Heart rate variability for medical decision support systems: A review

An effective cross-scenario remote heart rate estimation network based on global-local information and video transformer

Remote photoplethysmography (rPPG) technology is a non-contact physiological signal measurement method, characterized by non-invasiveness and ease of use. It has broad application potential in medical health, human factors engineering, and other fields. However, current rPPG technology is highly susceptible to variations in lighting conditions, head pose changes, and partial occlusions, posing significant challenges for its widespread application. In order to improve the accuracy of remote heart rate estimation and enhance model generalization, we propose PulseFormer, a dual-path network based on transformer. By integrating local and global information and utilizing fast and slow paths, PulseFormer effectively captures the temporal variations of key regions and spatial variations of the global area, facilitating the extraction of rPPG feature information while mitigating the impact of background noise variations. Heart rate estimation results on the popular rPPG dataset show that PulseFormer achieves state-of-the-art performance on public datasets. Additionally, we establish a dataset containing facial expressions and synchronized physiological signals in driving scenarios and test the pre-trained model from the public dataset on this collected dataset. The results indicate that PulseFormer exhibits strong generalization capabilities across different data distributions in cross-scenario settings. Therefore, this model is applicable for heart rate estimation of individuals in various scenarios.

Long-COVID-19 autonomic dysfunction: An integrated view in the framework of inflammaging

The recently identified syndrome known as Long COVID (LC) is characterized by a constellation of debilitating conditions that impair both physical and cognitive functions, thus reducing the quality of life and increasing the risk of developing the most common age-related diseases. These conditions are linked to the presence of symptoms of autonomic dysfunction, in association with low cortisol levels, suggestive of reduced hypothalamic-pituitary-adrenal (HPA) axis activity, and with increased pro-inflammatory condition. Alterations of dopamine and serotonin neurotransmitter levels were also recently observed in LC. Interestingly, at least some of the proposed mechanisms of LC development overlap with mechanisms of Autonomic Nervous System (ANS) imbalance, previously detailed in the framework of the aging process. ANS imbalance is characterized by a proinflammatory sympathetic overdrive, and a concomitant decreased anti-inflammatory vagal parasympathetic activity, associated with reduced anti-inflammatory effects of the HPA axis and cholinergic anti-inflammatory pathway (CAP). These neuro-immune-endocrine system imbalanced activities fuel the vicious circle of chronic inflammation, i.e. inflammaging. Here, we refine our original hypothesis that ANS dysfunction fuels inflammaging and propose that biomarkers of ANS imbalance could also be considered biomarkers of inflammaging, recognized as the main risk factor for developing age-related diseases and the sequelae of viral infections, i.e. LC.

Automatic identification of hypertension and assessment of its secondary effects using artificial intelligence: A systematic review (2013-2023)

Artificial Intelligence (AI) techniques are increasingly used in computer-aided diagnostic tools in medicine. These techniques can also help to identify Hypertension (HTN) in its early stage, as it is a global health issue. Automated HTN detection uses socio-demographic, clinical data, and physiological signals. Additionally, signs of secondary HTN can also be identified using various imaging modalities. This systematic review examines related work on automated HTN detection. We identify datasets, techniques, and classifiers used to develop AI models from clinical data, physiological signals, and fused data (a combination of both). Image-based models for assessing secondary HTN are also reviewed. The majority of the studies have primarily utilized single-modality approaches, such as biological signals (e.g., electrocardiography, photoplethysmography), and medical imaging (e.g., magnetic resonance angiography, ultrasound). Surprisingly, only a small portion of the studies (22 out of 122) utilized a multi-modal fusion approach combining data from different sources. Even fewer investigated integrating clinical data, physiological signals, and medical imaging to understand the intricate relationships between these factors. Future research directions are discussed that could build better healthcare systems for early HTN detection through more integrated modeling of multi-modal data sources.

