Derivative Method to Detect Sleep and Awake States through Heart Rate Variability Analysis Using Machine Learning Algorithms.

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

Heart Rate Variability for Evaluating Psychological Stress Changes in Healthy Adults: A Scoping Review.

The utility of heart rate variability (HRV) for characterizing psychological stress is primarily impacted by methodological considerations such as study populations, experienced versus induced stress, and method of stress assessment. Here, we review studies on the associations between HRV and psychological stress, examining the nature of stress, ways stress was assessed, and HRV metrics used. The review was performed according to the PRISMA guidelines on select databases. Studies that examined the HRV-stress relationship via repeated measurements and validated psychometric instruments were included (n = 15). Participant numbers and ages ranged between 10 and 403 subjects and 18 and 60 years, respectively. Both experimental (n = 9) and real-life stress (n = 6) have been explored. While RMSSD was the most reported HRV metric (n = 10) significantly associated with stress, other metrics, including LF/HF (n = 7) and HF power (n = 6) were also reported. Various linear and nonlinear HRV metrics have been utilized, with nonlinear metrics used less often. The most frequently used psychometric instrument was the State-Trait Anxiety Inventory (n = 10), though various other instruments have been reported. In conclusion, HRV is a valid measure of the psychological stress response. Standard stress induction and assessment protocols combined with validated HRV measures in different domains will improve the validity of findings.

Assessing the utility of atrial fibrillation induction to risk stratify children with Wolff-Parkinson-White syndrome.

BACKGROUND: Wolff-Parkinson-White syndrome is associated with sudden cardiac death from rapid conduction through the accessory pathway in atrial fibrillation. Adult patients are at higher risk for sudden cardiac death if the shortest-pre-excited-RR-interval in atrial fibrillation (SPERRI) is ≤250 milliseconds (msec) during electrophysiologic study. Exclusive conduction through the atrioventricular node in atrial fibrillation is presumed to convey lower risk. The shortest-pre-excited-paced-cycle-length with atrial pacing has also served as a marker for risk stratification. OBJECTIVE: To determine accessory pathway characteristic of patients undergoing induction of atrial fibrillation during electrophysiologic study. METHODS: We reviewed 321 pediatric patients that underwent electrophysiologic study between 2010 and 2019. Induction of atrial fibrillation was attempted on patients while on isoproterenol and SPERRI was measured if atrial fibrillation was induced. Shortest-pre-excited-paced-cycle-length (SPPCL) was determined while on isoproterenol. RESULTS: Atrial fibrillation was induced in 233 (73%) patients. Of those, 104 (45%) patients conducted exclusively through the atrioventricular node during atrial fibrillation (Group A). The remaining 129 (55%) patients had some conduction through the accessory pathway (Group B). In Group A, SPPCL was 260 msec with 48 (46%) conducting through the accessory pathway at ≤250 msec. In Group B, SPPCL was 240 msec with 92 patients (71%) conducting at ≤250 msec (p < 0.05). In Group B, SPERRI was 250 msec and had a positive correlation with SPPCL (p < 0.001, R2 = 0.28). Almost half (46%) of those with exclusive conduction through the atrioventricular node in atrial fibrillation had rapid accessory pathway conduction with atrial pacing. CONCLUSION: Conduction in atrial fibrillation during electrophysiologic study on isoproterenol via the atrioventricular node may not exclude high-risk accessory pathways in pediatric patients.

Non-Standard Electrode Placement Strategies for ECG Signal Acquisition.

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

Atrioventricular Synchronization for Detection of Atrial Fibrillation and Flutter in One to Twelve ECG Leads Using a Dense Neural Network Classifier.

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

Effects of capacitive and resistive electric transfer and hot pack interventions on the autonomic nervous system in young women.

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

[Sleep apnea automatic detection method based on convolutional neural network].

Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.

Autonomic dysfunction in restless legs syndrome.

OBJECTIVE: Autonomic dysfunction in patients with RLS has been described in some domains; however, detailed studies on this subject are limited and report conflicting results. In this study, we aimed to evaluate autonomic functions electrophysiologically and clinically in patients with restless legs syndrome (RLS). METHODS: Fifty-two adult patients with RLS and 40 healthy controls were enrolled in this prospective study. Electrophysiological tests of sympathetic skin response (SSR) and RR interval variability (RRIV) analysis were performed, and the SCOPA-AUT questionnaire was applied to evaluate autonomic functions. RESULTS: There was no significant difference in terms of SSR results between patients and controls (p > 0.05). However, there were significant differences between the patient and control groups in terms of RRIV analyses at rest, deep breathing, and valsalva, and also valsalva ratio (p = 0.037, p = 0.049, p = 0.017, p = 0.020). The mean SCOPA-AUT total score was higher in the RLS group compared with the control group (20.7 ± 10 vs 14.2 ± 8; p = 0.003). Significant differences were found regarding gastrointestinal, urinary, and cardiovascular domains (p = 0.01, p = 0.007, p = 0.049); on the other hand, pupillomotor, thermoregulatory, and sexual function did not significantly differ (p > 0.05). CONCLUSION: Autonomic functions should be questioned in detail as well as motor and sensory symptoms of RLS, and care should be taken especially on cardiac dysfunction.

A Prototype Framework Design for Assisting the Detection of Atrial Fibrillation Using a Generic Low-Cost Biomedical Sensor.

Cardiovascular diseases are the leading cause of death around the world. As a result, low-cost biomedical sensors have been gaining importance in business and research over the last few decades. Their main benefits include their small size, light weight, portability and low power consumption. Despite these advantages, they are not generally used for clinical monitoring mainly because of their low accuracy in data acquisition. In this emerging technological context, this paper contributes by discussing a methodology to help practitioners build a prototype framework based on a low-cost commercial sensor. The resulting application consists of four modules; namely, a digitalization module whose input is an electrocardiograph signal in portable document format (PDF) or joint photographic expert group format (JPEG), a module to further process and filter the digitalized signal, a selectable data calibration module and, finally, a module implementing a classification algorithm to distinguish between individuals with normal sinus rhythms and those with atrial fibrillation. This last module employs our recently published symbolic recurrence quantification analysis (SRQA) algorithm on a time series of RR intervals. Moreover, we show that the algorithm applies to any biomedical low-cost sensor, achieving good results without requiring.

Complexity and Disorder of 1/fα Noises.

The complexity and the disorder of a 1/fα noise time series are quantified by entropy of entropy (EoE) and average entropy (AE), respectively. The resulting EoE vs. AE plot of a series of 1/fα noises of various values of α exhibits a distinct inverted U curve. For the 1/fα noises, we have shown that α decreases monotonically as AE increases, which indicates that α is also a measure of disorder. Furthermore, a 1/fα noise and a cardiac interbeat (RR) interval series are considered equivalent as they have the same AE. Accordingly, we have found that the 1/fα noises for α around 1.5 are equivalent to the RR interval series of healthy subjects. The pink noise at α = 1 is equivalent to atrial fibrillation (AF) RR interval series while the white noise at α = 0 is more disordered than AF RR interval series. These results, based on AE, are different from the previous ones based on spectral analysis. The testing macro-average F-score is 0.93 when classifying the RR interval series of three groups using AE-based α, while it is 0.73 when using spectral-analysis-based α.