An Efficient R-peak Detection Based on New Nonlinear Transformation and First-Order Gaussian Differentiator

A multi-task learning model using RR intervals and respiratory effort to assess sleep disordered breathing

BACKGROUND

Sleep-disordered breathing (SDB) affects a significant portion of the population. As such, there is a need for accessible and affordable assessment methods for diagnosis but also case-finding and long-term follow-up. Research has focused on exploiting cardiac and respiratory signals to extract proxy measures for sleep combined with SDB event detection. We introduce a novel multi-task model combining cardiac activity and respiratory effort to perform sleep-wake classification and SDB event detection in order to automatically estimate the apnea-hypopnea index (AHI) as severity indicator.

METHODS

The proposed multi-task model utilized both convolutional and recurrent neural networks and was formed by a shared part for common feature extraction, a task-specific part for sleep-wake classification, and a task-specific part for SDB event detection. The model was trained with RR intervals derived from electrocardiogram and respiratory effort signals. To assess performance, overnight polysomnography (PSG) recordings from 198 patients with varying degree of SDB were included, with manually annotated sleep stages and SDB events.

RESULTS

We achieved a Cohen's kappa of 0.70 in the sleep-wake classification task, corresponding to a Spearman's correlation coefficient (R) of 0.830 between the estimated total sleep time (TST) and the TST obtained from PSG-based sleep scoring. Combining the sleep-wake classification and SDB detection results of the multi-task model, we obtained an R of 0.891 between the estimated and the reference AHI. For severity classification of SBD groups based on AHI, a Cohen's kappa of 0.58 was achieved. The multi-task model performed better than a single-task model proposed in a previous study for AHI estimation, in particular for patients with a lower sleep efficiency (R of 0.861 with the multi-task model and R of 0.746 with single-task model with subjects having sleep efficiency < 60%).

CONCLUSION

Assisted with automatic sleep-wake classification, our multi-task model demonstrated proficiency in estimating AHI and assessing SDB severity based on AHI in a fully automatic manner using RR intervals and respiratory effort. This shows the potential for improving SDB screening with unobtrusive sensors also for subjects with low sleep efficiency without adding additional sensors for sleep-wake detection.

Multi-night home assessment of sleep structure in OSA with and without insomnia

OBJECTIVE

To explore sleep structure in participants with obstructive sleep apnea (OSA) and comorbid insomnia (COMISA) and participants with OSA without insomnia (OSA-only) using both single-night polysomnography and multi-night wrist-worn photoplethysmography/accelerometry.

METHODS

Multi-night 4-class sleep-staging was performed with a validated algorithm based on actigraphy and heart rate variability, in 67 COMISA (23 women, median age: 51 years) and 50 OSA-only (15 women, median age: 51) participants. Sleep statistics were compared using linear regression models and mixed-effects models. Multi-night variability was explored using a clustering approach and between- and within-participant analysis.

RESULTS

Polysomnographic parameters showed no significant group differences. Multi-night measurements, during 13.4 ± 5.2 nights per subject, demonstrated a longer sleep onset latency and lower sleep efficiency for the COMISA group. Detailed analysis of wake parameters revealed longer mean durations of awakenings in COMISA, as well as higher numbers of awakenings lasting 5 min and longer (WKN≥5min) and longer wake after sleep onset containing only awakenings of 5 min or longer. Within-participant variance was significantly larger in COMISA for sleep onset latency, sleep efficiency, mean duration of awakenings and WKN≥5min. Unsupervised clustering uncovered three clusters; participants with consistently high values for at least one of the wake parameters, participants with consistently low values, and participants displaying higher variability.

CONCLUSION

Patients with COMISA more often showed extended, and more variable periods of wakefulness. These observations were not discernible using single night polysomnography, highlighting the relevance of multi-night measurements to assess characteristics indicative for insomnia.

Heart rate response to cortical arousals in patients with isolated obstructive sleep apnea and with comorbid insomnia (COMISA)

PURPOSE

Comorbid insomnia often occurs in patients with obstructive sleep apnea (OSA), referred to as COMISA. Cortical arousals manifest as a common feature in both OSA and insomnia, often accompanied by elevated heart rate (HR). Our objective was to evaluate the heart rate response to nocturnal cortical arousals in patients with COMISA and patients with OSA alone.

