which affects people's well-being and is often detected at a later stage of depression with a likelihood of suicidal ideation. Early detection of MDD is thus necessary to reduce the impact, however, it requires monitoring vitals in daily living conditions. EEG is generally multi-channel and due to difficulty in signal acquisition, it is unsuitable for home-based monitoring, whereas, wearable sensors can collect single-channel ECG. Classical machine-learning based MDD detection studies commonly use various heart rate variability features. Feature generation, which requires domain knowledge, is often challenging, and requires computation power, often unsuitable for real time processing, MDDBranchNet is a proposed parallel-branch deep learning model for MDD binary classification from a single channel ECG which uses additional ECG-derived signals such as R-R signal and degree distribution time series of horizontal visibility graph. The use of derived branches was able to increase the model's accuracy by around 7%. An optimal 20-second overlapped segmentation of ECG recording was found to be beneficial with a 70% prediction threshold for maximum MDD detection with a minimum false positive rate. The proposed model evaluated MDD prediction from signal excerpts, irrespective of location (first, middle or last one-third of the recording), instead of considering the entire ECG signal with minimal performance variation stressing the idea that MDD phenomena are likely to manifest uniformly throughout the recording.

Predicting the dynamics of heart rate variability in patients with type 1 diabetes against improving glycemic control

The aim of the study: to analyze the effect of improvement of glycemic control on heart rate variability changes in patients with type 1 diabetes against the background of insulin therapy correction and to predict this dynamics based on the parameters of continuous glucose monitoring. We examined 49 patients with the level of glycosylated hemoglobin ≥7% and &lt;10% without late diabetic complications. The average age – 32.0 (21.5; 38.0) years, the average disease duration – 9.5 (5.0; 17.5) years. The study was based on the simultaneous registration of heart rate variability and continuous glucose monitoring before and 3 months after correction of insulin therapy. Logistic regression analysis and ROC-analysis were used to predict the changes. After 3 months, the patients had significant decrease in the level of glycosylated hemoglobin, glycose variability, and a decrease in the frequency of hypoglycemic episodes. Heart rate variability increased in 73.5% of persons. The presence of hypoglycemia, standard deviation of blood glucose levels and glomerular filtration rate after treatment turned out to be prognostic factors for the predicting improvement in heart rate variability (the proportion of correct prediction of the patient's actual belonging to one or another prognostic group was 76.39%). Based on the calculation of the theoretical values of the positive result probability using the logistic equation, a detailed scale for predicting changes in heart rhythm variability for type 1 diabetes patients was proposed: up to 0.07 – a low probability of a positive result; 0.07-0.29 – the probability of a positive result is below average; 0.29-0.51 – a moderate probability of a positive result; 0.51-0.90 – high probability of a positive result; more than 0.90 – a very high probability of a positive result. We found that improvement of glycemic control leads to an increase in both frequency and time characteristics of heart rate variability. The increase in the likelihood of improvement of heart rate variability in patients with type 1 diabetes was more likely to be associated with reduced glycose variability and fewer hypoglycemic episodes. We developed a predictive mathematical model of heart rate variability based on the continuous glucose monitoring parameters for type 1 diabetes with sensitivity of 88.0% and specificity 68.18%, AUC 0.739 (p=0.001).

Влияние загрязнённой радионуклидами среды на сердечный ритм детей в современных условиях

The main aim was to study the characteristics of heart rate variability in 8- and 10-year boys and girls that permanently reside in areas with an increased level of radioactive contamination. The body functions are formed by close interaction of the body and the environment. The adaptive responses of the developing organism are improved at each ontogenetic stage as its contact with the environment become more complex. We found that features of heart rate regulation depend on the area of residence. The contribution of the autonomous circuit of heart rate regulation is increased for 8- and 10-year-old girls from radio-ecologically safe areas (RESA). Based on the principle of functional antagonism this leads to a weakening of the central circuit of regulation. The shift gradient of indicators is higher for 8-year-old girls from radio-ecologically unfavorable areas (REUA) compared to 10-year-old girls. This reflects the greater sensitivity of their organism to adverse factors. The dominance of the autonomous circuit of regulation was marked for 8- and 10-year-old boys from the RESA. In contrast an imbalance in the operation of regulatory mechanisms with an increase in the central regulatory circuit was found for boys from the REUA. High centralization of cardiac control indicates that adaptation mechanisms are in a state of pronounced tension. The increase in the shift gradient for boys from REUA falls at the age of 10 years. The results of the study revealed gender differences in the regulation of heart rhythm. The obtained data is important diagnostic aspects of morphofunctional maturation of the organism for subsequent ontogenetic stages depending on environmental living conditions.