Heart rate variability in school-age children born moderate-to-late preterm

BACKGROUND

Prematurity is associated with reduced cardiac autonomic function. This study aimed to investigate the heart rate variability (HRV) in school-age children born moderately to late preterm (MLPT).

METHODS

This cross-sectional study investigated school-age children, aged 5 to 10 years, born moderate-to-late preterm. Electrocardiograms recordings were performed during fifteen-minutes. Time and frequency domain parameters were calculated, corrected for heart rate and compared between the groups.

RESULTS

A total of 123 children were evaluated and 119 were included in this study. HRV measures, studied in the time and frequency domains, were similar in both groups. Corrected values of root mean square of successive differences between normal cycles (RMSSD), percentage of successive cycles with a duration difference >50 ms (pNN50%), and high frequency (HF), indices that predominantly represent the parasympathetic activity of the autonomic nervous system, were 1.6E-7 and 1.8E-7 (p=0.226); 1.6E-13 and 1.6E-13 (p=0.506); 6.9E-12 and 7.4E-12 (p=0.968) in the preterm and control groups, respectively.

CONCLUSION

This study did not find differences in heart rate variability between school-age children born MLPT and those born at term, suggesting that plasticity of cardiac autonomic modulation continues to occur in children up to school age or there is less impairment of the autonomic system in MLPT.

An extensive quantitative analysis of the effects of errors in beat-to-beat intervals on all commonly used HRV parameters

Heart rate variability (HRV) analysis is often used to estimate human health and fitness status. More specifically, a range of parameters that express the variability in beat-to-beat intervals are calculated from electrocardiogram beat detections. Since beat detection may yield erroneous interval data, these errors travel through the processing chain and may result in misleading parameter values that can lead to incorrect conclusions. In this study, we utilized Monte Carlo simulation on real data, Kolmogorov-Smirnov tests and Bland-Altman analysis to carry out extensive analysis of the noise sensitivity of different HRV parameters. The used noise models consider Gaussian and student-t distributed noise. As a result we observed that commonly used HRV parameters (e.g. pNN50 and LF/HF ratio) are especially sensitive to noise and that all parameters show biases to some extent. We conclude that researchers should be careful when reporting different HRV parameters, consider the distributions in addition to mean values, and consider reference data if applicable. The analysis of HRV parameter sensitivity to noise and resulting biases presented in this work generalizes over a wide population and can serve as a reference and thus provide a basis for the decision about which HRV parameters to choose under similar conditions.

ECG-Free Heartbeat Detection in Seismocardiography and Gyrocardiography Signals Provides Acceptable Heart Rate Variability Indices in Healthy and Pathological Subjects

Cardio-mechanical monitoring techniques, such as Seismocardiography (SCG) and Gyrocardiography (GCG), have received an ever-growing interest in recent years as potential alternatives to Electrocardiography (ECG) for heart rate monitoring. Wearable SCG and GCG devices based on lightweight accelerometers and gyroscopes are particularly appealing for continuous, long-term monitoring of heart rate and its variability (HRV). Heartbeat detection in cardio-mechanical signals is usually performed with the support of a concurrent ECG lead, which, however, limits their applicability in standalone cardio-mechanical monitoring applications. The complex and variable morphology of SCG and GCG signals makes the ECG-free heartbeat detection task quite challenging; therefore, only a few methods have been proposed. Very recently, a template matching method based on normalized cross-correlation (NCC) has been demonstrated to provide very accurate detection of heartbeats and estimation of inter-beat intervals in SCG and GCG signals of pathological subjects. In this study, the accuracy of HRV indices obtained with this template matching method is evaluated by comparison with ECG. Tests were performed on two public datasets of SCG and GCG signals from healthy and pathological subjects. Linear regression, correlation, and Bland-Altman analyses were carried out to evaluate the agreement of 24 HRV indices obtained from SCG and GCG signals with those obtained from ECG signals, simultaneously acquired from the same subjects. The results of this study show that the NCC-based template matching method allowed estimating HRV indices from SCG and GCG signals of healthy subjects with acceptable accuracy. On healthy subjects, the relative errors on time-domain indices ranged from 0.25% to 15%, on frequency-domain indices ranged from 10% to 20%, and on non-linear indices were within 8%. The estimates obtained on signals from pathological subjects were affected by larger errors. Overall, GCG provided slightly better performances as compared to SCG, both on healthy and pathological subjects. These findings provide, for the first time, clear evidence that monitoring HRV via SCG and GCG sensors without concurrent ECG is feasible with the NCC-based template matching method for heartbeat detection.

