A comparison of probabilistic classifiers for sleep stage classification

Somnotate: A probabilistic sleep stage classifier for studying vigilance state transitions

Electrophysiological recordings from freely behaving animals are a widespread and powerful mode of investigation in sleep research. These recordings generate large amounts of data that require sleep stage annotation (polysomnography), in which the data is parcellated according to three vigilance states: awake, rapid eye movement (REM) sleep, and non-REM (NREM) sleep. Manual and current computational annotation methods ignore intermediate states because the classification features become ambiguous, even though intermediate states contain important information regarding vigilance state dynamics. To address this problem, we have developed "Somnotate"-a probabilistic classifier based on a combination of linear discriminant analysis (LDA) with a hidden Markov model (HMM). First we demonstrate that Somnotate sets new standards in polysomnography, exhibiting annotation accuracies that exceed human experts on mouse electrophysiological data, remarkable robustness to errors in the training data, compatibility with different recording configurations, and an ability to maintain high accuracy during experimental interventions. However, the key feature of Somnotate is that it quantifies and reports the certainty of its annotations. We leverage this feature to reveal that many intermediate vigilance states cluster around state transitions, whereas others correspond to failed attempts to transition. This enables us to show for the first time that the success rates of different types of transition are differentially affected by experimental manipulations and can explain previously observed sleep patterns. Somnotate is open-source and has the potential to both facilitate the study of sleep stage transitions and offer new insights into the mechanisms underlying sleep-wake dynamics.

Performance of an open machine learning model to classify sleep/wake from actigraphy across ∼24-hour intervals without knowledge of rest timing

GOAL AND AIMS

Commonly used actigraphy algorithms are designed to operate within a known in-bed interval. However, in free-living scenarios this interval is often unknown. We trained and evaluated a sleep/wake classifier that operates on actigraphy over ∼24-hour intervals, without knowledge of in-bed timing.

FOCUS TECHNOLOGY

Actigraphy counts from ActiWatch Spectrum devices.

REFERENCE TECHNOLOGY

Sleep staging derived from polysomnography, supplemented by observation of wakefulness outside of the staged interval. Classifications from the Oakley actigraphy algorithm were additionally used as performance reference.

SAMPLE

Adults, sleeping in either a home or laboratory environment.

DESIGN

Machine learning was used to train and evaluate a sleep/wake classifier in a supervised learning paradigm. The classifier is a temporal convolutional network, a form of deep neural network.

CORE ANALYTICS

Performance was evaluated across ∼24 hours, and additionally restricted to only in-bed intervals, both in terms of epoch-by-epoch performance, and the discrepancy of summary statistics within the intervals.

ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES

Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset.

CORE OUTCOMES

Over ∼24 hours, the temporal convolutional network classifier produced the same or better performance as the Oakley classifier on all measures tested. When restricting analysis to the in-bed interval, the temporal convolutional network remained favorable on several metrics.

IMPORTANT SUPPLEMENTAL OUTCOMES

Performance decreased on the Multi-Ethnic Study of Atherosclerosis dataset, especially when restricting analysis to the in-bed interval.

CORE CONCLUSION

A classifier using data labeled over ∼24-hour intervals allows for the continuous classification of sleep/wake without knowledge of in-bed intervals. Further development should focus on improving generalization performance.

Methodologies and Wearable Devices to Monitor Biophysical Parameters Related to Sleep Dysfunctions: An Overview

Sleep is crucial for human health from metabolic, mental, emotional, and social points of view; obtaining good sleep in terms of quality and duration is fundamental for maintaining a good life quality. Over the years, several systems have been proposed in the scientific literature and on the market to derive metrics used to quantify sleep quality as well as detect sleep disturbances and disorders. In this field, wearable systems have an important role in the discreet, accurate, and long-term detection of biophysical markers useful to determine sleep quality. This paper presents the current state-of-the-art wearable systems and software tools for sleep staging and detecting sleep disorders and dysfunctions. At first, the paper discusses sleep's functions and the importance of monitoring sleep to detect eventual sleep disturbance and disorders. Afterward, an overview of prototype and commercial headband-like wearable devices to monitor sleep is presented, both reported in the scientific literature and on the market, allowing unobtrusive and accurate detection of sleep quality markers. Furthermore, a survey of scientific works related the effect of the COVID-19 pandemic on sleep functions, attributable to both infection and lifestyle changes. In addition, a survey of algorithms for sleep staging and detecting sleep disorders is introduced based on an analysis of single or multiple biosignals (EEG-electroencephalography, ECG-electrocardiography, EMG-electromyography, EOG-electrooculography, etc.). Lastly, comparative analyses and insights are provided to determine the future trends related to sleep monitoring systems.

Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm

Background and Objectives: Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. Materials and Methods: A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. Results: The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). Conclusions: Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.

Aleatory-aware deep uncertainty quantification for transfer learning

The user does not have any idea about the credibility of outcomes from deep neural networks (DNN) when uncertainty quantification (UQ) is not employed. However, current Deep UQ classification models capture mostly epistemic uncertainty. Therefore, this paper aims to propose an aleatory-aware Deep UQ method for classification problems. First, we train DNNs through transfer learning and collect numeric output posteriors for all training samples instead of logical outputs. Then we determine the probability of happening a certain class from K-nearest output posteriors of the same DNN in training samples. We name this probability as opacity score, as the paper focuses on the detection of opacity on X-ray images. This score reflects the level of aleatory on the sample. When the NN is certain on the classification of the sample, the probability of happening a class becomes much higher than the probabilities of others. Probabilities for different classes become close to each other for a highly uncertain classification outcome. To capture the epistemic uncertainty, we train multiple DNNs with different random initializations, model selection, and augmentations to observe the effect of these training parameters on prediction and uncertainty. To reduce execution time, we first obtain features from the pre-trained NN. Then we apply features to the ensemble of fully connected layers to get the distribution of opacity score during the test. We also train several ResNet and DenseNet DNNs to observe the effect of model selection on prediction and uncertainty. The paper also demonstrates a patient referral framework based on the proposed uncertainty quantification. The scripts of the proposed method are available at the following link: https://github.com/dipuk0506/Aleatory-aware-UQ.

Automated Scoring of Sleep and Associated Events

Conventionally, sleep and associated events are scored visually by trained technologists according to the rules summarized in the American Academy of Sleep Medicine Manual. Since its first publication in 2007, the manual was continuously updated; the most recent version as of this writing was published in 2020. Human expert scoring is considered as gold standard, even though there is increasing evidence of limited interrater reliability between human scorers. Significant advances in machine learning have resulted in powerful methods for addressing complex classification problems such as automated scoring of sleep and associated events. Evidence is increasing that these autoscoring systems deliver performance comparable to manual scoring and offer several advantages to visual scoring: (1) avoidance of the rather expensive, time-consuming, and difficult visual scoring task that can be performed only by well-trained and experienced human scorers, (2) attainment of consistent scoring results, and (3) proposition of added value such as scoring in real time, sleep stage probabilities per epoch (hypnodensity), estimates of signal quality and sleep/wake-related features, identifications of periods with clinically relevant ambiguities (confidence trends), configurable sensitivity and rule settings, as well as cardiorespiratory sleep staging for home sleep apnea testing. This chapter describes the development of autoscoring systems since the first attempts in the 1970s up to the most recent solutions based on deep neural network approaches which achieve an accuracy that allows to use the autoscoring results directly for review and interpretation by a physician.

Effects of Touchscreen Media Use on Toddlers' Sleep: Insights from Longtime ECG Monitoring

Wearable biomedical sensor technology enables reliable monitoring of physiological data, even in very young children. The purpose of the present study was to develop algorithms for gaining valid physiological indicators of sleep quality in toddlers, using data from an undisturbing and easy-to-use wearable device. The study further reports the application of this technique to the investigation of potential impacts of early touchscreen media use. Toddlers' touchscreen media use is of strong interest for parents, educators, and researchers. Mostly, negative effects of media use are assumed, among them, disturbances of sleep and impairments of learning and development. In 55 toddlers (32 girls, 23 boys; 27.4 ± 4.9 months; range: 16-37 months), ECG monitoring was conducted for a period of 30 (±3) h. Parents were asked about their children's touchscreen media use and they rated their children's sleep quality. The use of touchscreen media predicted the physiologically determined quality of sleep but not parent-reported sleep quality (such as sleep onset latency). Greater heart rate differences between restless sleep phases and restful sleep indicated poorer nighttime recovery in children with more frequent use of touchscreen media. The study demonstrates that the expert analysis of the ECG during sleep is a potent tool for the estimation of sleep quality in toddlers.

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.

Estimating sleep stages using cardiorespiratory signals: validation of a novel algorithm across a wide range of sleep-disordered breathing severity

STUDY OBJECTIVES

We have developed the CardioRespiratory Sleep Staging (CReSS) algorithm for estimating sleep stages using heart rate variability and respiration, allowing for estimation of sleep staging during home sleep apnea tests. Our objective was to undertake an epoch-by-epoch validation of algorithm performance against the gold standard of manual polysomnography sleep staging.