METHODS

We analyzed data from patients with COMISA and from patients with OSA matched for apnea-hypopnea index. Sleep staging and analysis of respiratory events and cortical arousals were performed using the Philips Somnolyzer automatic scoring system. Beat-by-beat HR was analyzed from the onset of the cortical arousal to 30 heartbeats afterwards. HR responses were divided into peak and recovery phases. Cortical arousals were separately evaluated according to subtype (related to respiratory events and spontaneous) and duration (3-6 s, 6-10 s, 10-15 s).

RESULTS

A total of 72 patients with COMISA and 72 patients with OSA were included in this study. There were no overall group differences in the number of cortical arousals with and without autonomic activation. No significant differences were found for spontaneous cortical arousals. The OSA group had more cortical arousals related to respiratory events (21.0 [14.8-30.0] vs 16.0 [9.0-27.0], p = 0.016). However, the COMISA group had longer cortical arousals (7.2 [6.4-7.8] vs 6.7 [6.2-7.7] s, p = 0.024) and the HR recovery phase was prolonged (52.5 [30.8-82.5] vs 40.0 [21.8-55.5] beats/min, p = 0.017). Both the peak and the recovery phase for longer cortical arousals with a duration of 10-15 s were significantly higher in patients with COMISA compared to patients with OSA (47.0 [27.0-97.5] vs 34.0 [21.0-71.0] beats/min, p = 0.032 and 87.0 [47.0-132.0] vs 71.0 [43.0-103.5] beats/min, p = 0.049, respectively).

CONCLUSIONS

The HR recovery phase after cortical arousals related to respiratory events is prolonged in patients with COMISA compared to patients with OSA alone. This response could be indicative of the insomnia component in COMISA.

Performance of cardiorespiratory-based sleep staging in patients using beta blockers

STUDY OBJECTIVES

Automatic sleep staging based on cardiorespiratory signals from home sleep monitoring devices holds great clinical potential. Using state-of-the-art machine learning, promising performance has been reached in patients with sleep disorders. However, it is unknown whether performance would hold in individuals with potentially altered autonomic physiology, for example under the influence of medication. Here, we assess an existing sleep staging algorithm in patients with sleep disorders with and without the use of beta blockers.

METHODS

We analyzed a retrospective dataset of sleep recordings of 57 patients with sleep disorders using beta blockers and 57 age-matched patients with sleep disorders not using beta blockers. Sleep stages were automatically scored based on electrocardiography and respiratory effort from a thoracic belt, using a previously developed machine-learning algorithm (CReSS algorithm). For both patient groups, sleep stages classified by the model were compared to gold standard manual polysomnography scoring using epoch-by-epoch agreement. Additionally, for both groups, overall sleep parameters were calculated and compared between the two scoring methods.

RESULTS

Substantial agreement was achieved for four-class sleep staging in both patient groups (beta blockers: kappa = 0.635, accuracy = 78.1%; controls: kappa = 0.660, accuracy = 78.8%). No statistical difference in epoch-by-epoch agreement was found between the two groups. Additionally, the groups did not differ on agreement of derived sleep parameters.

CONCLUSIONS

We showed that the performance of the CReSS algorithm is not deteriorated in patients using beta blockers. Results do not indicate a fundamental limitation in leveraging autonomic characteristics to obtain a surrogate measure of sleep in this clinically relevant population.

CITATION

Hermans L, van Meulen F, Anderer P, et al. Performance of cardiorespiratory-based sleep staging in patients using beta blockers. J Clin Sleep Med. 2024;20(4):575-581.