Cardiovascular autonomic dysfunction in "Long COVID": pathophysiology, heart rate variability, and inflammatory markers

Long COVID is characterized by persistent signs and symptoms that continue or develop for more than 4 weeks after acute COVID-19 infection. Patients with Long COVID experience a cardiovascular autonomic imbalance known as dysautonomia. However, the underlying autonomic pathophysiological mechanisms behind this remain unclear. Current hypotheses include neurotropism, cytokine storms, and inflammatory persistence. Certain immunological factors indicate autoimmune dysfunction, which can be used to identify patients at a higher risk of Long COVID. Heart rate variability can indicate autonomic imbalances in individuals suffering from Long COVID, and measurement is a non-invasive and low-cost method for assessing cardiovascular autonomic modulation. Additionally, biochemical inflammatory markers are used for diagnosing and monitoring Long COVID. These inflammatory markers can be used to improve the understanding of the mechanisms driving the inflammatory response and its effects on the sympathetic and parasympathetic pathways of the autonomic nervous system. Autonomic imbalances in patients with Long COVID may result in lower heart rate variability, impaired vagal activity, and substantial sympathovagal imbalance. New research on this subject must be encouraged to enhance the understanding of the long-term risks that cardiovascular autonomic imbalances can cause in individuals with Long COVID.

A Real-Time Evaluation Algorithm for Noncontact Heart Rate Variability Monitoring

Noncontact vital sign monitoring based on radar has attracted great interest in many fields. Heart Rate Variability (HRV), which measures the fluctuation of heartbeat intervals, has been considered as an important indicator for general health evaluation. This paper proposes a new algorithm for HRV monitoring in which frequency-modulated continuous-wave (FMCW) radar is used to separate echo signals from different distances, and the beamforming technique is adopted to improve signal quality. After the phase reflecting the chest wall motion is demodulated, the acceleration is calculated to enhance the heartbeat and suppress the impact of respiration. The time interval of each heartbeat is estimated based on the smoothed acceleration waveform. Finally, a joint optimization algorithm was developed and is used to precisely segment the acceleration signal for analyzing HRV. Experimental results from 10 participants show the potential of the proposed algorithm for obtaining a noncontact HRV estimation with high accuracy. The proposed algorithm can measure the interbeat interval (IBI) with a root mean square error (RMSE) of 14.9 ms and accurately estimate HRV parameters with an RMSE of 3.24 ms for MEAN (the average value of the IBI), 4.91 ms for the standard deviation of normal to normal (SDNN), and 9.10 ms for the root mean square of successive differences (RMSSD). These results demonstrate the effectiveness and feasibility of the proposed method in emotion recognition, sleep monitoring, and heart disease diagnosis.

