Snoring Events Research Articles

Automated sleep apnea detection from snoring and carotid pulse signals using an innovative neck wearable piezoelectric sensor

This study introduces an innovative wearable neck piezoelectric sensor (NPS) that measures snoring vibrations and carotid pulsations, offering a significant advancement in sleep apnea syndrome (SAS) diagnosis. Utilizing advanced algorithms like discrete wavelet transform and dynamic thresholding, the NPS detects snoring events with 83% accuracy, comparable to polysomnography, and calculates key metrics such as the snoring index (SI) and normalized snoring vibration energy (SVE%). Unlike traditional methods, the SVE% from NPS directly correlates with subjective assessments of snoring severity. It also measures carotid pulsation metrics such as pulse rate and the standard deviation of normal-to-normal intervals, achieving 85% accuracy in sleep phase determination against polysomnography. Moreover, NPS surpasses traditional methods in SI and SVE% accuracy, closely aligning with clinical evaluations of SAS severity. This user-friendly technology automates the measurement of critical snoring metrics, transforming SAS diagnosis and treatment by enhancing accessibility and efficiency for healthcare providers and patients.

A smart detection method for sleep posture based on a flexible sleep monitoring belt and vital sign signals

People spend approximately one-third of their lives in sleep, but more and more people are suffering from sleep disorders. Sleep posture is closely related to sleep quality, so related detection is very significant. In our previous work, a smart flexible sleep monitoring belt with MEMS triaxial accelerometer and pressure sensor has been developed to detect the vital signs, snore events and sleep stages. However, the method for sleep posture detection has not been studied. Therefore, to achieve high performance, low cost and comfortable experience, this paper proposes a smart detection method for sleep posture based on a flexible sleep monitoring belt and vital sign signals measured by a MEMS Inertial Measurement Unit (IMU). Statistical analysis and wavelet packet transform are applied for the feature extraction of the vital sign signals. Then the algorithm of recursive feature elimination with cross-validation is introduced to further extract the key features. Besides, machine learning models with 10-fold cross validation process, such as decision tree, random forest, support vector machine, extreme gradient boosting and adaptive boosting, were adopted to recognize the sleep posture. 15 subjects were recruited to participate the experiment. Experimental results demonstrate that the detection accuracy of the random forest algorithm is the highest among the five machine learning models, which reaches 96.02 %. Therefore, the proposed sleep posture detection method based on the flexible sleep monitoring belt is feasible and effective.

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-Snoring Sound Events

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-Snoring Sound Events

A multi-branch convolutional neural network for snoring detection based on audio

Obstructive sleep apnea (OSA) is associated with various health complications, and snoring is a prominent characteristic of this disorder. Therefore, the exploration of a concise and effective method for detecting snoring has consistently been a crucial aspect of sleep medicine. As the easily accessible data, the identification of snoring through sound analysis offers a more convenient and straightforward method. The objective of this study was to develop a convolutional neural network (CNN) for classifying snoring and non-snoring events based on audio. This study utilized Mel-frequency cepstral coefficients (MFCCs) as a method for extracting features during the preprocessing of raw data. In order to extract multi-scale features from the frequency domain of sound sources, this study proposes the utilization of a multi-branch convolutional neural network (MBCNN) for the purpose of classification. The network utilized asymmetric convolutional kernels to acquire additional information, while the adoption of one-hot encoding labels aimed to mitigate the impact of labels. The experiment tested the network’s performance by utilizing a publicly available dataset consisting of 1,000 sound samples. The test results indicate that the MBCNN achieved a snoring detection accuracy of 99.5%. The integration of multi-scale features and the implementation of MBCNN, based on audio data, have demonstrated a substantial improvement in the performance of snoring classification.

SLEEP-SEE-THROUGH: Explainable Deep Learning for Sleep Event Detection and Quantification From Wearable Somnography.