Maximum a posteriori detection of heartbeats from a chest-worn accelerometer

Objective. Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assesment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach. We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximumaposterioriestimation and a Markov decision process to approach an optimal solution.Main results. The maximumaposterioriestimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heartrate measurement. Performance held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance. The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

Remote Emotion Recognition Using Continuous-Wave Bio-Radar System

The Bio-Radar is herein presented as a non-contact radar system able to capture vital signs remotely without requiring any physical contact with the subject. In this work, the ability to use the proposed system for emotion recognition is verified by comparing its performance on identifying fear, happiness and a neutral condition, with certified measuring equipment. For this purpose, machine learning algorithms were applied to the respiratory and cardiac signals captured simultaneously by the radar and the referenced contact-based system. Following a multiclass identification strategy, one could conclude that both systems present a comparable performance, where the radar might even outperform under specific conditions. Emotion recognition is possible using a radar system, with an accuracy equal to 99.7% and an F1-score of 99.9%. Thus, we demonstrated that it is perfectly possible to use the Bio-Radar system for this purpose, which is able to be operated remotely, avoiding the subject awareness of being monitored and thus providing more authentic reactions.

SelANet: decision-assisting selective sleep apnea detection based on confidence score

BACKGROUND

One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of labor, cost, and time. Therefore, studies have been conducted to develop automated detection algorithms using limited biological signals that can be more easily diagnosed. However, the lack of information from limited signals can result in uncertainty from artificial intelligence judgments. Therefore, we performed selective prediction by using estimated respiratory signals from electrocardiogram and oxygen saturation signals based on confidence scores to classify only those sleep apnea occurrence samples with high confidence. In addition, for samples with high uncertainty, this algorithm rejected them, providing a second opinion to the clinician.

METHOD

Our developed model utilized polysomnography data from 994 subjects obtained from Massachusetts General Hospital. We performed feature extraction from the latent vector using the autoencoder. Then, one dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was designed and trained to measure confidence scores for input, with an additional selection function. We set a confidence score threshold called the target coverage and performed optimization only on samples with confidence scores higher than the target coverage. As a result, we demonstrated that the empirical coverage trained in the model converged to the target coverage.

RESULT

To confirm whether the model has been optimized according to the objectives, the coverage violation was used to measure the difference between the target coverage and the empirical coverage. As a result, the value of coverage violation was found to be an average of 0.067. Based on the model, we evaluated the classification performance of sleep apnea and confirmed that it achieved 90.26% accuracy, 91.29% sensitivity, and 89.21% specificity. This represents an improvement of approximately 7.03% in all metrics compared to the performance achieved without using a selective prediction.

CONCLUSION

This algorithm based on selective prediction utilizes confidence measurement method to minimize the problem caused by limited biological information. Based on this approach, this algorithm is applicable to wearable devices despite low signal quality and can be used as a simple detection method that determine the need for polysomnography or complement it.

The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

BACKGROUND

Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.

METHODS

We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.

RESULTS

Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).

CONCLUSION

Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.

A computationally efficient algorithm for wearable sleep staging in clinical populations

This study describes a computationally efficient algorithm for 4-class sleep staging based on cardiac activity and body movements. Using an accelerometer to calculate gross body movements and a reflective photoplethysmographic (PPG) sensor to determine interbeat intervals and a corresponding instantaneous heart rate signal, a neural network was trained to classify between wake, combined N1 and N2, N3 and REM sleep in epochs of 30 s. The classifier was validated on a hold-out set by comparing the output against manually scored sleep stages based on polysomnography (PSG). In addition, the execution time was compared with that of a previously developed heart rate variability (HRV) feature-based sleep staging algorithm. With a median epoch-per-epoch κ of 0.638 and accuracy of 77.8% the algorithm achieved an equivalent performance when compared to the previously developed HRV-based approach, but with a 50-times faster execution time. This shows how a neural network, without leveraging any a priori knowledge of the domain, can automatically "discover" a suitable mapping between cardiac activity and body movements, and sleep stages, even in patients with different sleep pathologies. In addition to the high performance, the reduced complexity of the algorithm makes practical implementation feasible, opening up new avenues in sleep diagnostics.

The Accuracy of Wrist-Worn Photoplethysmogram-Measured Heart and Respiratory Rates in Abdominal Surgery Patients: Observational Prospective Clinical Validation Study

BACKGROUND

Postoperative deterioration is often preceded by abnormal vital parameters. Therefore, vital parameters of postoperative patients are routinely measured by nursing staff. Wrist-worn sensors could potentially provide an alternative tool for the measurement of vital parameters in low-acuity settings. These devices would allow more frequent or even continuous measurements of vital parameters without relying on time-consuming manual measurements, provided their accuracy in this clinical population is established.