Machine learning workflow for edge computed arrhythmia detection in exploration class missions

Deep-space missions require preventative care methods based on predictive models for identifying in-space pathologies. Deploying such models requires flexible edge computing, which Open Neural Network Exchange (ONNX) formats enable by optimizing inference directly on wearable edge devices. This work demonstrates an innovative approach to point-of-care machine learning model pipelines by combining this capacity with an advanced self-optimizing training scheme to classify periods of Normal Sinus Rhythm (NSR), Atrial Fibrillation (AFIB), and Atrial Flutter (AFL). 742 h of electrocardiogram (ECG) recordings were pre-processed into 30-second normalized samples where variable mode decomposition purged muscle artifacts and instrumentation noise. Seventeen heart rate variability and morphological ECG features were extracted by convoluting peak detection with Gaussian distributions and delineating QRS complexes using discrete wavelet transforms. The decision tree classifier’s features, parameters, and hyperparameters were self-optimized through stratified triple nested cross-validation ranked on F1-scoring against cardiologist labeling. The selected model achieved a macro F1-score of 0.899 with 0.993 for NSR, 0.938 for AFIB, and 0.767 for AFL. The most important features included median P-wave amplitudes, PRR20, and mean heart rates. The ONNX-translated pipeline took 9.2 s/sample. This combination of our self-optimizing scheme and deployment use case of ONNX demonstrated overall accurate operational tachycardia detection.

Assessment of heart rate variability in 4–6 years-old children in contrast hardening

The article presents the results of assessing the features of heart rate variability in children of senior preschool age (4-6 years old) who are engaged in contrast hardening according to a specially developed technique (Fisher T.A., Kolyvanova S.S., Dremina E.L., patent RU2744024C2, 9.07.2019) in a preschool educational institution. Significantly higher statistical indicators evaluating the overall autonomic tone (SDNN, RMSSD, рNN50, CV) were revealed in children involved in contrast hardening compared to the control group. Evaluation of statistical, spectral parameters of heart rate variability in the hardening group indicated the predominance of parasympathetic influences on heart rate and a shift in the autonomic balance towards parasympathicotonia. This was expressed in a significant decrease in VPR, an increase in high-frequency (HF) indicators and a decrease in the LF/HF index in children of the hardening group compared with the control.

Percent duration of heart rate acceleration within the respiratory cycle: a novel approach to assess heart rate asymmetry.

Accelerations and decelerations of heart rate are nonsymmetrical in the magnitude and number of beat-to-beat changes. The asymmetric features of heart rate variability are related to respiratory durations. To explore the link between respiration and heart rate asymmetry (HRA), we evaluated 14 seated, healthy young adults who breathed with nine combinations of inspiration duration (TI) and expiration duration (TE), chosen respectively from 2, 4, and 6 s. A 5-min R-R interval (RRI) time series was obtained from each study period to construct an averaged pattern waveform relative to the respiratory cycle. We observed that the time interval between inspiration onset and RRI minimum progressively lengthened as TI and TE increased. The time interval between expiration onset and RRI maximum also lengthened when TE increased but shortened when TI increased. Consequently, TI and TE had different effects on the acceleration time (AT; from RRI maximum to RRI minimum) and deceleration time (DT; from RRI minimum to RRI maximum). The percentage of AT within the respiratory cycle showed a strong correlation with traditional Guzik's (r = 0.862, P < 0.001) and Porta's (r = 0.878, P < 0.001) indexes of HRA assessed in a Poincaré plot analysis. These findings suggest that, in addition to considering the magnitude and number of beat-to-beat changes, HRA can also be assessed based on another aspect: the duration of consecutive changes. The stepwise link between the duration of heart rate change and respiratory duration provides insight into the mechanisms connecting respiration to HRA.NEW & NOTEWORTHY In healthy adults who regulated their breathing across nine combinations of inspiration and expiration durations, we used averaged pattern waveform technique to quantify the durations of heart rate acceleration and deceleration within the respiratory cycle. The percent duration of acceleration showed a strong correlation with traditional heart rate asymmetry indexes, which evaluate the magnitude and number of beat-to-beat changes. This new approach opens a window to explore the asymmetric features of heart rate variability.