Characterising the motion and cardiorespiratory interaction of preterm infants can improve the classification of their sleep state.

AIM: This study aimed to classify quiet sleep, active sleep and wake states in preterm infants by analysing cardiorespiratory signals obtained from routine patient monitors. METHODS: We studied eight preterm infants, with an average postmenstrual age of 32.3 ± 2.4 weeks, in a neonatal intensive care unit in the Netherlands. Electrocardiography and chest impedance respiratory signals were recorded. After filtering and R-peak detection, cardiorespiratory features and motion and cardiorespiratory interaction features were extracted, based on previous research. An extremely randomised trees algorithm was used for classification and performance was evaluated using leave-one-patient-out cross-validation and Cohen's kappa coefficient. RESULTS: A sleep expert annotated 4731 30-second epochs (39.4 h) and active sleep, quiet sleep and wake accounted for 73.3%, 12.6% and 14.1% respectively. Using all features, and the extremely randomised trees algorithm, the binary discrimination between active and quiet sleep was better than between other states. Incorporating motion and cardiorespiratory interaction features improved the classification of all sleep states (kappa 0.38 ± 0.09) than analyses without these features (kappa 0.31 ± 0.11). CONCLUSION: Cardiorespiratory interactions contributed to detecting quiet sleep and motion features contributed to detecting wake states. This combination improved the automated classifications of sleep states.

A Review on Atrial Fibrillation Detection From Ambulatory ECG.

Atrial fibrillation (AF) is a prevalent clinical arrhythmia disease and is an important cause of stroke, heart failure, and sudden death. Due to the insidious onset and no obvious clinical symptoms of AF, the status of AF diagnosis and treatment is not optimal. Early AF screening or detection is essential. Internet of Things (IoT) and artificial intelligence (AI) technologies have driven the development of wearable electrocardiograph (ECG) devices used for health monitoring, which are an effective means of AF detection. The main challenges of AF analysis using ambulatory ECG include ECG signal quality assessment to select available ECG, the robust and accurate detection of QRS complex waves to monitor heart rate, and AF identification under the interference of abnormal ECG rhythm. Through ambulatory ECG measurement and intelligent detection technology, the probability of postoperative recurrence of AF can be reduced, and personalized treatment and management of patients with AF can be realized. This work describes the status of AF monitoring technology in terms of devices, algorithms, clinical applications, and future directions.

Combining Cardiorespiratory Signals and Video-Based Actigraphy for Classifying Preterm Infant Sleep States.

The classification of sleep state in preterm infants, particularly in distinguishing between active sleep (AS) and quiet sleep (QS), has been investigated using cardiorespiratory information such as electrocardiography (ECG) and respiratory signals. However, accurately differentiating between AS and wake remains challenging; therefore, there is a pressing need to include additional information to further enhance the classification performance. To address the challenge, this study explores the effectiveness of incorporating video-based actigraphy analysis alongside cardiorespiratory signals for classifying the sleep states of preterm infants. The study enrolled eight preterm infants, and a total of 91 features were extracted from ECG, respiratory signals, and video-based actigraphy. By employing an extremely randomized trees (ET) algorithm and leave-one-subject-out cross-validation, a kappa score of 0.33 was achieved for the classification of AS, QS, and wake using cardiorespiratory features only. The kappa score significantly improved to 0.39 when incorporating eight video-based actigraphy features. Furthermore, the classification performance of AS and wake also improved, showing a kappa score increase of 0.21. These suggest that combining video-based actigraphy with cardiorespiratory signals can potentially enhance the performance of sleep-state classification in preterm infants. In addition, we highlighted the distinct strengths and limitations of video-based actigraphy and cardiorespiratory data in classifying specific sleep states.

Pitfalls in EEG Analysis in Patients With Nonconvulsive Status Epilepticus: A Preliminary Study.