OBJECTIVE

This study aimed to assess the accuracy of heart rate (HR) and respiratory rate (RR) measures obtained via a wearable photoplethysmography (PPG) wristband in a cohort of postoperative patients.

METHODS

The accuracy of the wrist-worn PPG sensor was assessed in 62 post-abdominal surgery patients (mean age 55, SD 15 years; median BMI 34, IQR 25-40 kg/m²). The wearable obtained HR and RR measurements were compared to those of the reference monitor in the postanesthesia or intensive care unit. Bland-Altman and Clarke error grid analyses were performed to determine agreement and clinical accuracy.

RESULTS

Data were collected for a median of 1.2 hours per patient. With a coverage of 94% for HR and 34% for RR, the device was able to provide accurate measurements for the large majority of the measurements as 98% and 93% of the measurements were within 5 bpm or 3 rpm of the reference signal. Additionally, 100% of the HR and 98% of the RR measurements were clinically acceptable on Clarke error grid analysis.

CONCLUSIONS

The wrist-worn PPG device is able to provide measurements of HR and RR that can be seen as sufficiently accurate for clinical applications. Considering the coverage, the device was able to continuously monitor HR and report RR when measurements of sufficient quality were obtained.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03923127; https://www.clinicaltrials.gov/ct2/show/NCT03923127.

Toward interpretable digital biomarkers of walking and reaching in Parkinson's disease

Multimodal digital data registered with wearable biosensors have emerged as highly complementary of clinical pencil-and-paper criteria, offering new insights in ways to detect and diagnose various aspects of Parkinson's disease (PD). A pressing question is how to combine both the clinical knowledge of PD and the new technology to create interpretable digital biomarkers easily obtainable with off-the-shelf technology. Several challenges concerning disparity in biophysical units, anatomical differences across participants, sensor positioning, and sampling resolution are addressed in this work, along with identification of optimal parameters to automatically differentiate patients with PD from controls. We combine data from a multitude of biosensors registering signals from the central (electroencephalography) and peripheral (magnetometry, kinematics) nervous systems, inclusive of the autonomic nervous system (electrocardiogram), as the participants perform natural tasks requiring different levels of intentional planning and automatic control. We find that magnetometer data during walking, across a variety of amplitude and timing signals, provide optimal separation of PD from neurotypical controls. We conclude that using multimodal signals within the context of actions that bear different levels of intent, can be revealing of features of PD that would scape the naked eye. Further, we add that clinical criteria combined with such optimal digital parameter spaces offer a far more complete picture of PD than using either one of these pieces of data alone.

Predicting the Next-Day Perceived and Physiological Stress of Pregnant Women by Using Machine Learning and Explainability: Algorithm Development and Validation

Background

Cognitive behavioral therapy–based interventions are effective in reducing prenatal stress, which can have severe adverse health effects on mothers and newborns if unaddressed. Predicting next-day physiological or perceived stress can help to inform and enable pre-emptive interventions for a likely physiologically and perceptibly stressful day. Machine learning models are useful tools that can be developed to predict next-day physiological and perceived stress by using data collected from the previous day. Such models can improve our understanding of the specific factors that predict physiological and perceived stress and allow researchers to develop systems that collect selected features for assessment in clinical trials to minimize the burden of data collection.

Objective

The aim of this study was to build and evaluate a machine-learned model that predicts next-day physiological and perceived stress by using sensor-based, ecological momentary assessment (EMA)–based, and intervention-based features and to explain the prediction results.

Methods

We enrolled pregnant women into a prospective proof-of-concept study and collected electrocardiography, EMA, and cognitive behavioral therapy intervention data over 12 weeks. We used the data to train and evaluate 6 machine learning models to predict next-day physiological and perceived stress. After selecting the best performing model, Shapley Additive Explanations were used to identify the feature importance and explainability of each feature.