Evidence is rapidly accumulating that multifactorial nocturnal monitoring, through the coupling of wearable devices and deep learning, may be disruptive for early diagnosis and assessment of sleep disorders. In this work, optical, differential air-pressure and acceleration signals, acquired by a chest-worn sensor, are elaborated into five somnographic-like signals, which are then used to feed a deep network. This addresses a three-fold classification problem to predict the overall signal quality (normal, corrupted), three breathing-related patterns (normal, apnea, irregular) and three sleep-related patterns (normal, snoring, noise). In order to promote explainability, the developed architecture generates additional information in the form of qualitative (saliency maps) and quantitative (confidence indices) data, which helps to improve the interpretation of the predictions. Twenty healthy subjects enrolled in this study were monitored overnight for approximately ten hours during sleep. Somnographic-like signals were manually labeled according to the three class sets to build the training dataset. Both record- and subject-wise analyses were performed to evaluate the prediction performance and the coherence of the results. The network was accurate (0.96) in distinguishing normal from corrupted signals. Breathing patterns were predicted with higher accuracy (0.93) than sleep patterns (0.76). The prediction of irregular breathing was less accurate (0.88) than that of apnea (0.97). In the sleep pattern set, the distinction between snoring (0.73) and noise events (0.61) was less effective. The confidence index associated with the prediction allowed us to elucidate ambiguous predictions better. The saliency map analysis provided useful insights to relate predictions to the input signal content. While preliminary, this work supported the recent perspective on the use of deep learning to detect particular sleep events in multiple somnographic signals, thus representing a step towards bringing the use of AI-based tools for sleep disorder detection incrementally closer to clinical translation.

0373 Association of U.S. Military Burn Pit Smoke Exposure with Insomnia and Sleep Apnea Symptoms

Abstract Introduction Burn pits (BPs) have been widely used by the U.S. military for waste disposal. Due to the obviously toxic nature of the BP emissions, exposure may contribute to diverse adverse health conditions, including sleep apnea. To our knowledge, this is the first study to examine the association between self-estimated amount of BP emission exposure and self-reported sleep complaints. Methods We used an online health questionnaire of the VA/DoD Airborne Hazards and Open Burn Pit Registry administered between April 2014 and August 2022 to 320,231 Veterans and active-duty personnel (age 40.1±9.2 years, BMI 28.8±4.5 kg/m2, 11% female, 75% white). Outcomes included insomnia, short sleep duration < 6hrs, sleep apnea events, and snoring. The exposure variable was cumulative BP exposure that was calculated by multiplying the response (in hours) to a question about burn pit exposure by number of deployment days, summing across deployments, and categorizing by quartile. We employed separate logistic regression models to determine the association between cumulative BP exposure days and sleep outcomes using no BP exposure as the reference. We adjusted the models by age, BMI, sex, race, ethnicity, military branch and duty status. Results We observed higher odds of insomnia as the duration of BP exposure increased in each quartile (Q1-Q4 ORs:1.8-3.4, p<.001). The same trend was observed for shorter sleep duration (Q1-Q4 ORs:1.6-2.4, p<.001), sleep apnea (Q1-Q4 ORs:1.4-2.4, p<.0001) and snoring (Q1-Q4 ORs:1.3-1.8, p<.0001). Conclusion Higher levels of BP emission exposure was associated with a greater report of insomnia symptoms, shorter sleep duration, snoring and sleep apnea events. Future research will focus on examining the association of BP emission ­exposure and objective sleep data extracted from polysomnography reports in the Veteran Affairs electronic medical records. Support (if any) This work is supported by the Department of Veteran Affairs, Veterans Health Administration, Office of Research and Development, and the Center for Innovations in Quality, Effectiveness and Safety (CIN 13-413), Michael E DeBakey Veteran Affairs Medical Center Bridge Grant (PI: Nowakowski), and the VA Airborne Hazards and Burn Pit Center of Excellence Pilot Grant (PI: Nowakowski).