The Impact of Heart Rate Variability Monitoring on Preventing Severe Cardiovascular Events

The increase in the incidence of cardiovascular diseases worldwide raises concerns about the urgent need to increase definite measures for the self-determination of different parameters, especially those defining cardiac function. Heart rate variability (HRV) is a non-invasive method used to evaluate autonomic nervous system modulation on the cardiac sinus node, thus describing the oscillations between consecutive electrocardiogram R-R intervals. These fluctuations are undetectable except when using specialized devices, with ECG Holter monitoring considered the gold standard. HRV is considered an independent biomarker for measuring cardiovascular risk and for screening the occurrence of both acute and chronic heart diseases. Also, it can be an important predictive factor of frailty or neurocognitive disorders, like anxiety and depression. An increased HRV is correlated with rest, exercise, and good recovery, while a decreased HRV is an effect of stress or illness. Until now, ECG Holter monitoring has been considered the gold standard for determining HRV, but the recent decade has led to an accelerated development of technology using numerous devices that were created specifically for the pre-hospital self-monitoring of health statuses. The new generation of devices is based on the use of photoplethysmography, which involves the determination of blood changes at the level of blood vessels. These devices provide additional information about heart rate (HR), blood pressure (BP), peripheral oxygen saturation (SpO²), step counting, physical activity, and sleep monitoring. The most common devices that have this technique are smartwatches (used on a large scale) and chest strap monitors. Therefore, the use of technology and the self-monitoring of heart rate and heart rate variability can be an important first step in screening cardiovascular pathology and reducing the pressure on medical services in a hospital. The use of telemedicine can be an alternative, especially among elderly patients who are associated with walking disorders, frailty, or neurocognitive disorders.

Heart rate variability changes with respect to time and exercise intensity during heart-rate-controlled steady-state treadmill running

The aim of this work was to investigate the time and exercise intensity dependence of heart rate variability (HRV). Time-dependent, cardiovascular-drift-related increases in heart rate (HR) were inhibited by enforcing a constant heart rate throughout the exercise with a feedback control system. Thirty-two healthy adults performed HR-stabilised treadmill running exercise at two distinct exercise intensity levels. Standard time and frequency domain HRV metrics were computed and served as outcomes. Significant decreases were detected in 8 of the 14 outcomes for the time dependence analysis and in 6 of the 7 outcomes for the exercise intensity dependence analysis (excluding the experimental speed-signal frequency analysis). Furthermore, metrics that have been reported to reach an intensity-dependent near-zero minimum rapidly (usually at moderate intensity) were found to be near constant over time and only barely decreased with intensity. Taken together, these results highlight that HRV generally decreases with time and with exercise intensity. The intensity-related reductions were found to be greater in value and significance compared to the time-related reductions. Additionally, the results indicate that decreases in HRV metrics with time or exercise intensity are only detectable as long as their metric-specific near-zero minimum has not yet been reached.

ECG-Free Heartbeat Detection in Seismocardiography Signals via Template Matching

Cardiac monitoring can be performed by means of an accelerometer attached to a subject's chest, which produces the Seismocardiography (SCG) signal. Detection of SCG heartbeats is commonly carried out by taking advantage of a simultaneous electrocardiogram (ECG). SCG-based long-term monitoring would certainly be less obtrusive and easier to implement without an ECG. Few studies have addressed this issue using a variety of complex approaches. This study proposes a novel approach to ECG-free heartbeat detection in SCG signals via template matching, based on normalized cross-correlation as heartbeats similarity measure. The algorithm was tested on the SCG signals acquired from 77 patients with valvular heart diseases, available from a public database. The performance of the proposed approach was assessed in terms of sensitivity and positive predictive value (PPV) of the heartbeat detection and accuracy of inter-beat intervals measurement. Sensitivity and PPV of 96% and 97%, respectively, were obtained by considering templates that included both systolic and diastolic complexes. Regression, correlation, and Bland-Altman analyses carried out on inter-beat intervals reported slope and intercept of 0.997 and 2.8 ms (R² > 0.999), as well as non-significant bias and limits of agreement of ±7.8 ms. The results are comparable or superior to those achieved by far more complex algorithms, also based on artificial intelligence. The low computational burden of the proposed approach makes it suitable for direct implementation in wearable devices.

