Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics

Inter-day reliability of heart rate complexity and variability metrics in healthy highly active younger and older adults

PURPOSE

To investigate the inter-day reliability of time-domain, frequency-domain, and nonlinear HRV metrics in healthy highly active younger and older adults. The study also assessed the effect of age on the HRV metrics.

METHODS

Forty-four older adults (34 M, 10F; 59 ± 5 years;V ˙ O 2peak  = 40.9 ± 7.6 ml kg-1 min-1) and twenty-two younger adults (16 M, 6F; 22 ± 4 years;V ˙ O 2peak  = 47.2 ± 12.8 ml kg-1 min-1) attended the laboratory. Visit one assessed aerobic fitness through an exercise test. In visits two and three, participants completed a 30-min supine RR interval measurement to derive the HRV metrics.

RESULTS

The younger group (YG) and older group (OG) demonstrated poor to good day-to-day relative and absolute reliability for all HRV metrics (OG, ICCs = 0.33 to 0.69 and between day CVs = 3.8 to 29.2%; YG, ICCs = 0.37 to 0.93 and between day CVs = 3.5 to 36.5%). There was a significant reduction in ApEn (P < 0.001), SampEn (P = 0.031), RMSSD (P < 0.001), SDNN (P < 0.001), LF power (P < 0.001) and HF power (P < 0.001), HRV metrics with ageing. There was no significant effect of age the complexity metrics DFA α1 (P = 0.107), α2 (P = 0.147) and CI-8 (P = 0.493).

CONCLUSION

HRV metrics are reproducible between days in both healthy highly active younger and older adults. There is a decline in linear and nonlinear HRV metrics with age, albeit there being no age-related change in the nonlinear metrics, DFA α1, α2 and CI-8.

Using explainable AI to investigate electrocardiogram changes during healthy aging-From expert features to raw signals

Cardiovascular diseases remain the leading global cause of mortality. Age is an important covariate whose effect is most easily investigated in a healthy cohort to properly distinguish the former from disease-related changes. Traditionally, most of such insights have been drawn from the analysis of electrocardiogram (ECG) feature changes in individuals as they age. However, these features, while informative, may potentially obscure underlying data relationships. In this paper we present the following contributions: (1) We employ a deep-learning model and a tree-based model to analyze ECG data from a robust dataset of healthy individuals across varying ages in both raw signals and ECG feature format. (2) We use explainable AI methods to identify the most discriminative ECG features across age groups.(3) Our analysis with tree-based classifiers reveals age-related declines in inferred breathing rates and identifies notably high SDANN values as indicative of elderly individuals, distinguishing them from younger adults. (4) Furthermore, the deep-learning model underscores the pivotal role of the P-wave in age predictions across all age groups, suggesting potential changes in the distribution of different P-wave types with age. These findings shed new light on age-related ECG changes, offering insights that transcend traditional feature-based approaches.

Slope Entropy Characterisation: An Asymmetric Approach to Threshold Parameters Role Analysis

Slope Entropy (SlpEn) is a novel method recently proposed in the field of time series entropy estimation. In addition to the well-known embedded dimension parameter, m, used in other methods, it applies two additional thresholds, denoted as δ and γ, to derive a symbolic representation of a data subsequence. The original paper introducing SlpEn provided some guidelines for recommended specific values of these two parameters, which have been successfully followed in subsequent studies. However, a deeper understanding of the role of these thresholds is necessary to explore the potential for further SlpEn optimisations. Some works have already addressed the role of δ, but in this paper, we extend this investigation to include the role of γ and explore the impact of using an asymmetric scheme to select threshold values. We conduct a comparative analysis between the standard SlpEn method as initially proposed and an optimised version obtained through a grid search to maximise signal classification performance based on SlpEn. The results confirm that the optimised version achieves higher time series classification accuracy, albeit at the cost of significantly increased computational complexity.

Heart failure classification using deep learning to extract spatiotemporal features from ECG

BACKGROUND

Heart failure is a syndrome with complex clinical manifestations. Due to increasing population aging, heart failure has become a major medical problem worldwide. In this study, we used the MIMIC-III public database to extract the temporal and spatial characteristics of electrocardiogram (ECG) signals from patients with heart failure.

METHODS

We developed a NYHA functional classification model for heart failure based on a deep learning method. We introduced an integrating attention mechanism based on the CNN-LSTM-SE model, segmenting the ECG signal into 2 to 20 s long segments. Ablation experiments showed that the 12 s ECG signal segments could be used with the proposed deep learning model for superior classification of heart failure.

RESULTS

The accuracy, positive predictive value, sensitivity, and specificity of the NYHA functional classification method were 99.09, 98.9855, 99.033, and 99.649%, respectively.

CONCLUSIONS

The comprehensive performance of this model exceeds similar methods and can be used to assist in clinical medical diagnoses.

Modifications of long-term heart rate variability produced in an experimental model of diet-induced metabolic syndrome

Metabolic syndrome (MetS) has been linked to a higher prevalence of cardiac arrhythmias, the most frequent being atrial fibrillation, but the mechanisms are not well understood. One possible underlying mechanism may be an abnormal modulation of autonomic nervous system activity, which can be quantified by analysing heart rate variability (HRV). Our aim was to investigate the modifications of long-term HRV in an experimental model of diet-induced MetS to identify the early changes in HRV and the link between autonomic dysregulation and MetS components. NZW rabbits were randomly assigned to control (n = 10) or MetS (n = 10) groups, fed 28 weeks with high-fat, high-sucrose diet. 24-hour recordings were used to analyse HRV at week 28 using time-domain, frequency-domain and nonlinear analyses. Time-domain analysis showed a decrease in RR interval and triangular index (Ti). In the frequency domain, we found a decrease in the low frequency band. Nonlinear analyses showed a decrease in DFA-α1 and DFA-α2 (detrended fluctuations analysis) and maximum multiscale entropy. The strongest association between HRV parameters and markers of MetS was found between Ti and mean arterial pressure, and Ti and left atrial diameter, which could point towards the initial changes induced by the autonomic imbalance in MetS.

A fast permutation entropy for pulse rate variability online analysis with one-sample recursion

Pulse rate variability (PRV) signals are extracted from pulsation signal can be effectively used for cardiovascular disease monitoring in wearable devices. Permutation entropy (PE) algorithm is an effective index for the analysis of PRV signals. However, PE is computationally intensive and impractical for online PRV processing on wearable devices. Therefore, to overcome this challenge, a fast permutation entropy (FPE) algorithm is proposed based on the microprocessor data updating process in this paper, which can analyze PRV signals with single-sample recursive. The simulation data and PRV signals extracted from pulse signals in "Fantasia database" were utilized to verify the performance and accuracy of the improved methods. The results show that the speed of FPE is 211 times faster than PE and maintain the accuracy of algorithm (Root Mean Squared Error = 0) for simulation data with a length of 10,000 samples and embedded dimension m = 5, time delay τ = 5, buffer length Lw = 512. For the RRV signals with 3000∼5000 samples, the result show that the consumption of FPE is less than 0.2 s, which is 175 times faster than PE. This indicates that FPE has better application performance than PE. Furthermore, a low-cost wearable signal detection system is developed to verify the proposed method, the result show that the proposed method can calculate the FPE of PRV signal online with single-sample recursive calculation. Subsequently, entropy-based features are used to explore the performance of decision trees in identifying life-threatening arrhythmias, and the method resulted in a classification accuracy of 85.43%. It can therefore be inferred that the proposed method has great potential in cardiovascular disease.