METHODS

Using 296 polysomnographs, we created a limited montage of airflow and heart rate and deployed CReSS to identify each 30-second epoch as wake, light sleep (N1 + N2), deep sleep (N3), or rapid eye movement (REM) sleep. We calculated Cohen's kappa and the percentage of accurately identified epochs. We repeated our analyses after stratification by sleep-disordered breathing (SDB) severity, and after adding thoracic respiratory effort as a backup signal for periods of invalid airflow.

RESULTS

CReSS discriminated wake/light sleep/deep sleep/REM sleep with 78% accuracy; the kappa value was 0.643 (95% confidence interval, 0.641-0.645). Discrimination of wake/sleep demonstrated a kappa value of 0.711 and accuracy of 89%, non-REM sleep/REM sleep demonstrated a kappa of 0.790 and accuracy of 94%, and light sleep/deep sleep demonstrated a kappa of 0.469 and accuracy of 87%. Kappa values did not vary by more than 0.07 across subgroups of no SDB, mild SDB, moderate SDB, and severe SDB. Accuracy increased to 80%, with a kappa value of 0.680 (95% confidence interval, 0.678-0.682), when CReSS additionally utilized the thoracic respiratory effort signal.

CONCLUSIONS

We observed substantial agreement between CReSS and the gold-standard comparator of manual sleep staging of polysomnographic signals, which was consistent across the full range of SDB severity. Future research should focus on the extent to which CReSS reduces the discrepancy between the apnea-hypopnea index and the respiratory event index, and the ability of CReSS to identify REM sleep-related obstructive sleep apnea.

Automatic sleep staging using heart rate variability, body movements, and recurrent neural networks in a sleep disordered population

STUDY OBJECTIVES

To validate a previously developed sleep staging algorithm using heart rate variability (HRV) and body movements in an independent broad cohort of unselected sleep disordered patients.

METHODS

We applied a previously designed algorithm for automatic sleep staging using long short-term memory recurrent neural networks to model sleep architecture. The classifier uses 132 HRV features computed from electrocardiography and activity counts from accelerometry. We retrained our algorithm using two public datasets containing both healthy sleepers and sleep disordered patients. We then tested the performance of the algorithm on an independent hold-out validation set of sleep recordings from a wide range of sleep disorders collected in a tertiary sleep medicine center.

RESULTS

The classifier achieved substantial agreement on four-class sleep staging (wake/N1-N2/N3/rapid eye movement [REM]), with an average κ of 0.60 and accuracy of 75.9%. The performance of the sleep staging algorithm was significantly higher in insomnia patients (κ = 0.62, accuracy = 77.3%). Only in REM parasomnias, the performance was significantly lower (κ = 0.47, accuracy = 70.5%). For two-class wake/sleep classification, the classifier achieved a κ of 0.65, with a sensitivity (to wake) of 72.9% and specificity of 94.0%.

CONCLUSIONS

This study shows that the combination of HRV, body movements, and a state-of-the-art deep neural network can reach substantial agreement in automatic sleep staging compared with polysomnography, even in patients suffering from a multitude of sleep disorders. The physiological signals required can be obtained in various ways, including non-obtrusive wrist-worn sensors, opening up new avenues for clinical diagnostics.

Detecting sleep using heart rate and motion data from multisensor consumer-grade wearables, relative to wrist actigraphy and polysomnography

STUDY OBJECTIVES

Multisensor wearable consumer devices allowing the collection of multiple data sources, such as heart rate and motion, for the evaluation of sleep in the home environment, are increasingly ubiquitous. However, the validity of such devices for sleep assessment has not been directly compared to alternatives such as wrist actigraphy or polysomnography (PSG).

METHODS

Eight participants each completed four nights in a sleep laboratory, equipped with PSG and several wearable devices. Registered polysomnographic technologist-scored PSG served as ground truth for sleep-wake state. Wearable devices providing sleep-wake classification data were compared to PSG at both an epoch-by-epoch and night level. Data from multisensor wearables (Apple Watch and Oura Ring) were compared to data available from electrocardiography and a triaxial wrist actigraph to evaluate the quality and utility of heart rate and motion data. Machine learning methods were used to train and test sleep-wake classifiers, using data from consumer wearables. The quality of classifications derived from devices was compared.

RESULTS

For epoch-by-epoch sleep-wake performance, research devices ranged in d' between 1.771 and 1.874, with sensitivity between 0.912 and 0.982, and specificity between 0.366 and 0.647. Data from multisensor wearables were strongly correlated at an epoch-by-epoch level with reference data sources. Classifiers developed from the multisensor wearable data ranged in d' between 1.827 and 2.347, with sensitivity between 0.883 and 0.977, and specificity between 0.407 and 0.821.