0377 Sleep Health Disparities Among U.S. Military Personnel and Veterans Registered on the Burn Pit Registry

Abstract Introduction Disparities are underrecognized factors for sleep health. Additionally, there are concerns about sleep health among Veterens with exposure to burn pit smoke. This study aimed to examine the association between sex, race, and ethnicity and self-reported insomnia and sleep apnea symptoms in Veterans and active duty personnel. Methods Using items from the online health questionnaire of the VA/DoD Airborne Hazards and Open Burn Pit Registry administered between April 2014 and August 2022 to 320,231 Veterans and active duty personnel (age 40.1±9.2 y, 11% female, 75% white), we examined the association between sociodemographic variables (sex, race, and ethnicity) and self-reported sleep complaints (insomnia, sleep duration, sleep apnea events and snoring) in separate logistic regression models. Results Female sex predicted higher odds of insomnia (OR 1.3), where as male sex predicted higher odds of sleep apnea events (OR 2.6) and snoring (OR 2.4), p’s<.0001. African American race predicted higher odds of sleep apnea events, snoring, insomnia and shorter sleep duration (ORs1.5-3.2, p’s<.0001). Hispanic ethnicity predicted higher odds of sleep apnea events, snoring, insomnia and shorter sleep duration (ORs 1.2-1.6, p’s<.0001). Conclusion We observed a higher prevalence of self-reported sleep complaints among Black and Hispanic compared to White Veterans and active duty personnel who completed the burn pit registry. We also found a higher prevalence of insomnia in females compared to males, while snoring and sleep apnea events were more common in males compared to females. Future research will focus on sleep health dispartities of objective sleep data extracted from polysomnography reports in the Veteran Affairs electronic medical records in Veterans on the burn pit registry. Support (if any) This work is supported by the Department of Veteran Affairs, Veterans Health Administration, Office of Research and Development, Center for Innovations in Quality, Effectiveness and Safety (CIN 13-413); Michael E DeBakey VAMC Bridge Grant (PI: Nowakowski); and VA Airborne Hazards and Burn Pit Center of Excellence Pilot Grant (PI:Nowakowski).

Auditory Receptive Field Net Based Automatic Snore Detection for Wearable Devices.

Although obstructive sleep apnea and hypopnea syndrome (OSAHS) is a common sleep disease, it is sometimes difficult to be detected in time because of the inconvenience of polysomnography (PSG) examination. Since snoring is one of the earliest symptoms of OSAHS, it can be used for early OSAHS prediction. With the recent development of wearable and IoT sensors, we proposed a deep learning-based accurate snore detection model for long-term home monitoring of snoring during sleep. To enhance the discriminability of features between snoring and non-snoring events, an auditory receptive field (ARF) net was proposed and integrated into the feature extraction network. Based on the feature maps derived by the feature extraction network, the detection model predicted a series of candidate boxes and corresponding confidence scores for each candidate box, which denoted whether the candidate box contained a snore event from the input sound waveforms. A snore detection dataset with a total duration of more than 4600 min was developed to evaluate the proposed model. The experimental results on this dataset revealed that the proposed model outperformed other traditional approaches and deep learning models.

Design of embedded real-time system for snoring and OSA detection based on machine learning

Obstructive sleep apnea (OSA) is a common sleep disorder. As a gold standard to detect OSA, the polysomnography (PSG) is widely used. However, the acquisition of nighttime PSG signals is very inconvenient. Compared to PSG, snoring-based OSA detection is low-cost, convenient and non-invasive. In this work, the apnea situation is studied based on the nighttime snoring signals to detect OSA. Firstly, a nighttime audio database regarding snoring sounds is built by the multi-threshold endpoint detection from original night recordings. Next, feature extraction is carried out on the segregated sound signals to obtain the characteristic information of snoring. Then, feature categories are predicted based on the machine learning models. The proposed algorithm is transplanted to the embedded device to build a real-time system which can detect snoring and OSA events. The study experiments with a variety of detection schemes and finally trains a multi-classification temporal convolutional network (TCN) to classify night audio as non-snoring, snoring or OSA-related snoring. The experiment results have achieved good performance that the detection accuracy of OSA-related snoring is up to 96.7 %. In order to further promote this method, the trained TCN model is transplanted to an embedded device to detect snoring and OSA events using as a real-time system. The experimental results fully show that the proposed detection scheme can achieve high accuracy for the detection of snoring and OSA events, which demonstrates that it can be used a new tool to conveniently help potential OSA patients understand their sleep health for home health care.

Effects of demographic and sleep-related factors on snoring sound parameters

ObjectiveTo investigate the effect of frequently reported between-individual (viz., age, gender, body mass index [BMI], and apnea-hypopnea index [AHI]) and within-individual (viz., sleep stage and sleep position) snoring sound-related factors on snoring sound parameters in temporal, intensity, and frequency domains. MethodsThis study included 83 adult snorers (mean ± SD age: 42.2 ± 11.3 yrs; male gender: 59%) who underwent an overnight polysomnography (PSG) and simultaneous sound recording, from which a total of 131,745 snoring events were extracted and analyzed. Data on both between-individual and within-individual factors were extracted from the participants’ PSG reports. ResultsGender did not have any significant effect on snoring sound parameters. The fundamental frequency (FF; coefficient = −0.31; P = 0.02) and dominant frequency (DF; coefficient = −12.43; P < 0.01) of snoring sounds decreased with the increase of age, and the second formant increased (coefficient = 22.91; P = 0.02) with the increase of BMI. Severe obstructive sleep apnea (OSA; AHI ≥30 events/hour), non-rapid eye movement sleep stage 3 (N3), and supine position were all associated with more, longer, and louder snoring events (P < 0.05). Supine position was associated with higher FF and DF, and lateral decubitus positions were associated with higher formants. ConclusionsWithin the limitations of the current patient profile and included factors, AHI was found to have greater effects on snoring sound parameters than the other between-individual factors. The included within-individual factors were found to have greater effects on snoring sound parameters than the between-individual factors under study.