Characterization of Physiological Noise in Complex Cardiovascular Variability Series

The cardiovascular system can be analyzed using spectral, nonlinear, and complexity metrics. Nevertheless, dynamical noise may significantly impact these quantifiers. To our knowledge, there has been no attempt to quantify the intrinsic cardiovascular system noise driving heartbeat dynamics. To this end, this study presents a novel, model-free framework to define and quantify physiological noise using nonlinear Approximate Entropy profile. The framework was tested using analytical noisy series and then applied to real Heart Rate Variability (HRV) series gathered from a publicly-available dataset of recordings from 19 young and 19 elderly subjects watching the movie "Fantasia". Results suggest that physiological noise may account for over 15% of cardiovascular dynamics and is influenced by aging, with decreased cardiac noise in the elderly compared to the young subjects. Our findings indicate that physiological noise is a crucial factor in characterizing cardiovascular dynamics, and current spectral, nonlinear, and complexity assessments should take into account underlying dynamical noise estimates.

Visibility Graph Analysis of Heartbeat Time Series: Comparison of Young vs. Old, Healthy vs. Diseased, Rest vs. Exercise, and Sedentary vs. Active

Using the visibility graph algorithm (VGA), a complex network can be associated with a time series, such that the properties of the time series can be obtained by studying those of the network. Any value of the time series becomes a node of the network, and the number of other nodes that it is connected to can be quantified. The degree of connectivity of a node is positively correlated with its magnitude. The slope of the regression line is denoted by k-M, and, in this work, this parameter was calculated for the cardiac interbeat time series of different contrasting groups, namely: young vs. elderly; healthy subjects vs. patients with congestive heart failure (CHF); young subjects and adults at rest vs. exercising young subjects and adults; and, finally, sedentary young subjects and adults vs. active young subjects and adults. In addition, other network parameters, including the average degree and the average path length, of these time series networks were also analyzed. Significant differences were observed in the k-M parameter, average degree, and average path length for all analyzed groups. This methodology based on the analysis of the three mentioned parameters of complex networks has the advantage that such parameters are very easy to calculate, and it is useful to classify heartbeat time series of subjects with CHF vs. healthy subjects, and also for young vs. elderly subjects and sedentary vs. active subjects.

Performance Assessment of Heartbeat Detection Algorithms on Photoplethysmograph and Functional NearInfrared Spectroscopy Signals

With wearable sensors, the acquisition of physiological signals has become affordable and feasible in everyday life. Specifically, Photoplethysmography (PPG), being a low-cost and highly portable technology, has attracted notable interest for measuring and diagnosing cardiac activity, one of the most important physiological and autonomic indicators. In addition to the technological development, several specific signal-processing algorithms have been designed to enable reliable detection of heartbeats and cope with the lower quality of the signals. In this study, we compare three heartbeat detection algorithms: Derivative-Based Detection (DBD), Recursive Combinatorial Optimization (RCO), and Multi-Scale Peak and Trough Detection (MSPTD). In particular, we considered signals from two datasets, namely, the PPG-DALIA dataset (N = 15) and the FANTASIA dataset (N = 20) which differ in terms of signal characteristics (sampling frequency and length) and type of acquisition devices (wearable and medical-grade). The comparison is performed both in terms of heartbeat detection performance and computational workload required to execute the algorithms. Finally, we explore the applicability of these algorithms on the cardiac component obtained from functional Near InfraRed Spectroscopy signals (fNIRS).The results indicate that, while the MSPTD algorithm achieves a higher F1 score in cases that involve body movements, such as cycling (MSPTD: Mean = 74.7, SD = 14.4; DBD: Mean = 54.4, SD = 21.0; DBD + RCO: Mean = 49.5, SD = 22.9) and walking up and down the stairs (MSPTD: Mean = 62.9, SD = 12.2; DBD: Mean = 50.5, SD = 11.9; DBD + RCO: Mean = 45.0, SD = 14.0), for all other activities the three algorithms perform similarly. In terms of computational complexity, the computation time of the MSPTD algorithm appears to grow exponentially with the signal sampling frequency, thus requiring longer computation times in the case of high-sampling frequency signals, where the usage of the DBD and RCO algorithms might be preferable. All three algorithms appear to be appropriate candidates for exploring the applicability of heartbeat detection on fNIRS data.

Characterization of autonomic states by complex sympathetic and parasympathetic dynamics

Assessment of heartbeat dynamics provides a promising framework for non-invasive monitoring of cardiovascular and autonomic states. Nevertheless, the non-specificity of such measurements among clinical populations and healthy conditions associated with different autonomic states severely limits their applicability and exploitation in naturalistic conditions. This limitation arises especially when pathological or postural change-related sympathetic hyperactivity is compared to autonomic changes across age and experimental conditions. In this frame, we investigate the intrinsic irregularity and complexity of cardiac sympathetic and vagal activity series in different populations, which are associated with different cardiac autonomic dynamics. Sample entropy, fuzzy entropy, and distribution entropy are calculated on the recently proposed sympathetic and parasympathetic activity indices (SAI and PAI) series, which are derived from publicly available heartbeat series of congestive heart failure patients, elderly and young subjects watching a movie in the supine position, and healthy subjects undergoing slow postural changes. Results show statistically significant differences between pathological/old subjects and young subjects in the resting state and during slow tilt, with interesting trends in SAI- and PAI-related entropy values. Moreover, while CHF patients and healthy subjects in upright position show the higher cardiac sympathetic activity, elderly and young subjects in resting state showed higher vagal activity. We conclude that quantification of intrinsic cardiac complexity from sympathetic and vagal dynamics may provide new physiology insights and improve on the non-specificity of heartbeat-derived biomarkers.

Heartbeat detector from ECG and PPG signals based on wavelet transform and upper envelopes

The analysis of cardiac activity is one of the most common elements for evaluating the state of a subject, either to control possible health risks, sports performance, stress levels, etc. This activity can be recorded using different techniques, with electrocardiogram and photoplethysmogram being the most common. Both techniques make significantly different waveforms, however the first derivative of the photoplethysmographic data produces a signal structurally similar to the electrocardiogram, so any technique focusing on detecting QRS complexes, and thus heartbeats in electrocardiogram, is potentially applicable to photoplethysmogram. In this paper, we develop a technique based on the wavelet transform and envelopes to detect heartbeats in both electrocardiogram and photoplethysmogram. The wavelet transform is used to enhance QRS complexes with respect to other signal elements, while the envelopes are used as an adaptive threshold to determine their temporal location. We compared our approach with three other techniques using electrocardiogram signals from the Physionet database and photoplethysmographic signals from the DEAP database. Our proposal showed better performances when compared to others. When the electrocardiographic signal was considered, the method had an accuracy greater than 99.94%, a true positive rate of 99.96%, and positive prediction value of 99.76%. When photoplethysmographic signals were investigated, an accuracy greater than 99.27%, a true positive rate of 99.98% and positive prediction value of 99.50% were obtained. These results indicate that our proposal can be adapted better to the recording technology.