Objective: Electroencephalography (EEG) interpretations through visual (by human raters) and automated (by computer technology) analysis were still not reliable for the diagnosis of nonconvulsive status epilepticus (NCSE). This study aimed to identify typical pitfalls in the EEG analysis and make suggestions as to how those pitfalls might be avoided. Methods: We analyzed the EEG recordings of individuals who had clinically confirmed or suspected NCSE. Epileptiform EEG activity during seizures (ictal discharges) was visually analyzed by 2 independent raters. We investigated whether unreliable EEG visual interpretations quantified by low interrater agreement can be predicted by the characteristics of ictal discharges and individuals' clinical data. In addition, the EEG recordings were automatically analyzed by in-house algorithms. To further explore the causes of unreliable EEG interpretations, 2 epileptologists analyzed EEG patterns most likely misinterpreted as ictal discharges based on the differences between the EEG interpretations through the visual and automated analysis. Results: Short ictal discharges with a gradual onset (developing over 3 s in length) were liable to be misinterpreted. An extra 2 min of ictal discharges contributed to an increase in the kappa statistics of >0.1. Other problems were the misinterpretation of abnormal background activity (slow-wave activities, other abnormal brain activity, and the ictal-like movement artifacts), continuous interictal discharges, and continuous short ictal discharges. Conclusion: A longer duration criterion for NCSE-EEGs than 10 s that is commonly used in NCSE working criteria is recommended. Using knowledge of historical EEGs, individualized algorithms, and context-dependent alarm thresholds may also avoid the pitfalls.

Epileptic Seizure Detection by Cascading Isolation Forest-Based Anomaly Screening and EasyEnsemble.

The electroencephalogram (EEG), for measuring the electrophysiological activity of the brain, has been widely applied in automatic detection of epilepsy seizures. Various EEG-based seizure detection algorithms have already yielded high sensitivity, but training those algorithms requires a large amount of labelled data. Data labelling is often done with a lot of human efforts, which is very time-consuming. In this study, we propose a hybrid system integrating an unsupervised learning (UL) module and a supervised learning (SL) module, where the UL module can significantly reduce the workload of data labelling. For preliminary seizure screening, UL synthesizes amplitude-integrated EEG (aEEG) extraction, isolation forest-based anomaly detection, adaptive segmentation, and silhouette coefficient-based anomaly detection evaluation. The UL module serves to quickly locate the determinate subjects (seizure segments and seizure-free segments) and the indeterminate subjects (potential seizure candidates). Afterwards, more robust seizure detection for the indeterminate subjects is performed by the SL using an EasyEnsemble algorithm. EasyEnsemble, as a class-imbalance learning method, can potentially decrease the generalization error of the seizure-free segments. The proposed method can significantly reduce the workload of data labelling while guaranteeing satisfactory performance. The proposed seizure detection system is evaluated using the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) scalp EEG dataset, and it achieves a mean accuracy of 92.62%, a mean sensitivity of 95.55%, and a mean specificity of 92.57%. To the best of our knowledge, this is the first epilepsy seizure detection study employing the integration of both the UL and the SL modules, achieving a competitive performance superior or similar to that of the state-of-the-art methods.

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography.

Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen's kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.

Characterizing cardiorespiratory interaction in preterm infants across sleep states using visibility graph analysis.

Cardiorespiratory interaction (CRI) has been intensively studied in adult sleep, yet not in preterm infants, in particular across different sleep states including wake (W), active sleep (AS), and quiet sleep (QS). The aim of this study was to quantify the interaction between cardiac and respiratory activities in different sleep states of preterm infants. The postmenstrual age (PMA) of preterm infants was also taken into consideration. The CRI during sleep was analyzed using a visibility graph (VG) method, enabling the nonlinear analysis of CRI in a complex network. For each sleep state, parameters quantifying various aspects of the CRI characteristics from constructed VG network including mean degree (Dm) and its variability (Dsd), clustering coefficient (CCm) and its variability (CCsd), assortativity coefficient (AC), and complexity (DSE) were extracted from the CRI networks. The interaction effect of sleep state and PMA was found to be statistically significant on all CRI parameters except for AC and DSE. The main effect between sleep state and CRI parameters was statistically significant except for CCm, and that between PMA and CRI parameters was statistically significant except for DSE. In conclusion, the CRI of preterm infants is associated with sleep states and PMA in general. For preterm infants with a larger PMA, CRI has a more clustered pattern during different sleep states, where QS shows a more regular, stratified, and stronger CRI than other states. In the future, these parameters can be potentially used to separate sleep states in preterm infants.NEW & NOTEWORTHY The interaction between cardiac and respiratory activities is investigated in preterm infant sleep using an advanced nonlinear method (visibility graph) and some important characteristics are shown to be significantly different across sleep states, which has not been studied before.