Screening the risk of obstructive sleep apnea by utilizing supervised learning techniques based on anthropometric features and snoring events.

Obstructive sleep apnea (OSA) is typically diagnosed by polysomnography (PSG). However, PSG is time-consuming and has some clinical limitations. This study thus aimed to establish machine learning models to screen for the risk of having moderate-to-severe and severe OSA based on easily acquired features. We collected PSG data on 3529 patients from Taiwan and further derived the number of snoring events. Their baseline characteristics and anthropometric measures were obtained, and correlations among the collected variables were investigated. Next, six common supervised machine learning techniques were utilized, including random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (kNN), support vector machine (SVM), logistic regression (LR), and naïve Bayes (NB). First, data were independently separated into a training and validation dataset (80%) and a test dataset (20%). The approach with the highest accuracy in the training and validation phase was employed to classify the test dataset. Next, feature importance was investigated by calculating the Shapley value of every factor, which represented the impact on OSA risk screening. The RF produced the highest accuracy (of >70%) in the training and validation phase in screening for both OSA severities. Hence, we employed the RF to classify the test dataset, and results showed a 79.32% accuracy for moderate-to-severe OSA and 74.37% accuracy for severe OSA. Snoring events and the visceral fat level were the most and second most essential features of screening for OSA risk. The established model can be considered for screening for the risk of having moderate-to-severe or severe OSA.

A Novel Snore Detection and Suppression Method for a Flexible Patch With MEMS Microphone and Accelerometer

Sleep apnea impacts more and more people all over the world, and obstructive sleep apnea of which is the most frequent. Hence, research on snoring detection and related suppression methods is extremely urgent. In this article, a novel low-cost flexible patch with MEMS microphone and accelerometer is developed to detect snore event and sleeping posture, and a small vibration motor embedded in the patch is designed to suppress snoring. Theoretical analyses of short-time energy, piecewise average filtering (PAF), and Mel-frequency cepstral coefficients (MFCCs) processing are described in detail, and the improved MFCCs are put forward and used as the input of the convolutional neural network (CNN). Furthermore, the snore recognition method based on the combination of similarity analysis and CNN analysis is presented, followed by the snoring suppression method. Experimental results demonstrate that the main features of the sound signals can be extracted effectively by PAF and MFCCs processing, and the data compression ratio is about 99.41%. Besides, the locations of the eigenvectors can be found accurately based on short-time energy analysis. The numbers of high similarity of snoring signals within 30 s are larger than 3, while those of non-snoring signals are often less than 3. If the preliminary screening with similarity analysis is passed, CNN analysis will be conducted to judge whether there are snoring events. The accuracy of snore recognition with CNN analysis is calculated to be as high as 99.25%. Finally, the average snoring time measured by the smart patch with snoring suppression is reduced to 15 from 135 min, which indicates that the proposed snore recognition and suppression methods are effective.

A Smart Flexible Vital Signs and Sleep Monitoring Belt Based on MEMS Triaxial Accelerometer and Pressure Sensor

People spend about one third of their lifetime in sleep, and sleep quality has a great impact on people’s health. Therefore, vital signs and sleep quality monitoring are more and more important. In this article, a novel smart flexible sleep monitoring belt with MEMS triaxial accelerometer and pressure sensor is developed to detect vital signs, snore events, and sleep stages. Besides, the related algorithms and methods for data preprocessing, heart and respiration rates detection, snoring recognition, and sleep stages classification are proposed in detail. Then, a series of sleep experiments is performed based on the experimental platform for the smart flexible belt, and the test results measured by PolySomnoGraphy are used as the golden standards for comparison. The experimental results demonstrate that the detection accuracies of heart rate and respiration rate of the belt are about 1.5 and 0.7 bpm, respectively. The accuracy of 97.2% is achieved by the proposed snoring recognition method. In addition, as for 2-stage analysis, the sensitivities of awake and asleep stages are 90.2% and 100%, respectively; meanwhile, the corresponding accuracy of sleep stages prediction is as high as 95.1%. However, as for 4-stage analysis, the sensitivities of awake, rapid eye movement, light sleep, and deep sleep stages are 90.2%, 77.1%, 78.1%, and 73.5%, respectively; meanwhile, the corresponding accuracy of sleep stages prediction decreases to 79.7%. In general, the test results indicate that vital signs detection, snoring recognition, and sleep stages classification based on the sleep monitoring belt are feasible and effective. Hence, this smart flexible belt can be widely used for sleep monitoring at home due to low cost and high performance.