A fast sample entropy for pulse rate variability analysis

Sample entropy is an effective nonlinear index for analyzing pulse rate variability (PRV) signal, but it has problems with a large amount of calculation and time consumption. Therefore, this study proposes a fast sample entropy calculation method to analyze the PRV signal according to the microprocessor process of data updating and the principle of sample entropy. The simulated data and PRV signal are employed as experimental data to verify the accuracy and time consumption of the proposed method. The experimental results on simulated data display that the proposed improved sample entropy can improve the operation rate of the entropy value by a maximum of 47.6 times and an average of 28.6 times and keep the entropy value unchanged. Experimental results on PRV signal display that the proposed improved sample entropy has great potential in the real-time processing of physiological signals, which can increase approximately 35 times.

Biometric Recognition: A Systematic Review on Electrocardiogram Data Acquisition Methods

In the last decades, researchers have shown the potential of using Electrocardiogram (ECG) as a biometric trait due to its uniqueness and hidden nature. However, despite the great number of approaches found in the literature, no agreement exists on the most appropriate methodology. This paper presents a systematic review of data acquisition methods, aiming to understand the impact of some variables from the data acquisition protocol of an ECG signal in the biometric identification process. We searched for papers on the subject using Scopus, defining several keywords and restrictions, and found a total of 121 papers. Data acquisition hardware and methods vary widely throughout the literature. We reviewed the intrusiveness of acquisitions, the number of leads used, and the duration of acquisitions. Moreover, by analyzing the literature, we can conclude that the preferable solutions include: (1) the use of off-the-person acquisitions as they bring ECG biometrics closer to viable, unconstrained applications; (2) the use of a one-lead setup; and (3) short-term acquisitions as they required fewer numbers of contact points, making the data acquisition of benefit to user acceptance and allow faster acquisitions, resulting in a user-friendly biometric system. Thus, this paper reviews data acquisition methods, summarizes multiple perspectives, and highlights existing challenges and problems. In contrast, most reviews on ECG-based biometrics focus on feature extraction and classification methods.

Age-dependent cardiorespiratory directional coupling in wake-resting state

Objective.Cooperation in the cardiorespiratory system helps maintain internal stability. Various types of system interactions have been investigated; however, the characteristics of the interactions have mostly been studied using data collected in well-defined physiological states, such as sleep. Furthermore, most analyses provided general information about the interaction, making it difficult to quantify how the systems influenced one another.Approach.Cardiorespiratory directional coupling was investigated in different age groups (20 young and 19 elderly subjects) in a wake-resting state. The directionality index (DI) was calculated using instantaneous phases from the heartbeat interval and respiratory signal to provide information about the strength and direction of interaction between the systems. Statistical analysis was performed between the groups on the DI and independent measures of directionality (nc_r: influence from cardiac system to respiratory system, and nc_c: influence from the respiratory system to the cardiac system).Main results.The values of DI were -0.52 and -0.17 in the young and elderly groups, respectively (p< 0.001). Furthermore, the values of nc_rand nc_cwere found to be significantly different between the groups (p< 0.001), respectively.Significance.Changes in both directions between the systems influence different aspects of cardiorespiratory coupling between the groups. This observation could be linked to different levels of autonomic modulation associated with ageing. Our approach could aid in quantitatively tracking and comprehending how systems interact in response to physiological and environmental changes. It could also be used to understand how abnormal interaction characteristics influence physiological system dysfunctions and disorders.

Advances in Multivariate and Multiscale Physiological Signal Analysis

Physiological systems are characterized by complex dynamics and nonlinear behaviors due to their intricate structural organization and regulatory mechanisms [...].

Information-Based Similarity of Ordinal Pattern Sequences as a Novel Descriptor in Obstructive Sleep Apnea Screening Based on Wearable Photoplethysmography Bracelets

Obstructive sleep apnea (OSA) is a common respiratory disorder associated with autonomic nervous system (ANS) dysfunction, resulting in abnormal heart rate variability (HRV). Capable of acquiring heart rate (HR) information with more convenience, wearable photoplethysmography (PPG) bracelets are proven to be a potential surrogate for electrocardiogram (ECG)-based devices. Meanwhile, bracelet-type PPG has been heavily marketed and widely accepted. This study aims to investigate the algorithm that can identify OSA with wearable devices. The information-based similarity of ordinal pattern sequences (OP_IBS), which is a modified version of the information-based similarity (IBS), has been proposed as a novel index to detect OSA based on wearable PPG signals. A total of 92 PPG recordings (29 normal subjects, 39 mild-moderate OSA subjects and 24 severe OSA subjects) were included in this study. OP_IBS along with classical indices were calculated. For severe OSA detection, the accuracy of OP_IBS was 85.9%, much higher than that of the low-frequency power to high-frequency power ratio (70.7%). The combination of OP_IBS, IBS, CV and LF/HF can achieve 91.3% accuracy, 91.0% sensitivity and 91.5% specificity. The performance of OP_IBS is significantly improved compared with our previous study based on the same database with the IBS method. In the Physionet database, OP_IBS also performed exceptionally well with an accuracy of 91.7%. This research shows that the OP_IBS method can access the HR dynamics of OSA subjects and help diagnose OSA in clinical environments.

Fractal Properties of Heart Rate Dynamics: A New Biomarker for Anesthesia-Biphasic Changes in General Anesthesia and Decrease in Spinal Anesthesia

Processed electroencephalogram (EEG) has been considered a useful tool for measuring the depth of anesthesia (DOA). However, because of its inability to detect the activities of the brain stem and spinal cord responsible for most of the vital signs, a new biomarker for measuring the multidimensional activities of the central nervous system under anesthesia is required. Detrended fluctuation analysis (DFA) is a new technique for detecting the scaling properties of nonstationary heart rate (HR) behavior. This study investigated the changes in fractal properties of heart rate variability (HRV), a nonlinear analysis, under intravenous propofol, inhalational desflurane, and spinal anesthesia. We compared the DFA method with traditional spectral analysis to evaluate its potential as an alternative biomarker under different levels of anesthesia. Eighty patients receiving elective procedures were randomly allocated different anesthesia. HRV was measured with spectral analysis and DFA short-term (4-11 beats) scaling exponent (DFAα1). An increase in DFAα1 followed by a decrease at higher concentrations during propofol or desflurane anesthesia is observed. Spinal anesthesia decreased the DFAα1 and low-/high-frequency ratio (LF/HF ratio). DFAα1 of HRV is a sensitive and specific method for distinguishing changes from baseline to anesthesia state. The DFAα1 provides a potential real-time biomarker to measure HRV as one of the multiple dimensions of the DOA.