Cardiovascular and autonomic dysfunction in long-COVID syndrome and the potential role of non-invasive therapeutic strategies on cardiovascular outcomes

A significant percentage of COVID-19 survivors develop long-lasting cardiovascular sequelae linked to autonomic nervous system dysfunction, including fatigue, arrhythmias, and hypertension. This post-COVID-19 cardiovascular syndrome is one facet of "long-COVID," generally defined as long-term health problems persisting/appearing after the typical recovery period of COVID-19. Despite the fact that this syndrome is not fully understood, it is urgent to develop strategies for diagnosing/managing long-COVID due to the immense potential for future disease burden. New diagnostic/therapeutic tools should provide health personnel with the ability to manage the consequences of long-COVID and preserve/improve patient quality of life. It has been shown that cardiovascular rehabilitation programs (CRPs) stimulate the parasympathetic nervous system, improve cardiorespiratory fitness (CRF), and reduce cardiovascular risk factors, hospitalization rates, and cognitive impairment in patients suffering from cardiovascular diseases. Given their efficacy in improving patient outcomes, CRPs may have salutary potential for the treatment of cardiovascular sequelae of long-COVID. Indeed, there are several public and private initiatives testing the potential of CRPs in treating fatigue and dysautonomia in long-COVID subjects. The application of these established rehabilitation techniques to COVID-19 cardiovascular syndrome represents a promising approach to improving functional capacity and quality of life. In this brief review, we will focus on the long-lasting cardiovascular and autonomic sequelae occurring after COVID-19 infection, as well as exploring the potential of classic and novel CRPs for managing COVID-19 cardiovascular syndrome. Finally, we expect this review will encourage health care professionals and private/public health organizations to evaluate/implement non-invasive techniques for the management of COVID-19 cardiovascular sequalae.

Wearable Devices for Remote Monitoring of Heart Rate and Heart Rate Variability-What We Know and What Is Coming

Heart rate at rest and exercise may predict cardiovascular risk. Heart rate variability is a measure of variation in time between each heartbeat, representing the balance between the parasympathetic and sympathetic nervous system and may predict adverse cardiovascular events. With advances in technology and increasing commercial interest, the scope of remote monitoring health systems has expanded. In this review, we discuss the concepts behind cardiac signal generation and recording, wearable devices, pros and cons focusing on accuracy, ease of application of commercial and medical grade diagnostic devices, which showed promising results in terms of reliability and value. Incorporation of artificial intelligence and cloud based remote monitoring have been evolving to facilitate timely data processing, improve patient convenience and ensure data security.

A review of automated sleep disorder detection

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.

Environmental Benefits of Sleep Apnoea Detection in the Home Environment

Sleep Apnoea (SA) is a common chronic illness that affects nearly 1 billion people around the world, and the number of patients is rising. SA causes a wide range of psychological and physiological ailments that have detrimental effects on a patient’s wellbeing. The high prevalence and negative health effects make SA a public health problem. Whilst the current gold standard diagnostic procedure, polysomnography (PSG), is reliable, it is resource-expensive and can have a negative impact on sleep quality, as well as the environment. With this study, we focus on the environmental impact that arises from resource utilisation during SA detection, and we propose remote monitoring (RM) as a potential solution that can improve the resource efficiency and reduce travel. By reusing infrastructure technology, such as mobile communication, cloud computing, and artificial intelligence (AI), RM establishes SA detection and diagnosis support services in the home environment. However, there are considerable barriers to a widespread adoption of this technology. To gain a better understanding of the available technology and its associated strength, as well as weaknesses, we reviewed scientific papers that used various strategies for RM-based SA detection. Our review focused on 113 studies that were conducted between 2018 and 2022 and that were listed in Google Scholar. We found that just over 50% of the proposed RM systems incorporated real time signal processing and around 20% of the studies did not report on this important aspect. From an environmental perspective, this is a significant shortcoming, because 30% of the studies were based on measurement devices that must travel whenever the internal buffer is full. The environmental impact of that travel might constitute an additional need for changing from offline to online SA detection in the home environment.