Freezing of gait detection in Parkinson's disease via multimodal analysis of EEG and accelerometer signals.

Parkinson's disease (PD) patients with freezing of gait (FOG) can suddenly lose their forward moving ability leading to unexpected falls. To overcome FOG and avoid the falls, a real-time accurate FOG detection or prediction system is desirable to trigger on-demand cues. In this study, we designed and implemented an in-place movement experiment for PD patients to provoke FOG and meanwhile acquired multimodal physiological signals, such as electroencephalography (EEG) and accelerometer signals. A multimodal model using brain activity from EEG and motion data from accelerometers was developed to improve FOG detection performance. In the detection of over 700 FOG episodes observed in the experiments, the multimodal model achieved 0.211 measured by Matthews Correlation Coefficient (MCC) compared with the single-modal models (0.127 or 0.139).Clinical Relevance- This is the first study to use multimodal: EEG and accelerometer signal analysis in FOG detection, and an improvement was achieved.

False alarms reduction in non-convulsive status epilepticus detection via continuous EEG analysis.

OBJECTIVE: Frequent false alarms from computer-assisted monitoring systems may harm the safety of patients with non-convulsive status epilepticus (NCSE). In this study, we aimed at reducing false alarms in the NCSE detection based on preventing from three common errors: over-interpretation of abnormal background activity, dense short ictal discharges and continuous interictal discharges as ictal discharges. APPROACH: We analyzed 10 participants' hospital-archived 127-hour electroencephalography (EEG) recordings with 310 ictal discharges. To reduce the false alarms caused by abnormal background activity, we used morphological features extracted by visibility graph methods in addition to time-frequency features. To reduce the false alarms caused by over-interpreting short ictal discharges and interictal discharges, we created two synthetic classes-'Suspected Non-ictal' and 'Suspected Ictal'-based on the misclassified categories and constructed a synthetic 4-class dataset combining the standard two classes-'Non-ictal' and 'Ictal'-to train a 4-class classifier. Precision-recall curves were used to compare our proposed 4-class classification model and the standard 2-class classification model with or without the morphological features in the leave-one-out cross validation stage. The sensitivity and precision were primarily used as performance metrics for the detection of a seizure event. MAIN RESULTS: The 4-class classification model improved the performance of the standard 2-class model, in particular increasing the precision by 15% at an 80% sensitivity level when only time-frequency features were used. Using the morphological features, the 4-class classification model achieved the best performances: a sensitivity of 93% ± 12% and a precision of 55% ± 30% in the group level. 100% accuracy was reached in a participant's 4.3-hour recording with 5 ictal discharges. SIGNIFICANCE: False alarms in the NCSE detection were remarkably reduced using the morphological features and the proposed 4-class classification model.

Atrial fibrillation monitoring with wrist-worn photoplethysmography-based wearables: State-of-the-art review.

Early detection and diagnosis of atrial fibrillation (AF) is essential in order to prevent stroke and other severe health consequences. The challenges in diagnosing AF arise from its intermittent and asymptomatic nature. Wrist-worn devices that use monitoring based on photoplethysmography have been proposed recently as a possible solution because of their ability to monitor heart rate and rhythm for long periods of time at low cost. Long-term continuous monitoring with implantable devices has been shown to increase the percentage of detected AF episodes, but the additional value of wrist-worn devices has yet to be determined. In this review, we present the state of the art in AF detection with wrist-worn devices, discuss the potential of the technology and current knowledge gaps, and propose directions for future research. The state-of-the-art methods show excellent accuracy for AF detection. However, most of the studies were conducted in hospital settings, and more studies showing the accuracy of the technology for ambulatory long-term monitoring are needed. Objective comparison of results and methodologies among different studies currently is difficult due to the lack of adequate public datasets.