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

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

Slope Entropy Characterisation: The Role of the δ Parameter

Many time series entropy calculation methods have been proposed in the last few years. They are mainly used as numerical features for signal classification in any scientific field where data series are involved. We recently proposed a new method, Slope Entropy (SlpEn), based on the relative frequency of differences between consecutive samples of a time series, thresholded using two input parameters, γ and δ. In principle, δ was proposed to account for differences in the vicinity of the 0 region (namely, ties) and, therefore, was usually set at small values such as 0.001. However, there is no study that really quantifies the role of this parameter using this default or other configurations, despite the good SlpEn results so far. The present paper addresses this issue, removing δ from the SlpEn calculation to assess its real influence on classification performance, or optimising its value by means of a grid search in order to find out if other values beyond the 0.001 value provide significant time series classification accuracy gains. Although the inclusion of this parameter does improve classification accuracy according to experimental results, gains of 5% at most probably do not support the additional effort required. Therefore, SlpEn simplification could be seen as a real alternative.

The association between continuous ambulatory heart rate, heart rate variability, and 24-h rhythms of heart rate with familial longevity and aging

Aging is associated with changes in heart rate (HR), heart rate variability (HRV), and 24-h rhythms in HR. Longevity has been linked to lower resting HR, while a higher resting HR and a decreased HRV were linked to cardiovascular events and increased mortality risk. HR and HRV are often investigated during a short electrocardiogram (ECG) measurement at a hospital. In this study, we aim to investigate the relationship between HR parameters with familial longevity and chronological age derived from continuous ambulatory ECG measurements collected over a period of 24 to 90 hours. We included 73 middle-aged participants (mean (SD) age: 67.0 (6.16) years), comprising 37 offspring of long-lived families, 36 of their partners, and 35 young participants (22.8 (3.96) years). We found no association with familial longevity, but middle-aged participants had lower 24-h HR (average and maximum HR, not minimum HR), lower amplitudes, and earlier trough and peak times than young participants. Associations in HR with chronological age could be caused by the aging process or by differences in environmental factors. Interestingly, middle-aged participants had a less optimal HRV during long-term recordings in both the sleep and awake periods, which might indicate that their heart is less adaptable than that of young participants. This could be a first indication of deteriorated cardiovascular health in middle-aged individuals.

Maternal autonomic responsiveness is attenuated in healthy pregnancy: a phase rectified signal averaging analysis

Autonomic regulation is essential in enabling a healthy pregnancy. In fact, several pregnancy complications are associated with autonomic dysfunction. Better understanding of the maternal autonomic state during healthy pregnancy may aid in the early detection of such complications. One aspect of autonomic regulation is autonomic responsiveness, which can by assessed by phase rectified signal averaging (PRSA). While other areas of research have found blunted physiological responses in pregnancy, this paper presents the first investigation of maternal autonomic responsiveness as assessed by PRSA. We find significantly reduced rates of responses, as well as an attenuated capacity for heart rate acceleration when comparing pregnant women to non-pregnant controls. We hypothesize that this attenuated autonomic control may serve to protect the mother against her imbalanced autonomic state, as increased sympathetic and decreased parasympathetic modulation accompany healthy pregnancies. Clinical Relevance- Maternal autonomic responsiveness is attenuated in pregnancy in comparison to non-pregnant women. Understanding maternal autonomic state not only improves our knowledge of gestational physiology but also forms the basis for the early detection of pregnancy complications associated with maternal autonomic dysfunction.

Heart Rate Variability in Healthy Subjects During Monitored, Short-Term Stress Followed by 24-hour Cardiac Monitoring

Heart Rate Variability (HRV) can be a useful metric to capture meaningful information about heart function. One of the non-linear indices used to analyze HRV, Detrended Fluctuation Analysis (DFA), finds short and long-term correlations in RR intervals to capture quantitative information about variability. This study focuses on the impact of visual and mental stimulation on HRV as expressed via DFA within healthy adults. Visual stimulation can activate the automatic nervous system to directly impact physiological behavior such as heart rate. In this investigation of HRV, 70 participants (21 males) viewed images on a screen followed by a math and recall task. Each viewing segment lasted 2 min and 18 s. The math and memory recall task segment lasted 4 min total. This process was repeated 9 times during which the participants’ electrocardiogram was recorded. 37 participants (12 males) opted in for an additional 24-h Holter recording after the viewing and task segments of the study were complete. Participants were randomly assigned to either a pure (organized image presentation) or mixed (random image presentation) image regime for the viewing portion of the study to investigate the impact of the external environment on HRV. DFA α1 was extracted from the RR intervals. Our findings suggest that DFA α1 can differentiate between the viewing [DFA α1 range from 0.96 (SD = 0.25) to 1.08 (SD = 0.22)] and the task segments [DFA α1 range from 1.17 (SD = 0.21) to 1.26 (SD = 0.25)], p < 0.0006 for all comparisons. However, DFA α1 was not able to distinguish between the two image regimes. During the 24-hour follow up, participants had an average DFA α1 = 1.09 (SD = 0.14). In conclusion, our findings suggest a graded response in DFA during short term stimulation and a responsiveness in participants to adjust physiologically to their external environment expressed through the DFA exponent.

Heart Rate Fractality Disruption as a Footprint of Subthreshold Depressive Symptoms in a Healthy Population

OBJECTIVE

Psychopathology (and depression in particular) is a cardiovascular risk factor independent from any co-occurring pathology. This link is traced back to the mind-heart-body connection, whose underlying mechanisms are still not completely known. To study psychopathology in relation to the heart, it is necessary to observe the autonomic nervous system, which mediates among the parts of that connection. Its gold standard of evaluation is the study of heart rate variability (HRV). To investigate whether any association exists between the HRV parameters and sub-threshold depressive symptoms in a sample of healthy subjects.

METHOD

In this cross-sectional study, two short-term HRV recordings (5 min - supine and sitting) have been analyzed in 77 healthy subjects. Here we adopted a three-fold approach to evaluate HRV: a set of scores belonging to the time domain; to the frequency domain (high, low, and very low frequencies) and a set of 'nonlinear' parameters. The PHQ-9 (Patient Health Questionnaire-9) scale was used to detect depressive symptoms.

RESULTS

Depressive symptoms were associated only with a parameter from the non-linear approach and specifically the long-term fluctuations of fractal dimensions (DFA-α2). This association remained significant even after controlling for age, gender, BMI (Body-Mass-Index), arterial hypertension, anti-hypertensive drugs, dyslipidemia, and smoking habits. Moreover, the DFA-α2 was not affected by the baroreflex (postural change), unlike other autonomic markers.