Results

A total of 16 pregnant women enrolled in the study. Overall, 4157.18 hours of data were collected, and participants answered 2838 EMAs. After applying feature selection, 8 and 10 features were found to positively predict next-day physiological and perceived stress, respectively. A random forest classifier performed the best in predicting next-day physiological stress (F1 score of 0.84) and next-day perceived stress (F1 score of 0.74) by using all features. Although any subset of sensor-based, EMA-based, or intervention-based features could reliably predict next-day physiological stress, EMA-based features were necessary to predict next-day perceived stress. The analysis of explainability metrics showed that the prolonged duration of physiological stress was highly predictive of next-day physiological stress and that physiological stress and perceived stress were temporally divergent.

Conclusions

In this study, we were able to build interpretable machine learning models to predict next-day physiological and perceived stress, and we identified unique features that were highly predictive of next-day stress that can help to reduce the burden of data collection.

Validation of Heart Rate Extracted From Wrist-Based Photoplethysmography in the Perioperative Setting: Prospective Observational Study

Background

Measurement of heart rate (HR) through an unobtrusive, wrist-worn optical HR monitor (OHRM) could enable earlier recognition of patient deterioration in low acuity settings and enable timely intervention.

Objective

The goal of this study was to assess the agreement between the HR extracted from the OHRM and the gold standard 5-lead electrocardiogram (ECG) connected to a patient monitor during surgery and in the recovery period.

Methods

In patients undergoing surgery requiring anesthesia, the HR reported by the patient monitor’s ECG module was recorded and stored simultaneously with the photopletysmography (PPG) from the OHRM attached to the patient’s wrist. The agreement between the HR reported by the patient’s monitor and the HR extracted from the OHRM’s PPG signal was assessed using Bland-Altman analysis during the surgical and recovery phase.

Results

A total of 271.8 hours of data in 99 patients was recorded simultaneously by the OHRM and patient monitor. The median coverage was 86% (IQR 65%-95%) and did not differ significantly between surgery and recovery (Wilcoxon paired difference test P=.17). Agreement analysis showed the limits of agreement (LoA) of the difference between the OHRM and the ECG HR were within the range of 5 beats per minute (bpm). The mean bias was –0.14 bpm (LoA between –3.08 bpm and 2.79 bpm) and –0.19% (LoA between –5 bpm to 5 bpm) for the PPG- measured HR compared to the ECG-measured HR during surgery; during recovery, it was –0.11 bpm (LoA between –2.79 bpm and 2.59 bpm) and –0.15% (LoA between –3.92% and 3.64%).

Conclusions

This study shows that an OHRM equipped with a PPG sensor can measure HR within the ECG reference standard of –5 bpm to 5 bpm or –10% to 10% in the perioperative setting when the PPG signal is of sufficient quality. This implies that an OHRM can be considered clinically acceptable for HR monitoring in low acuity hospitalized patients.

Convolutional neural network for classification of eight types of arrhythmia using 2D time-frequency feature map from standard 12-lead electrocardiogram

Electrocardiograms (ECGs) are widely used for diagnosing cardiac arrhythmia based on the deformation of signal shapes due to changes in various heart diseases. However, these abnormal signs may not be observed in some 12 ECG channels, depending on the location, the heart shape, and the type of cardiac arrhythmia. Therefore, it is necessary to closely and comprehensively observe ECG records acquired from 12 channel electrodes to diagnose cardiac arrhythmias accurately. In this study, we proposed a clustering algorithm that can classify persistent cardiac arrhythmia as well as episodic cardiac arrhythmias using the standard 12-lead ECG records and the 2D CNN model using the time–frequency feature maps to classify the eight types of arrhythmias and normal sinus rhythm. The standard 12-lead ECG records were provided by China Physiological Signal Challenge 2018 and consisted of 6877 patients. The proposed algorithm showed high performance in classifying persistent cardiac arrhythmias; however, its accuracy was somewhat low in classifying episodic arrhythmias. If our proposed model is trained and verified using more clinical data, we believe it can be used as an auxiliary device for diagnosing cardiac arrhythmias.