Detecting Atrial Fibrillation and Atrial Flutter in Daily Life Using Photoplethysmography Data.

OBJECTIVE: Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. METHODS: A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75%-25% for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. RESULTS: The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1% and 98.2/99.7/92.8%, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. CONCLUSION: The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. SIGNIFICANCE: PPG could indicate presence of AFL, not only AF.

Sleep stage classification from heart-rate variability using long short-term memory neural networks.

Automated sleep stage classification using heart rate variability (HRV) may provide an ergonomic and low-cost alternative to gold standard polysomnography, creating possibilities for unobtrusive home-based sleep monitoring. Current methods however are limited in their ability to take into account long-term sleep architectural patterns. A long short-term memory (LSTM) network is proposed as a solution to model long-term cardiac sleep architecture information and validated on a comprehensive data set (292 participants, 584 nights, 541.214 annotated 30 s sleep segments) comprising a wide range of ages and pathological profiles, annotated according to the Rechtschaffen and Kales (R&K) annotation standard. It is shown that the model outperforms state-of-the-art approaches which were often limited to non-temporal or short-term recurrent classifiers. The model achieves a Cohen's k of 0.61 ± 0.15 and accuracy of 77.00 ± 8.90% across the entire database. Further analysis revealed that the performance for individuals aged 50 years and older may decline. These results demonstrate the merit of deep temporal modelling using a diverse data set and advance the state-of-the-art for HRV-based sleep stage classification. Further research is warranted into individuals over the age of 50 as performance tends to worsen in this sub-population.

Automated preterm infant sleep staging using capacitive electrocardiography.

OBJECTIVE: To date, mainly obtrusive methods (e.g. adhesive electrodes in electroencephalography or electrocardiography) have been necessary to determine the preterm infant sleep states. As any obtrusive measure should be avoided in preterm infants because of their immature skin development, we investigated the possibility of automated sleep staging using electrocardiograph signals from non-adhesive capacitive electrocardiography. APPROACH: Capacitive electrocardiography data from eight different patients with a mean gestational age of 30 ± 2.5 weeks are compared to manually annotated reference signals from classic adhesive electrodes. The sleep annotations were performed by two trained observers based on behavioral observations. MAIN RESULTS: Based on these annotations, classification performance of the preterm infant active and quiet sleep states, based on capacitive electrocardiography signals, showed a kappa value of 0.56 ± 0.20. Adding wake and caretaking into the classification, a performance of kappa 0.44 ± 0.21 was achieved. In-between sleep state performance showed a classification performance of kappa 0.36 ± 0.12. Lastly, a performance for all sleep states of kappa 0.35 ± 0.17 was attained. SIGNIFICANCE: Capacitive electrocardiography signals can be utilized to classify the central preterm infant sleep states, active and quiet sleep. With further research based on our results, automated classification of sleep states can become an essential instrument in future intensive neonatal care for continuous brain maturation monitoring. In particular, being able to use capacitive electrocardiography for continuous monitoring is a significant contributor to reducing disruption and harm for this extremely fragile patient group.

Estimating blood pressure trends and the nocturnal dip from photoplethysmography.