CONCLUSIONS

Fractal analysis of HRV (DFA-α2) allows then to predict depressive symptoms below the diagnostic threshold in healthy subjects regardless of their health status. DFA-α2 may be considered as an imprint of subclinical depression on the heart rhythm.

ResNet-50 for 12-Lead Electrocardiogram Automated Diagnosis

Nowadays, the implementation of Artificial Intelligence (AI) in medical diagnosis has attracted major attention within both the academic literature and industrial sector. AI would include deep learning (DL) models, where these models have been achieving a spectacular performance in healthcare applications. According to the World Health Organization (WHO), in 2020 there were around 25.6 million people who died from cardiovascular diseases (CVD). Thus, this paper aims to shad the light on cardiology since it is widely considered as one of the most important in medicine field. The paper develops an efficient DL model for automatic diagnosis of 12-lead electrocardiogram (ECG) signals with 27 classes, including 26 types of CVD and a normal sinus rhythm. The proposed model consists of Residual Neural Network (ResNet-50). An experimental work has been conducted using combined public databases from the USA, China, and Germany as a proof-of-concept. Simulation results of the proposed model have achieved an accuracy of 97.63% and a precision of 89.67%. The achieved results are validated against the actual values in the recent literature.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

RapidHRV: an open-source toolbox for extracting heart rate and heart rate variability

Heart rate and heart rate variability have enabled insight into a myriad of psychophysiological phenomena. There is now an influx of research attempting using these metrics within both laboratory settings (typically derived through electrocardiography or pulse oximetry) and ecologically-rich contexts (via wearable photoplethysmography, i.e., smartwatches). However, these signals can be prone to artifacts and a low signal to noise ratio, which traditionally are detected and removed through visual inspection. Here, we developed an open-source Python package, RapidHRV, dedicated to the preprocessing, analysis, and visualization of heart rate and heart rate variability. Each of these modules can be executed with one line of code and includes automated cleaning. In simulated data, RapidHRV demonstrated excellent recovery of heart rate across most levels of noise (>=10 dB) and moderate-to-excellent recovery of heart rate variability even at relatively low signal to noise ratios (>=20 dB) and sampling rates (>=20 Hz). Validation in real datasets shows good-to-excellent recovery of heart rate and heart rate variability in electrocardiography and finger photoplethysmography recordings. Validation in wrist photoplethysmography demonstrated RapidHRV estimations were sensitive to heart rate and its variability under low motion conditions, but estimates were less stable under higher movement settings.

The Movesense Medical Sensor Chest Belt Device as Single Channel ECG for RR Interval Detection and HRV Analysis during Resting State and Incremental Exercise: A Cross-Sectional Validation Study

The value of heart rate variability (HRV) in the fields of health, disease, and exercise science has been established through numerous investigations. The typical mobile-based HRV device simply records interbeat intervals, without differentiation between noise or arrythmia as can be done with an electrocardiogram (ECG). The intent of this report is to validate a new single channel ECG device, the Movesense Medical sensor, against a conventional 12 channel ECG. A heterogeneous group of 21 participants performed an incremental cycling ramp to failure with measurements of HRV, before (PRE), during (EX), and after (POST). Results showed excellent correlations between devices for linear indexes with Pearson's r between 0.98 to 1.0 for meanRR, SDNN, RMSSD, and 0.95 to 0.97 for the non-linear index DFA a1 during PRE, EX, and POST. There was no significant difference in device specific meanRR during PRE and POST. Bland-Altman analysis showed high agreement between devices (PRE and POST: meanRR bias of 0.0 and 0.4 ms, LOA of 1.9 to -1.8 ms and 2.3 to -1.5; EX: meanRR bias of 11.2 to 6.0 ms; LOA of 29.8 to -7.4 ms during low intensity exercise and 8.5 to 3.5 ms during high intensity exercise). The Movesense Medical device can be used in lieu of a reference ECG for the calculation of HRV with the potential to differentiate noise from atrial fibrillation and represents a significant advance in both a HR and HRV recording device in a chest belt form factor for lab-based or remote field-application.

A Multiscale Partition-Based Kolmogorov–Sinai Entropy for the Complexity Assessment of Heartbeat Dynamics

Background: Several methods have been proposed to estimate complexity in physiological time series observed at different time scales, with a particular focus on heart rate variability (HRV) series. In this frame, while several complexity quantifiers defined in the multiscale domain have already been investigated, the effectiveness of a multiscale Kolmogorov–Sinai (K-S) entropy has not been evaluated yet for the characterization of heartbeat dynamics. Methods: The use of the algorithmic information content, which is estimated through an effective compression algorithm, is investigated to quantify multiscale partition-based K-S entropy on publicly available experimental HRV series gathered from young and elderly subjects undergoing a visual elicitation task (Fantasia). Moreover, publicly available HRV series gathered from healthy subjects, as well as patients with atrial fibrillation and congestive heart failure in unstructured conditions have been analyzed as well. Results: Elderly people are associated with a lower HRV complexity and a more predictable cardiovascular dynamics, with significantly lower partition-based K-S entropy than the young adults. Major differences between these groups occur at partitions greater than six. In case of partition cardinality greater than 5, patients with congestive heart failure show a minimal predictability, while atrial fibrillation shows a higher variability, and hence complexity, which is actually reduced by the time coarse-graining procedure. Conclusions: The proposed multiscale partition-based K-S entropy is a viable tool to investigate complex cardiovascular dynamics in different physiopathological states.

Tangle: A metric for quantifying complexity and erratic behavior in short time series

Temporal complexity refers to qualities of a time series that are emergent, erratic, or not easily described by linear processes. Quantifying temporal complexity within a system is key to understanding the time based dynamics of said system. However, many current methods of complexity quantification are not widely used in psychological research because of their technical difficulty, computational intensity, or large number of required data samples. These requirements impede the study of complexity in many areas of psychological science. A method is presented, tangle, which overcomes these difficulties and allows for complexity quantification in relatively short time series, such as those typically obtained from psychological studies. Tangle is a measure of how dissimilar a given process is from simple periodic motion. Tangle relies on the use of a three-dimensional time delay embedding of a one-dimensional time series. This embedding is then iteratively scaled and premultiplied by a modified upshift matrix until a convergence criterion is reached. The efficacy of tangle is shown on five mathematical time series and using emotional stability, anxiety time series data obtained from 65 socially anxious participants over a 5-week period, and positive affect time series derived from a single participant who experienced a major depression episode during measurement. Simulation results show tangle is able to distinguish between different complex temporal systems in time series with as few as 50 samples. Tangle shows promise as a reliable quantification of irregular behavior of a time series. Unlike many other complexity quantification metrics, tangle is technically simple to implement and is able to uncover meaningful information about time series derived from psychological research studies. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

ECG and Heart Rate Variability in Sleep-Related Breathing Disorders

Here we discuss the current perspectives of comprehensive heart rate variability (HRV) analysis in electrocardiogram (ECG) signals as a non-invasive and reliable measure to assess autonomic function in sleep-related breathing disorders (SDB). It is a tool of increasing interest as different facets of HRV can be implemented to screen and diagnose SDB, monitor treatment efficacy, and prognose adverse cardiovascular outcomes in patients with sleep apnea. In this context, the technical aspects, pathophysiological features, and clinical applications of HRV are discussed to explore its usefulness in better understanding SDB.