Electrocardiogram-Based Emotion Recognition Systems and Their Applications in Healthcare-A Review

Affective computing is a field of study that integrates human affects and emotions with artificial intelligence into systems or devices. A system or device with affective computing is beneficial for the mental health and wellbeing of individuals that are stressed, anguished, or depressed. Emotion recognition systems are an important technology that enables affective computing. Currently, there are a lot of ways to build an emotion recognition system using various techniques and algorithms. This review paper focuses on emotion recognition research that adopted electrocardiograms (ECGs) as a unimodal approach as well as part of a multimodal approach for emotion recognition systems. Critical observations of data collection, pre-processing, feature extraction, feature selection and dimensionality reduction, classification, and validation are conducted. This paper also highlights the architectures with accuracy of above 90%. The available ECG-inclusive affective databases are also reviewed, and a popularity analysis is presented. Additionally, the benefit of emotion recognition systems towards healthcare systems is also reviewed here. Based on the literature reviewed, a thorough discussion on the subject matter and future works is suggested and concluded. The findings presented here are beneficial for prospective researchers to look into the summary of previous works conducted in the field of ECG-based emotion recognition systems, and for identifying gaps in the area, as well as in developing and designing future applications of emotion recognition systems, especially in improving healthcare.

The Autonomic Nervous System Differentiates between Levels of Motor Intent and End Effector

While attempting to bridge motor control and cognitive science, the nascent field of embodied cognition has primarily addressed intended, goal-oriented actions. Less explored, however, have been unintended motions. Such movements tend to occur largely beneath awareness, while contributing to the spontaneous control of redundant degrees of freedom across the body in motion. We posit that the consequences of such unintended actions implicitly contribute to our autonomous sense of action ownership and agency. We question whether biorhythmic activities from these motions are separable from those which intentionally occur. Here we find that fluctuations in the biorhythmic activities of the nervous systems can unambiguously differentiate across levels of intent. More important yet, this differentiation is remarkable when we examine the fluctuations in biorhythmic activity from the autonomic nervous systems. We find that when the action is intended, the heart signal leads the body kinematics signals; but when the action segment spontaneously occurs without instructions, the heart signal lags the bodily kinematics signals. We conclude that the autonomic nervous system can differentiate levels of intent. Our results are discussed while considering their potential translational value.

A Lightweight Deep Learning Model for Fast Electrocardiographic Beats Classification With a Wearable Cardiac Monitor: Development and Validation Study

Background

Electrocardiographic (ECG) monitors have been widely used for diagnosing cardiac arrhythmias for decades. However, accurate analysis of ECG signals is difficult and time-consuming work because large amounts of beats need to be inspected. In order to enhance ECG beat classification, machine learning and deep learning methods have been studied. However, existing studies have limitations in model rigidity, model complexity, and inference speed.

Objective

To classify ECG beats effectively and efficiently, we propose a baseline model with recurrent neural networks (RNNs). Furthermore, we also propose a lightweight model with fused RNN for speeding up the prediction time on central processing units (CPUs).

Methods

We used 48 ECGs from the MIT-BIH (Massachusetts Institute of Technology-Beth Israel Hospital) Arrhythmia Database, and 76 ECGs were collected with S-Patch devices developed by Samsung SDS. We developed both baseline and lightweight models on the MXNet framework. We trained both models on graphics processing units and measured both models’ inference times on CPUs.

Results

Our models achieved overall beat classification accuracies of 99.72% for the baseline model with RNN and 99.80% for the lightweight model with fused RNN. Moreover, our lightweight model reduced the inference time on CPUs without any loss of accuracy. The inference time for the lightweight model for 24-hour ECGs was 3 minutes, which is 5 times faster than the baseline model.

Conclusions

Both our baseline and lightweight models achieved cardiologist-level accuracies. Furthermore, our lightweight model is competitive on CPU-based wearable hardware.