Automatic Identification of Snoring and Groaning Segments in Acoustic Recordings.

Sleep-related breathing disorders have severe impact on the quality of lives of those suffering from them. These disorders present with a variety of symptoms, out of which snoring and groaning are very common. This paper presents an algorithm to identify and classify segments of acoustic respiratory sound recordings that contain both groaning and snoring events. The recordings were obtained from a database containing 20 subjects from which features based on the Mel-frequency cepstral coefficients (MFCC) were extracted. In the first stage of the algorithm, segments of recordings consisting of either snoring or groaning episodes - without classifying them - were identified. In the second stage, these segments were further differentiated into individual groaning or snoring events. The algorithm in the first stage achieved a sensitivity and specificity of 90.5% ±2.9% and 90.0% ±1.6% respectively, using a RUSBoost model. In the second stage, a random forest classifier was used, and the accuracies for groan and snore events were 78.1% ±4.7% and 78.4% ±4.7% respectively.

Toward Sleep Study Automation: Detection Evaluation of Respiratory-Related Events.

The diagnosis of sleep disordered breathing depends on the detection of respiratory-related events: apneas, hypopneas, snores, or respiratory event-related arousals from sleep studies. While a number of automatic detection methods have been proposed, their reproducibility has been an issue, in part due to the absence of a generally accepted protocol for evaluating their results. With sleep measurements this is usually treated as a classification problem and the accompanying issue of localization is not treated as similarly critical. To address these problems we present a detection evaluation protocol that is able to qualitatively assess the match between two annotations of respiratory-related events. This protocol relies on measuring the relative temporal overlap between two annotations in order to find an alignment that maximizes their F1-score at the sequence level. This protocol can be used in applications which require a precise estimate of the number of events, total event duration, and a joint estimate of event number and duration. We assess its application using a data set that contains over 10,000 manually annotated snore events from 9 subjects, and show that when using the American Academy of Sleep Medicine Manual standard, two sleep technologists can achieve an F1-score of 0.88 when identifying the presence of snore events. In addition, we drafted rules for marking snore boundaries and showed that one sleep technologist can achieve F1-score of 0.94 at the same tasks. Finally, we compared this protocol against the protocol that is used to evaluate sleep spindle detection and highlighted the differences.

Definition of the snoring episode index based on the analyses of snoring parameters and the apnea hypopnea index

Although snoring is the most common subjective symptom in obstructive sleep apnea (OSA), an international consensus on the definition of snoring is lacking. This study aimed to define snoring by analyzing correlations between snoring parameters and the apnea hypopnea index (AHI). We retrospectively analyzed the polysomnography data of patients with OSA. A snoring event was defined when airflow pressure was > 200 microbar. We included four snoring parameters. Snoring percentage was defined as the cumulative time of snoring events divided by total sleep time. A snoring episode was defined as the occurrence of ≥ 3 consecutive snoring events, and the snoring episode index was defined as the number of snoring episodes per hour. The average and longest durations of snoring episodes were also investigated. The study enrolled 5035 patients. Their mean AHI was 26.5/h and the mean snoring episode index was 19.2/h. Although the four snoring parameters showed significant correlations with the AHI, the snoring episode index showed the strongest positive correlation with the AHI (r = 0.741, P < 0.001). The snoring episode index may be used as a definition of snoring from the perspective of a highly positive correlation with the AHI.

Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in patients with obstructive sleep apnea: a prospective clinical study.