Variational Embedding Multiscale Sample Entropy: A Tool for Complexity Analysis of Multichannel Systems

Entropy-based methods have received considerable attention in the quantification of structural complexity of real-world systems. Among numerous empirical entropy algorithms, conditional entropy-based methods such as sample entropy, which are associated with amplitude distance calculation, are quite intuitive to interpret but require excessive data lengths for meaningful evaluation at large scales. To address this issue, we propose the variational embedding multiscale sample entropy (veMSE) method and conclusively demonstrate its ability to operate robustly, even with several times shorter data than the existing conditional entropy-based methods. The analysis reveals that veMSE also exhibits other desirable properties, such as the robustness to the variation in embedding dimension and noise resilience. For rigor, unlike the existing multivariate methods, the proposed veMSE assigns a different embedding dimension to every data channel, which makes its operation independent of channel permutation. The veMSE is tested on both stimulated and real world signals, and its performance is evaluated against the existing multivariate multiscale sample entropy methods. The proposed veMSE is also shown to exhibit computational advantages over the existing amplitude distance-based entropy methods.

Similarity Changes Analysis for Heart Rate Fluctuation Regularity as a New Screening Method for Congestive Heart Failure

Congestive heart failure (CHF) is a chronic cardiovascular condition associated with dysfunction of the autonomic nervous system (ANS). Heart rate variability (HRV) has been widely used to assess ANS. This paper proposes a new HRV analysis method, which uses information-based similarity (IBS) transformation and fuzzy approximate entropy (fApEn) algorithm to obtain the fApEn_IBS index, which is used to observe the complexity of autonomic fluctuations in CHF within 24 h. We used 98 ECG records (54 health records and 44 CHF records) from the PhysioNet database. The fApEn_IBS index was statistically significant between the control and CHF groups (p < 0.001). Compared with the classical indices low-to-high frequency power ratio (LF/HF) and IBS, the fApEn_IBS index further utilizes the changes in the rhythm of heart rate (HR) fluctuations between RR intervals to fully extract relevant information between adjacent time intervals and significantly improves the performance of CHF screening. The CHF classification accuracy of fApEn_IBS was 84.69%, higher than LF/HF (77.55%) and IBS (83.67%). Moreover, the combination of IBS, fApEn_IBS, and LF/HF reached the highest CHF screening accuracy (98.98%) with the random forest (RF) classifier, indicating that the IBS and LF/HF had good complementarity. Therefore, fApEn_IBS effusively reflects the complexity of autonomic nerves in CHF and is a valuable CHF assessment tool.

Assessment of autonomic function by long-term heart rate variability: beyond the classical framework of LF and HF measurements

In the assessment of autonomic function by heart rate variability (HRV), the framework that the power of high-frequency component or its surrogate indices reflects parasympathetic activity, while the power of low-frequency component or LF/HF reflects sympathetic activity has been used as the theoretical basis for the interpretation of HRV. Although this classical framework has contributed greatly to the widespread use of HRV for the assessment of autonomic function, it was obtained from studies of short-term HRV (typically 5‑10 min) under tightly controlled conditions. If it is applied to long-term HRV (typically 24 h) under free-running conditions in daily life, erroneous conclusions could be drawn. Also, long-term HRV could contain untapped useful information that is not revealed in the classical framework. In this review, we discuss the limitations of the classical framework and present studies that extracted autonomic function indicators and other useful biomedical information from long-term HRV using novel approaches beyond the classical framework. Those methods include non-Gaussianity index, HRV sleep index, heart rate turbulence, and the frequency and amplitude of cyclic variation of heart rate.

Effects of different exercise interventions on heart rate variability and cardiovascular health factors in older adults: a systematic review

Background

Aging impairs physiological processes in the autonomic nervous, endocrine, and cardiovascular systems which are associated with increased risk of cardiovascular disease. Heart rate variability (HRV), the beat-to-beat variations of successive heartbeats, is an indicator of cardiac autonomic control and cardiovascular health. Physical activity has beneficial effects on cardiovascular health. However, no review has been conducted to summarize the effects of different exercise modalities on HRV in older adults. Therefore, the aim of this systematic review was to summarize the effects of endurance, resistance, coordinative, and multimodal exercise interventions on resting HRV and secondary health factors in healthy older adults aged 60 years in average and over.

Methods

Five databases (PubMed, Scopus, SPORTDiscus, Ovid, and Cochrane Library) were searched for eligible studies published between 2005 and September 8th, 2020. Two reviewers independently assessed the studies for potential inclusion. Outcome measures were changes in resting HRV indices, baroreflex sensitivity, blood pressure, body fat, body mass, body mass index, cardiac output, distance in the six-minute walking test, stroke volume, total peripheral resistance, and VO₂ max or VO₂ peak from pre to post intervention. The methodological quality of the final data set was assessed using two scales (TESTEX and STARD_HRV). This review was registered in PROSPERO: CRD42020206606.

Results

The literature search retrieved 3991 articles, of which 13 were included in the review. Five studies used multimodal, three studies endurance, two studies resistance, two studies coordinative, and one study used an endurance and a resistance training intervention. The majority of the studies revealed significant positive effects on cardiac autonomic control, except for the resistance training interventions. All exercise modalities improved secondary health factors. The methodological quality assessment revealed a few criteria to improve the quality of and comparability between studies.

Conclusion

This systematic review revealed beneficial effects on cardiac autonomic control in healthy older adults through endurance, coordinative, and multimodal training but not through resistance training. Secondary health factors improved after all types of physical interventions. Future investigations should more thoroughly adhere to methodological standards of exercise interventions and ECG recording for the assessment of autonomic regulation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s11556-021-00278-6.

A Delineator for Arterial Blood Pressure Waveform Analysis Based on a Deep Learning Technique

A deep learning technique based on semantic segmentation was implemented into the blood pressure detection points field. Two models were trained and evaluated in terms of a reference detector. The proposed methodology outperforms the reference detector in two of the three classic benchmarks and on signals from a public database that were modified with realistic test maneuvers and artifacts. Both models differentiate regions with valid information and artifacts. So far, no other delineator had shown this capacity.