CONCLUSIONS

Data from multisensor consumer wearables are strongly correlated with reference devices at the epoch level and can be used to develop epoch-by-epoch models of sleep-wake rivaling existing research devices.

Sleep Stage Estimation from Bed Leg Ballistocardiogram Sensors

Ballistocardiogram (BCG) is a graphical representation of the subtle oscillations in body movements caused by cardiovascular activity. Although BCGs cause less burden to the user, electrocardiograms (ECGs) are still commonly used in the clinical scene due to BCG sensors’ noise sensitivity. In this paper, a robust method for sleep time BCG measurement and a mathematical model for predicting sleep stages using BCG are described. The novel BCG measurement algorithm can be described in three steps: preprocessing, creation of heartbeat signal template, and template matching for heart rate variability detection. The effectiveness of this algorithm was validated with 99 datasets from 36 subjects, with photoplethysmography (PPG) to compute ground truth heart rate variability (HRV). On average, 86.9% of the inter-beat intervals were detected and the mean error was 8.5ms. This shows that our method successfully extracted beat-to-beat intervals from BCG during sleep, making its usability comparable to those of clinical ECGs. Consequently, compared to other conventional BCG systems, even more accurate sleep heart rate monitoring with a smaller burden to the patient is available. Moreover, the accuracy of the sleep stages mathematical model, validated with 100 datasets from 25 subjects, is 80%, which is higher than conventional five-stage sleep classification algorithms (max: 69%). Although, in this paper, we applied the mathematical model to heart rate interval features from BCG, theoretically, this sleep stage prediction algorithm can also be applied to ECG-extracted heart rate intervals.

Sleep stage prediction with raw acceleration and photoplethysmography heart rate data derived from a consumer wearable device

Wearable, multisensor, consumer devices that estimate sleep are now commonplace, but the algorithms used by these devices to score sleep are not open source, and the raw sensor data is rarely accessible for external use. As a result, these devices are limited in their usefulness for clinical and research applications, despite holding much promise. We used a mobile application of our own creation to collect raw acceleration data and heart rate from the Apple Watch worn by participants undergoing polysomnography, as well as during the ambulatory period preceding in lab testing. Using this data, we compared the contributions of multiple features (motion, local standard deviation in heart rate, and “clock proxy”) to performance across several classifiers. Best performance was achieved using neural nets, though the differences across classifiers were generally small. For sleep-wake classification, our method scored 90% of epochs correctly, with 59.6% of true wake epochs (specificity) and 93% of true sleep epochs (sensitivity) scored correctly. Accuracy for differentiating wake, NREM sleep, and REM sleep was approximately 72% when all features were used. We generalized our results by testing the models trained on Apple Watch data using data from the Multi-ethnic Study of Atherosclerosis (MESA), and found that we were able to predict sleep with performance comparable to testing on our own dataset. This study demonstrates, for the first time, the ability to analyze raw acceleration and heart rate data from a ubiquitous wearable device with accepted, disclosed mathematical methods to improve accuracy of sleep and sleep stage prediction.

The future of sleep health: a data-driven revolution in sleep science and medicine

In recent years, there has been a significant expansion in the development and use of multi-modal sensors and technologies to monitor physical activity, sleep and circadian rhythms. These developments make accurate sleep monitoring at scale a possibility for the first time. Vast amounts of multi-sensor data are being generated with potential applications ranging from large-scale epidemiological research linking sleep patterns to disease, to wellness applications, including the sleep coaching of individuals with chronic conditions. However, in order to realise the full potential of these technologies for individuals, medicine and research, several significant challenges must be overcome. There are important outstanding questions regarding performance evaluation, as well as data storage, curation, processing, integration, modelling and interpretation. Here, we leverage expertise across neuroscience, clinical medicine, bioengineering, electrical engineering, epidemiology, computer science, mHealth and human-computer interaction to discuss the digitisation of sleep from a inter-disciplinary perspective. We introduce the state-of-the-art in sleep-monitoring technologies, and discuss the opportunities and challenges from data acquisition to the eventual application of insights in clinical and consumer settings. Further, we explore the strengths and limitations of current and emerging sensing methods with a particular focus on novel data-driven technologies, such as Artificial Intelligence.

Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features

Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70%). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.