Lying Awake at Night: Cardiac Autonomic Activity in Relation to Sleep Onset and Maintenance

Insomnia, i.e., difficulties initiating and/or maintaining sleep, is one of the most common sleep disorders. To study underlying mechanisms for insomnia, we studied autonomic activity changes around sleep onset in participants without clinical insomnia but with varying problems with initiating or maintaining sleep quantified as increased sleep onset latency (SOL) and wake after sleep onset (WASO), respectively. Polysomnography and electrocardiography were simultaneously recorded in 176 participants during a single night. Cardiac autonomic activity was assessed using frequency domain analysis of RR intervals and results show that the normalized spectral power in the low frequency band (LF_nu) after sleep onset was significantly higher in participants with long SOL compared to participants with short SOL. Furthermore, the normalized spectral power in the high frequency band (HF_nu) was significantly lower in participants with long SOL as compared to participants with short SOL over 3 time periods (first 10 min in bed intending to sleep, 10 min before, and 10 min after sleep onset). These results suggest that participants with long SOL are more aroused in all three examined time periods when compared to participants with short SOL, especially for young adults (20–40 years). As there is no clear consensus on the cutoff for an increased WASO, we used a data-driven approach to explore different cutoffs to define short WASO and long WASO groups. LF_nu, HF_nu, and LF/HF differed between the long and the short WASO groups. A higher LF_nu and LF/HF and a lower HF_nu was observed in participants with long WASO for most cutoffs. The highest effect size was found using the cutoff of 66 min. Our findings suggest that autonomic cardiac activity has predictive value with respect to sleep characteristics pertaining to sleep onset and maintenance.

Extraction of foetal ECG from abdominal ECG by nonlinear transformation and estimations

BACKGROUND AND OBJECTIVE

This paper proposes a simple yet effective method for the extraction of foetal ECG from abdominal ECG which is necessary due to similar spatial and temporal content of mother and foetal ECG.

METHODS

The proposed algorithm for extraction of foetal ECG (fECG) from abdominal signal uses single channel. Pre-processing of abdominal ECG (abdECG) has been done to eliminate noise and condition the signal. The maternal ECG R-peaks have been detected based on thresholding, first order Gaussian differentiation and zero cross detection on pre-processed signal. Having identified R-peaks and pre-processed signal as base, using Maximum Likelihood Estimation, one beat including QRS complex morphology of maternal ECG (mECG) has been constructed. Extraction of maternal ECG from abdECG is done based on the constructed beat, R-peak locations and its corresponding QRS complex of abdECG. Extracted mECG has been cancelled from abdECG. This results in foetal ECG with residual noise. The noise has been reduced by Polynomial Approximation and Total Variation (PATV) to improve SNR. This approach ensures no loss of partially or completely overlapped fECG signals due to mECG removal. The algorithm is tested on three database namely daISy (DB_I), Physiobank challenge 2013 (DB_II) and abdominal and direct foetal ECG database (adfecgdb) of Physiobank (DB_III).

RESULTS

The algorithm detected no false positives or false negatives with certain channel for DB_I, DB_II and DB_III which shows that the proposed algorithm can achieve good performance. Overall accuracy and sensitivity of the system is 98.53% and 100% for DB_I. Best accuracy and sensitivity of 97.77% and 98.63% are obtained for DB_II. Best accuracy of 92.41% and sensitivity of 93.8% are obtained for DB_III. Correlation coefficient between actual foetal heart rate (fHR) and estimated fHR of 0.66 for DB_II and 0.59 for DB_III is obtained. The method has obtained overall F1 score of 99.25% for DB_I, 96.04% for DB_II and 94.25% for DB_III. It has obtained a best MSE of fHR and overall MSE of R-R interval which is 10.8bpm² and 2.2 ms for DB_II, 12bpm² and 2.14 ms for DB_III.

CONCLUSION

The results for different public databases show that the proposed method is capable of providing good results. The foetal QRS, R-peaks and R-R intervals have also been obtained in this method. Thus, it gives a significant contribution in the required area of research.

Noisy ECG Signal Analysis for Automatic Peak Detection

Cardiac signal processing is usually a computationally demanding task as signals are heavily contaminated by noise and other artifacts. In this paper, an effective approach for peak point detection and localization in noisy electrocardiogram (ECG) signals is presented. Six stages characterize the implemented method, which adopts the Hilbert transform and a thresholding technique for the detection of zones inside the ECG signal which could contain a peak. Subsequently, the identified zones are analyzed using the wavelet transform for R point detection and localization. The conceived signal processing technique has been evaluated, adopting ECG signals belonging to MIT-BIH Noise Stress Test Database, which includes specially selected Holter recordings characterized by baseline wander, muscle artifacts and electrode motion artifacts as noise sources. The experimental results show that the proposed method reaches most satisfactory performance, even when challenging ECG signals are adopted. The results obtained are presented, discussed and compared with some other R wave detection algorithms indicated in literature, which adopt the same database as a test bench. In particular, for a signal to noise ratio (SNR) equal to 6 dB, results with minimal interference from noise and artifacts have been obtained, since Se e +P achieve values of 98.13% and 96.91, respectively.