The primary aim was to predict upper airway collapse sites found in drug-induced sleep endoscopy (DISE) from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with obstructive sleep apnea (OSA). The secondary aim was to identify the above-mentioned parameters that are associated with complete concentric collapse of the soft palate. All patients with OSA who underwent DISE and simultaneous snoring sound recording were enrolled in this study. Demographic, anthropometric, clinical examination (viz., modified Mallampati classification and Friedman tonsil classification), and sleep study parameters were extracted from the polysomnography and DISE reports. Snoring sound parameters during DISE were calculated. One hundred and nineteen patients with OSA (79.8% men; age = 48.1 ± 12.4 years) were included. Increased body mass index was found to be associated with higher probability of oropharyngeal collapse (P < .01; odds ratio = 1.29). Patients with a high Friedman tonsil score were less likely to have tongue base collapse (P < .01; odd ratio = 0.12) and epiglottic collapse (P = .01; odds ratio = 0.20) than those with a low score. A longer duration of snoring events (P = .05; odds ratio = 2.99) was associated with a higher probability of complete concentric collapse of the soft palate. Within the current patient profile and approach, given that only a limited number of predictors were identified, it does not seem feasible to predict upper airway collapse sites found in DISE from demographic, anthropometric, clinical examination, sleep study, and snoring sound parameters in patients with OSA. Huang Z, Bosschieter PFN, Aarab G, etal. Predicting upper airway collapse sites found in drug-induced sleep endoscopy from clinical data and snoring sounds in obstructive sleep apnea patients: a prospective clinical study. J Clin Sleep Med. 2022;18(9):2119-2131.

Sleep Complaints Among School Children.

Sleep complaints are common among children. These include both night-time and daytime symptoms, such as trouble falling asleep, problems in maintaining sleep, snoring, and unusual events during sleep and daytime functioning impairment. However, sleep complaints in children are often overlooked and undertreated in clinical practice. Untreated sleep problems may further impact on children's development and will persist into adulthood in some cases. This review summarizes the common sleep complaints and disorders in school children, and provides an overview of the epidemiology, clinical features, consequences, and treatment of the sleep problems.

When adherence to CPAP fails, how do we treat workers with obstructive sleep apnea?

AimsA cross-sectional study was designed to evaluate the effectiveness of a mandibular advancement device (MAD) with respect to respiratory and sleep parameters among miners with obstructive sleep apnea syndrome (OSAS) and primary snore.MethodsThe target sample was composed by 102 Brazilian miners with a history of non-adherence to continuous positive airway pressure. All patients were treated with a MAD and underwent pre and post-treatment full-night polysomnography. Ethical approval and consents were obtained. Bivariate and logistic regression analyses were conducted. The level of statistical significance was set at 5%.ResultsAfter the treatment with MAD, 71.8% of patients presented a decrease ≥ 50% in the basal apnea-hypopnea index (AHI), 51.2% presented an AHI < 5 events/h and 83.3% reached an AHI<10/h, whereas 22.5% did not show any changes and 7.5% of the sample presented an increase in the AHI (p<0.05). There was an increase in the mean SpO2 nadir (p<0.001) and in the baseline duration of the REM sleep stage (p<0.05). The MAD significantly decreased snore events (p<0.05). Multivariate analysis did not identify predictive factors related to therapy success (decrease ≥ 50% of AHI). However, basal AHI was a significant predictor related to the secondary endpoint (AHI<10/h) (OR= 1.06, IC 95%1.00-1.13, p=0.007).ConclusionsThe MAD therapy showed significant improvements in AHI, minimum oxygen saturation, REM sleep and snoring.

Consumer Smartwatches As a Portable PSG: LSTM Based Neural Networks for a Sleep-Related Physiological Parameters Estimation.

Recently, mobile and wearable devices have become an increasingly integral part of our lives. They provide a possibility of detailed health monitoring using noninvasive and user-friendly techniques. However, lack of continuous monitoring, the need of specific sensors, and the limitations in memory and power consumption are only some of the potential drawbacks of such devices. In the current paper a system based on a deep recurrent neural network is developed for an automatic continuous monitoring of sleep-related physiological parameters by means of a wearable biosignal monitoring systems. Smartwatches based algorithm for non-invasive monitoring of sleep stages, respiratory events (including sleep apnea and hypopnea), snore and blood oxygen saturation is developed. Our experimental results demonstrate that proposed model constitutes a noninvasive and inexpensive screening system for sleep-related physiological parameters and pathological states. The model has shown a 77 % accuracy in sleep stages prediction, more than 80 % accuracy in epoch-by-epoch respiratory events classification, above 60 % accuracy in snore events classification and above 70 % accuracy in blood oxygen saturation (SpO2) level classification (for a two class problem with a SpO2 threshold of 95 %).