Quantifying partition-based Kolmogorov-Sinai Entropy on Heart Rate Variability: a young vs. elderly study

In the last decades, a considerable effort has been devoted to quantify complexity in physiological time series, with a particular focus on heart rate variability (HRV). To this end, exemplary quantifiers including Approximate Entropy and Sample Entropy have successfully been applied by leveraging on statistical approximation and further parametrization through the definition of tolerance and embedding dimension, among others. In this study, we investigate the use of the Algorithmic Information Content, which is estimated through an effective compression algorithm, to quantify partition-based Kolmogorov-Sinai (K-S) entropy on HRV series. We test such a K-S estimate on real data gathered from the Fantasia database, aiming to discern young vs. elderly complex dynamics. Experimental results show that elderly people are associated with a lower HRV complexity and a more predictable behavior, with significantly lower partition-based K-S entropy than the young adults. We conclude that partition-based K-S entropy may effectively be used to investigate pathological conditions in the cardiovascular system, complementing state-of-the-art methods for complexity assessment.

Identifying Heart Failure in ECG Data With Artificial Intelligence-A Meta-Analysis

Introduction: Electrocardiography (ECG) is a quick and easily accessible method for diagnosis and screening of cardiovascular diseases including heart failure (HF). Artificial intelligence (AI) can be used for semi-automated ECG analysis. The aim of this evaluation was to provide an overview of AI use in HF detection from ECG signals and to perform a meta-analysis of available studies.

Methods and Results: An independent comprehensive search of the PubMed and Google Scholar database was conducted for articles dealing with the ability of AI to predict HF based on ECG signals. Only original articles published in peer-reviewed journals were considered. A total of five reports including 57,027 patients and 579,134 ECG datasets were identified including two sets of patient-level data and three with ECG-based datasets. The AI-processed ECG data yielded areas under the receiver operator characteristics curves between 0.92 and 0.99 to identify HF with higher values in ECG-based datasets. Applying a random-effects model, an sROC of 0.987 was calculated. Using the contingency tables led to diagnostic odds ratios ranging from 3.44 [95% confidence interval (CI) = 3.12–3.76] to 13.61 (95% CI = 13.14–14.08) also with lower values in patient-level datasets. The meta-analysis diagnostic odds ratio was 7.59 (95% CI = 5.85–9.34).

Conclusions: The present meta-analysis confirms the ability of AI to predict HF from standard 12-lead ECG signals underlining the potential of such an approach. The observed overestimation of the diagnostic ability in artificial ECG databases compared to patient-level data stipulate the need for robust prospective studies.

Improved ECG-Derived Respiration Using Empirical Wavelet Transform and Kernel Principal Component Analysis

Many methods have been developed to derive respiration signals from electrocardiograms (ECGs). However, traditional methods have two main issues: (1) focusing on certain specific morphological characteristics and (2) not considering the nonlinear relationship between ECGs and respiration. In this paper, an improved ECG-derived respiration (EDR) based on empirical wavelet transform (EWT) and kernel principal component analysis (KPCA) is proposed. To tackle the first problem, EWT is introduced to decompose the ECG signal to extract the low-frequency part. To tackle the second issue, KPCA and preimaging are introduced to capture the nonlinear relationship between ECGs and respiration. The parameter selection of the radial basis function kernel in KPCA is also improved, ensuring accuracy and a reduction in computational cost. The correlation coefficient and amplitude square coherence coefficient are used as metrics to carry out quantitative and qualitative comparisons with three traditional EDR algorithms. The results show that the proposed method performs better than the traditional EDR algorithms in obtaining single-lead-EDR signals.

Technical aspects of cardiorespiratory estimation using subspace projections and cross entropy

BACKGROUND

Respiratory sinus arrhythmia (RSA) is a form of cardiorespiratory coupling. Its quantification has been suggested as a biomarker to diagnose different diseases. Two state-of-the-art methods, based on subspace projections and entropy, are used to estimate the RSA strength and are evaluated in this paper. Their computation requires the selection of a model order, and their performance is strongly related to the temporal and spectral characteristics of the cardiorespiratory signals.

OBJECTIVE

To evaluate the robustness of the RSA estimates to the selection of model order, delays, changes of phase and irregular heartbeats as well as to give recommendations for their interpretation on each case.

APPROACH

Simulations were used to evaluate the model order selection when calculating the RSA estimates explained before, as well as 3 different scenarios that can occur in signals acquired in non-controlled environments and/or from patient populations: the presence of irregular heartbeats; the occurrence of delays between heart rate variability (HRV) and respiratory signals; and the changes over time of the phase between HRV and respiratory signals.

MAIN RESULTS

It was found that using a single model order for all the calculations suffices to characterize the RSA estimates correctly. In addition, the RSA estimation in signals containing more than 5 irregular heartbeats in a period of 5 minutes might be misleading. Regarding the delays between HRV and respiratory signals, both estimates are robust. For the last scenario, the two approaches tolerate phase changes up to 54°, as long as this lasts less than one fifth of the recording duration.

SIGNIFICANCE

Guidelines are given to compute the RSA estimates in non-controlled environments and patient populations.

Enhanced detection of abnormalities in heart rate variability and dynamics by 7-day continuous ECG monitoring

Background

The analysis of heart rate variability (HRV) and heart rate (HR) dynamics by Holter ECG has been standardized to 24 hs, but longer‐term continuous ECG monitoring has become available in clinical practice. We investigated the effects of long‐term ECG on the assessment of HRV and HR dynamics.

Methods

Intraweek variations in HRV and HR dynamics were analyzed in 107 outpatients with sinus rhythm. ECG was recorded continuously for 7 days with a flexible, codeless, waterproof sensor attached on the upper chest wall. Data were divided into seven 24‐h segments, and standard time‐ and frequency‐domain HRV and nonlinear HR dynamics indices were computed for each segment.

Results

The intraweek coefficients of variance of HRV and HR dynamics indices ranged from 2.9% to 26.0% and were smaller for frequency‐domain than for time‐domain indices, and for indices reflecting slower HR fluctuations than faster fluctuations. The indices with large variance often showed transient abnormalities from day to day over 7 days, reducing the positive predictive accuracy of the 24‐h ECG for detecting persistent abnormalities over 7 days. Conversely, 7‐day ECG provided 2.3‐ to 6.5‐fold increase in sensitivity to detect persistent plus transient abnormalities compared with 24‐h ECG. It detected an average of 1.74 to 2.91 times as many abnormal indices as 24‐h ECG.

Conclusions

Long‐term ECG monitoring increases the accuracy and sensitivity of detecting persistent and transient abnormalities in HRV and HR dynamics and allows discrimination between the two types of abnormalities. Whether this discrimination improves risk stratification deserves further studies.

Copula-Based Data Augmentation on a Deep Learning Architecture for Cardiac Sensor Fusion

In the wake of Big Data, traditional Machine Learning techniques are now often integrated in the clinical workflow. Despite more capable, Deep Learning methods are not equally accepted given their unsatiated need for great amounts of training data and transversal use of the same architectures in fundamentally different areas with weakly-substantiated adaptations. To address the former, a cardiorespiratory signal synthesizer was designed by conditional sampling from a multimodally trained stochastic system of Gaussian copulas integrated in a Markov chain. With respect to the latter, a multi-branch convolutional neural network architecture was conceived to learn the best cardiac sensor-fusion strategy at every abstraction layer. The network was tailored to the tasks of cycle detection and classification for different cardiac modality combinations by a synthesizer-based data augmentation training framework and Bayesian hyperparameter optimization. The synthesizer yielded highly realistic signals in the time, frequency and phase domains for both healthy and pathological heart cycles as well as artifacts of different modalities. Benchmarking suggested that the network is able to surpass previous architectures and data augmentation provided a performance boost in realistic data availability scenarios. These included insufficient training data volume, as low as 150 cycles long, artifact contamination and absence of a classification data type in training.