Protocol of the SOMNIA project: an observational study to create a neurophysiological database for advanced clinical sleep monitoring

INTRODUCTION

Polysomnography (PSG) is the primary tool for sleep monitoring and the diagnosis of sleep disorders. Recent advances in signal analysis make it possible to reveal more information from this rich data source. Furthermore, many innovative sleep monitoring techniques are being developed that are less obtrusive, easier to use over long time periods and in the home situation. Here, we describe the methods of the Sleep and Obstructive Sleep Apnoea Monitoring with Non-Invasive Applications (SOMNIA) project, yielding a database combining clinical PSG with advanced unobtrusive sleep monitoring modalities in a large cohort of patients with various sleep disorders. The SOMNIA database will facilitate the validation and assessment of the diagnostic value of the new techniques, as well as the development of additional indices and biomarkers derived from new and/or traditional sleep monitoring methods.

METHODS AND ANALYSIS

We aim to include at least 2100 subjects (both adults and children) with a variety of sleep disorders who undergo a PSG as part of standard clinical care in a dedicated sleep centre. Full-video PSG will be performed according to the standards of the American Academy of Sleep Medicine. Each recording will be supplemented with one or more new monitoring systems, including wrist-worn photoplethysmography and actigraphy, pressure sensing mattresses, multimicrophone recording of respiratory sounds including snoring, suprasternal pressure monitoring and multielectrode electromyography of the diaphragm.

ETHICS AND DISSEMINATION

The study was reviewed by the medical ethical committee of the Maxima Medical Center (Eindhoven, the Netherlands, File no: N16.074). All subjects provide informed consent before participation.The SOMNIA database is built to facilitate future research in sleep medicine. Data from the completed SOMNIA database will be made available for collaboration with researchers outside the institute.

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.

Brain wave classification using long short-term memory network based OPTICAL predictor

Brain-computer interface (BCI) systems having the ability to classify brain waves with greater accuracy are highly desirable. To this end, a number of techniques have been proposed aiming to be able to classify brain waves with high accuracy. However, the ability to classify brain waves and its implementation in real-time is still limited. In this study, we introduce a novel scheme for classifying motor imagery (MI) tasks using electroencephalography (EEG) signal that can be implemented in real-time having high classification accuracy between different MI tasks. We propose a new predictor, OPTICAL, that uses a combination of common spatial pattern (CSP) and long short-term memory (LSTM) network for obtaining improved MI EEG signal classification. A sliding window approach is proposed to obtain the time-series input from the spatially filtered data, which becomes input to the LSTM network. Moreover, instead of using LSTM directly for classification, we use regression based output of the LSTM network as one of the features for classification. On the other hand, linear discriminant analysis (LDA) is used to reduce the dimensionality of the CSP variance based features. The features in the reduced dimensional plane after performing LDA are used as input to the support vector machine (SVM) classifier together with the regression based feature obtained from the LSTM network. The regression based feature further boosts the performance of the proposed OPTICAL predictor. OPTICAL showed significant improvement in the ability to accurately classify left and right-hand MI tasks on two publically available datasets. The improvements in the average misclassification rates are 3.09% and 2.07% for BCI Competition IV Dataset I and GigaDB dataset, respectively. The Matlab code is available at https://github.com/ShiuKumar/OPTICAL .

Sinus or not: a new beat detection algorithm based on a pulse morphology quality index to extract normal sinus rhythm beats from wrist-worn photoplethysmography recordings

OBJECTIVE

Wrist-worn photoplethysmography (PPG) can enable free-living physiological monitoring of people during diverse activities, ranging from sleep to physical exercise. In many applications, it is important to remove the pulses not related to sinus rhythm beats from the PPG signal before using it as a cardiovascular descriptor. In this manuscript, we propose an algorithm to assess the morphology of the PPG signal in order to reject non-sinus rhythm pulses, such as artefacts or pulses related to arrhythmic beats.

APPROACH

The algorithm segments the PPG signal into individual pulses and dynamically evaluates their morphological likelihood of being normal sinus rhythm pulses via a template-matching approach that accounts for the physiological variability of the signal. The normal sinus rhythm likelihood of each pulse is expressed as a quality index that can be employed to reject artefacts and pulses related to arrhythmic beats.

MAIN RESULTS

Thresholding the pulse quality index enables near-perfect detection of normal sinus rhythm beats by rejecting most of the non-sinus rhythm pulses (positive predictive value 98%-99%), both in healthy subjects and arrhythmic patients. The rejection of arrhythmic beats is almost complete (sensitivity to arrhythmic beats 7%-3%), while the sensitivity to sinus rhythm beats is not compromised (96%-91%).

SIGNIFICANCE

The developed algorithm consistently detects normal sinus rhythm beats in a PPG signal by rejecting artefacts and, as a first of its kind, arrhythmic beats. This increases the reliability in the extraction of features which are adversely influenced by the presence of non-sinus pulses, whether related to inter-beat intervals or to pulse morphology, from wrist-worn PPG signals recorded in free-living conditions.