Autonomic cardiac activity in adults with short and long sleep onset latency

Autonomic cardiac activity during sleep has been widely studied. Research has mostly focused on cardiac activity between different sleep stages and wakefulness as well as between normal and pathological sleep. This work investigates autonomic activity changes during sleep onset in healthy subjects with long and short sleep onset latency (SOL). Polysomnography (PSG) and electrocardiography (ECG) were simultaneously recorded in 186 healthy subjects during a single night. Autonomic activity was assessed based on frequency domain analysis of RR intervals and results show that the analysis of RR intervals differs significantly between the short SOL and the long SOL groups. We found that the spectral power in the low frequency band (LF) was significantly higher in the long SOL group compared to the short SOL group in the first 10 minutes in bed intended to sleep. There was no significant difference for LF and the spectral power in the high frequency band (HF) 10 minutes before and after sleep onset between the two groups. Only in the short SOL group there was a significant increase in HF from the first 10 minutes in bed intended to sleep to 10 minutes before SO, while LF decreased significantly in both groups. The effect of time (5.5-min bin) on the heart rate variability (HRV) features around sleep onset showed that both LF and HF differed significantly during the period surrounding sleep onset only in the short SOL group.

Characterization of Sensory-Motor Behavior Under Cognitive Load Using a New Statistical Platform for Studies of Embodied Cognition

The field of enacted/embodied cognition has emerged as a contemporary attempt to connect the mind and body in the study of cognition. However, there has been a paucity of methods that enable a multi-layered approach tapping into different levels of functionality within the nervous systems (e.g., continuously capturing in tandem multi-modal biophysical signals in naturalistic settings). The present study introduces a new theoretical and statistical framework to characterize the influences of cognitive demands on biophysical rhythmic signals harnessed from deliberate, spontaneous and autonomic activities. In this study, nine participants performed a basic pointing task to communicate a decision while they were exposed to different levels of cognitive load. Within these decision-making contexts, we examined the moment-by-moment fluctuations in the peak amplitude and timing of the biophysical time series data (e.g., continuous waveforms extracted from hand kinematics and heart signals). These spike-trains data offered high statistical power for personalized empirical statistical estimation and were well-characterized by a Gamma process. Our approach enabled the identification of different empirically estimated families of probability distributions to facilitate inference regarding the continuous physiological phenomena underlying cognitively driven decision-making. We found that the same pointing task revealed shifts in the probability distribution functions (PDFs) of the hand kinematic signals under study and were accompanied by shifts in the signatures of the heart inter-beat-interval timings. Within the time scale of an experimental session, marked changes in skewness and dispersion of the distributions were tracked on the Gamma parameter plane with 95% confidence. The results suggest that traditional theoretical assumptions of stationarity and normality in biophysical data from the nervous systems are incongruent with the true statistical nature of empirical data. This work offers a unifying platform for personalized statistical inference that goes far beyond those used in conventional studies, often assuming a “one size fits all model” on data drawn from discrete events such as mouse clicks, and observations that leave out continuously co-occurring spontaneous activity taking place largely beneath awareness.

A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment

Electrocardiogram (ECG) signal quality assessment (SQA) plays a vital role in significantly improving the diagnostic accuracy and reliability of unsupervised ECG analysis systems. In practice, the ECG signal is often corrupted with different kinds of noises and artifacts. Therefore, numerous SQA methods were presented based on the ECG signal and/or noise features and the machine learning classifiers and/or heuristic decision rules. This paper presents an overview of current state-of-the-art SQA methods and highlights the practical limitations of the existing SQA methods. Based upon past and our studies, it is noticed that a lightweight ECG noise analysis framework is highly demanded for real-time detection, localization, and classification of single and combined ECG noises within the context of wearable ECG monitoring devices which are often resource constrained.