OBJECTIVE: Evaluate a method for the estimation of the nocturnal systolic blood pressure (SBP) dip from 24 h blood pressure trends using a wrist-worn photoplethysmography (PPG) sensor and a deep neural network in free-living individuals, comparing the deep neural network to traditional machine learning and non-machine learning baselines. APPROACH: A wrist-worn PPG sensor was worn by 106 healthy individuals for 226 d during which 5111 reference values for blood pressure (BP) were obtained with a 24 h ambulatory BP monitor and matched with the PPG sensor data. Features based on heart rate variability and pulse morphology were extracted from the PPG waveforms. Long- and short term memory (LSTM) networks, dense networks, random forests and linear regression models were trained and evaluated in their capability of tracking trends in BP, as well as the estimation of the SBP dip. MAIN RESULTS: Best performance for estimating the SBP dip were obtained with a deep LSTM neural network with a root mean squared error (RMSE) of 3.12 [Formula: see text] 2.20 [Formula: see text] mmHg and a correlation of 0.69 [Formula: see text]. This dip was derived from trend estimates of BP which had an RMSE of 8.22 [Formula: see text] 1.49 mmHg for systolic and 6.55 [Formula: see text] 1.39 mmHg for diastolic BP (DBP). While other models had similar performance for the tracking of relative BP, they did not perform as well as the LSTM for the SBP dip. SIGNIFICANCE: The work provides first evidence for the unobtrusive estimation of the nocturnal SBP dip, a highly prognostic clinical parameter. It is also the first to evaluate unobtrusive BP measurement in a large data set of unconstrained 24 h measurements in free-living individuals and provides evidence for the utility of LSTM models in this domain.

Finger and forehead photoplethysmography-derived pulse-pressure variation and the benefits of baseline correction.

To non-invasively predict fluid responsiveness, respiration-induced pulse amplitude variation (PAV) in the photoplethysmographic (PPG) signal has been proposed as an alternative to pulse pressure variation (PPV) in the arterial blood pressure (ABP) signal. However, it is still unclear how the performance of the PPG-derived PAV is site-dependent during surgery. The aim of this study is to compare finger- and forehead-PPG derived PAV in their ability to approach the value and trend of ABP-derived PPV. Furthermore, this study investigates four potential confounding factors, (1) baseline variation, (2) PPV, (3) ratio of respiration and heart rate, and (4) perfusion index, which might affect the agreement between PPV and PAV. In this work, ABP, finger PPG, and forehead PPG were continuously recorded in 29 patients undergoing major surgery in the operating room. A total of 91.2 h data were used for analysis, from which PAV and PPV were calculated and compared. We analyzed the impact of the four factors using a multiple linear regression (MLR) analysis. The results show that compared with the ABP-derived PPV, finger-derived PAV had an agreement of 3.2 ± 5.1%, whereas forehead-PAV had an agreement of 12.0 ± 9.1%. From the MLR analysis, we found that baseline variation was a factor significantly affecting the agreement between PPV and PAV. After correcting for respiration-induced baseline variation, the agreements for finger- and forehead-derived PAV were improved to reach an agreement of - 1.2 ± 3.8% and 3.3 ± 4.8%, respectively. To conclude, finger-derived PAV showed better agreement with ABP-derived PPV compared to forehead-derived PAV. Baseline variation was a factor that significantly affected the agreement between PPV and PAV. By correcting for the baseline variation, improved agreements were obtained for both the finger and forehead, and the difference between these two agreements was diminished. The tracking abilities for both finger- and forehead-derived PAV still warrant improvement for wide use in clinical practice. Overall, our results show that baseline-corrected finger- and forehead-derived PAV may provide a non-invasive alternative for PPV.

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.

Automatic and Continuous Discomfort Detection for Premature Infants in a NICU Using Video-Based Motion Analysis.

Frequent pain and discomfort in premature infants can lead to long-term adverse neurodevelopmental outcomes. Video-based monitoring is considered to be a promising contactless method for identification of discomfort moments. In this study, we propose a video-based method for automated detection of infant discomfort. The method is based on analyzing facial and body motion. Therefore, motion trajectories are estimated from frame to frame using optical flow. For each video segment, we further calculate the motion acceleration rate and extract 18 time- and frequency-domain features characterizing motion patterns. A support vector machine (SVM) classifier is then applied to video sequences to recognize infant status of comfort or discomfort. The method is evaluated using 183 video segments for 11 infants from 17 heel prick events. Experimental results show an AUC of 0.94 for discomfort detection and the average accuracy of 0.86 when combining all proposed features, which is promising for clinical use.

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.