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Background

Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity.

Result

Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity.

Conclusion

These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment

An integrated framework for evaluation on typical ECG-derived respiration waveform extraction and respiration

OBJECTIVE

ECG-derived respiration (EDR) methods have been developed during the past decades to obtain respiration-relevant information. However, it is still necessary to compare the performance of these methods under uniform conditions for reasonable application.

APPROACH

In this paper, the performance of 10 feature-based EDR methods was evaluated comprehensively on three aspects: sampling rate, noise, and window length. The Fantasia database was used in this study, as it contained ECG signals and simultaneously measured respiration signals. The performance was quantified by two parameters: waveform correlation and breathing rate (BR) errors.

MAIN RESULTS

The BR errors of AM_area, AM_QR, AM_R were all below 2 beats per minute (bpm) when the sampling rate was above 150 Hz, while they decreased sharply by about 60% when the sampling rate was below 150 Hz. FM_RR presented stable performance with an error below 2 bpm at different sampling rates. The effect of noise was obviously found in amplitude-based EDR methods, with the maximum decreased by about 40% in waveform correlation. For all EDR methods, significant increase of BR errors occurred with the window shorting from 32 s to 16 s in the frequency-based technique. In addition, about 30%-40% of the window cannot obtain the BR error, calculated based on the time-based technique, within an 8 s window.

SIGNIFICANCE

We proposed a comprehensive and integrated evaluation on typical ECG-derived respiration waveform extraction and respiration rate calculation, providing references for algorithm selection based on different requirements.

Validation of the Withings Sleep Analyzer, an under-the-mattress device for the detection of moderate-severe sleep apnea syndrome

STUDY OBJECTIVES

To assess the diagnostic performance of a nonintrusive device placed under the mattress to detect sleep apnea syndrome.

METHODS

One hundred eighteen patients suspected to have obstructive sleep apnea syndrome completed a night at a sleep clinic with a simultaneous polysomnography (PSG) and recording with the Withings Sleep Analyzers. PSG nights were scored twice: first as simple polygraphy, then as PSG.

RESULTS

Average (standard deviation) apnea-hypopnea index from PSG was 31.2 events/h (25.0) and 32.8 events/h (29.9) according to the Withings Sleep Analyzers. The mean absolute error was 9.5 events/h. The sensitivity, specificity, and area under the receiver operating characteristic curve at thresholds of apnea-hypopnea index ≥ 15 events/h were, respectively, sensitivity (Se)₁₅ = 88.0%, specificity (Sp)₁₅ = 88.6%, and area under the receiver operating characteristic curve (AUROC) ₁₅ = 0.926. At the threshold of apnea-hypopnea index ≥ 30 events/h, results included Se₃₀ = 86.0%, Sp₃₀ = 91.2%, AUROC₃₀ = 0.954. The average total sleep time from PSG and the Withings Sleep Analyzers was 366.6 (61.2) and 392.4 (67.2) minutes, sleep efficiency was 82.5% (11.6) and 82.6% (11.6), and wake after sleep onset was 62.7 (48.0) and 45.2 (37.3) minutes, respectively.

CONCLUSIONS

Withings Sleep Analyzers accurately detect moderate-severe sleep apnea syndrome in patients suspected of sleep apnea syndrome. This simple and automated approach could be of great clinical value given the high prevalence of sleep apnea syndrome in the general population.

CLINICAL TRIAL REGISTRATION

Registry: ClinicalTrials.gov; Name: Validation of Withings Sleep for the Detection of Sleep Apnea Syndrome; URL: https://clinicaltrials.gov/ct2/show/NCT04234828; Identifier: NCT04234828.

Model-Based Evaluation of Methods for Respiratory Sinus Arrhythmia Estimation

OBJECTIVE

Respiratory sinus arrhythmia (RSA) refers to heart rate oscillations synchronous with respiration, and it is one of the major representations of cardiorespiratory coupling. Its strength has been suggested as a biomarker to monitor different conditions, and diseases. Some approaches have been proposed to quantify the RSA, but it is unclear which one performs best in specific scenarios. The main objective of this study is to compare seven state-of-the-art methods for RSA quantification using data generated with a model proposed to simulate, and control the RSA. These methods are also compared, and evaluated on a real-life application, for their ability to capture changes in cardiorespiratory coupling during sleep.

METHODS

A simulation model is used to create a dataset of heart rate variability, and respiratory signals with controlled RSA, which is used to compare the RSA estimation approaches. To compare the methods objectively in real-life applications, regression models trained on the simulated data are used to map the estimates to the same measurement scale. Results, and conclusion: RSA estimates based on cross entropy, time-frequency coherence, and subspace projections showed the best performance on simulated data. In addition, these estimates captured the expected trends in the changes in cardiorespiratory coupling during sleep similarly.

SIGNIFICANCE

An objective comparison of methods for RSA quantification is presented to guide future analyses. Also, the proposed simulation model can be used to compare existing, and newly proposed RSA estimates. It is freely accessible online.

Sex Differences in the Physiological Network of Healthy Young Subjects

Within human physiology, systemic interactions couple physiological variables to maintain homeostasis. These interactions change according to health status and are modified by factors such as age and sex. For several physiological processes, sex-based distinctions in normal physiology are present and defined in isolation. However, new methodologies are indispensable to analyze system-wide properties and interactions with the objective of exploring differences between sexes. Here we propose a new method to construct complex inferential networks from a normalization using the clinical criteria for health of physiological variables, and the correlations between anthropometric and blood tests biomarkers of 198 healthy young participants (117 women, 81 men, from 18 to 27 years old). Physiological networks of men have less correlations, displayed higher modularity, higher small-world index, but were more vulnerable to directed attacks, whereas networks of women were more resilient. The networks of both men and women displayed sex-specific connections that are consistent with the literature. Additionally, we carried out a time-series study on heart rate variability (HRV) using Physionet's Fantasia database. Autocorrelation of HRV, variance, and Poincare's plots, as a measure of variability, are statistically significant higher in young men and statistically significant different from young women. These differences are attenuated in older men and women, that have similar HRV distributions. The network approach revealed differences in the association of variables related to glucose homeostasis, nitrogen balance, kidney function, and fat depots. The clusters of physiological variables and their roles within the network remained similar regardless of sex. Both methodologies show a higher number of associations between variables in the physiological system of women, implying redundant mechanisms of control and simultaneously showing that these systems display less variability in time than those of men, constituting a more resilient system.