Robust, ECG-based detection of Sleep-disordered breathing in large population-based cohorts

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSION

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

Effects of sleep-disordered breathing on serum lipid levels in children:a case control study

BACKGROUND

Sleep-disordered breathing (SDB) during childhood is common and includes a range of breathing abnormalities that range from primary snoring (PS) to obstructive sleep apnea syndrome (OSAS).Studies have shown that not only OSAS, but also PS, which is originally considered harmless, could cause cardiovascular, cognitive, behavioral, and psychosocial problems. Many researches are focused on the relation of OSA and serum lipid levels. However, little studies are focused on PS and serum lipid levels in children.We evaluated whether serum lipid (total cholesterol (TC), triglyceride (TG), high-density lipoprotein cholesterol (HDL-C),low-density lipoprotein cholesterol (LDL-C)) concentrations were associated with specific components of SDB, including indices of oxygen reduction index, lowest oxygen saturation, mean oxygen saturation. And we explored whether serum lipid levels were associated with different degree sleep disordered (PS and OSA group) and obese.

METHODS

This was a cross-sectional study. Children who were complained by their guardians with habitual snoring and(or) mouth breathing were collected in the SDB group. Normal children without sleep problem were matched in the control group. Subjects in the SDB group underwent polysomnography. The serum lipid profiles of all the children included TC, TG, HDL-C and LDL-C concentrations were measured by appropriate enzymatic assays.

RESULTS

A total of 241 with Apnea/Hypopnea Index ≥ 5 (AHI) were assigned to the OSAS group and the remaining 155 with normal AHI were assigned to the PS group. The values of TC, TG, LDL-C and LDL/HDL were significantly higher in the OSAS group than in the PS group, and the values in the PS group were significantly higher than the control group. Multiple regression analysis revealed serum TG only correlated negatively with lowest oxygen saturation. Body mass index-z score has a positive effect on TG in all the 1310 children (P = 0.031) and in SDB 396 children(P = 0.012). The level of serum TG in obese group was significantly higher than that in non-obese group.

CONCLUSIONS

SDB had a very obvious effect on blood lipids, whereas PS without apnea and hypoxia. Obese only affects the aggregation of TG.

TRIAL REGISTRATION

ChiCTR1900026807(2019.10.23).

Scanning of obstructive sleep apnea syndrome using smartwatch: A comparison of smartwatch and polysomnography

BACKGROUND

Obstructive Sleep Apnea Syndrome (OSAS), which significantly impairs nighttime sleep quality and causes excessive daytime sleepiness, not only reduces the quality of life of patients, but also increases the social and socioeconomic burden. Wearable-noninvasive devices can provide faster OSAS screening and follow-up. Smartwatches as an objective, non-invasive, practical and relatively inexpensive method, they are attractive candidates for pre-evaluation of OSAS and referral to a physician. In this study, it was aimed to evaluate the effectiveness of a smart watch in detecting OSAS findings compared to the gold standard polysomnograhy (PSG).

METHODS

PSG data of the study group were compared with data such as SpO2, heart rate and saturation obtained by smartwatch from both sides, and the Cohen's kappa was used to measure for two methods and predictive values were evaluated.

RESULTS

A total of 115 participants [44 female (38.3%), mean age (SD): 49.24 (11.39)] were enrolled. 75 (65.22%) of the participants were diagnosed with OSAS, of which 29 (25.22%) participants have severe OSAS. The smartwatch showed good sensitivity (75% to 96%), specificity (79% to 91%), and diagnostic accuracy (AUC: 0.84 to 0.93) in predicting apnea and severe apnea, respectively. The highest agreement between PSG and smartwatch and the diagnostic ability of smartwatch were found in persons with severe OSAS.

CONCLUSION

The high PPV-NPV values in our study and the good compatibility coefficient of the smart watch with the PSG device can contribute to the expansion of the usage areas of smart watches that come into the lives of many people in daily practice.

Prediction of the Sleep Apnea Severity Using 2D-Convolutional Neural Networks and Respiratory Effort Signals

The high prevalence of sleep apnea and the limitations of polysomnography have prompted the investigation of strategies aimed at automated diagnosis using a restricted number of physiological measures. This study aimed to demonstrate that thoracic (THO) and abdominal (ABD) movement signals are useful for accurately estimating the severity of sleep apnea, even if central respiratory events are present. Thus, we developed 2D-convolutional neural networks (CNNs) jointly using THO and ABD to automatically estimate sleep apnea severity and evaluate the central event contribution. Our proposal achieved an intraclass correlation coefficient (ICC) = 0.75 and a root mean square error (RMSE) = 10.33 events/h when estimating the apnea-hypopnea index, and ICC = 0.83 and RMSE = 0.95 events/h when estimating the central apnea index. The CNN obtained accuracies of 94.98%, 79.82%, and 81.60% for 5, 15, and 30 events/h when evaluating the complete apnea hypopnea index. The model improved when the nature of the events was central: 98.72% and 99.74% accuracy for 5 and 15 events/h. Hence, the information extracted from these signals using CNNs could be a powerful tool to diagnose sleep apnea, especially in subjects with a high density of central apnea events.

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

BACKGROUND

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

METHOD

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

RESULT

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

CONCLUSION

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

Systematic review of automated sleep apnea detection based on physiological signal data using deep learning algorithm: a meta-analysis approach

Sleep apnea (SLA) is a respiratory-related sleep disorder that affects a major proportion of the population. The gold standard in sleep testing, polysomnography, is costly, inconvenient, and unpleasant, and it requires a skilled professional to score. Multiple researchers have suggested and developed automated scoring processes with less detectors and automated classification algorithms to resolve these problems. An automatic detection system will allow for a high diagnosis rate and the analysis of additional patients. Deep learning (DL) is achieving high priority due to the availability of databases and recently developed methods. As the most up-and-coming technique for classification and generative tasks, DL has shown its significant potential in 2-dimensional clinical image processing studies. However, physiological information collected as 1-dimensional data has yet to be effectively extracted from this new approach to achieve the needed medical goals. So, in this study, we review the most recent studies in the field of DL applied to physiological data based on pulse oxygen saturation, electrocardiogram, airflow, and sound signal. A total of 47 articles from different journals and publishing houses that were published between 2012 and 2022 were identified. The primary objective of this work is to perform a comprehensive analysis to analyze, classify, and compare the main characteristics of deep-learning algorithms applied in physiological data processing for SLA detection. Overall, our analysis provides comprehensive and detailed information for researchers looking to add to this field. The data input source, objective, DL network, training framework, and database references are the critical factors of the DL approach examined. These are the most critical variables that influence system performance. We categorized the relevant research studies in physiological sensor data analysis using the DL approach based on (1) Physiological sensor data aspects, like signal types, sampling frequency, and window size; and (2) DL model perspectives, such as learning structure and input data types.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-023-00297-5.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSION

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

Clarifying sleep characteristics and analyzing risk factors of sleep disorders to promote a predictive, preventive, and personalized medicine in patients with burn scars

Purpose

This study assessed sleep quality in patients with burn scars and investigated risk factors of sleep disorders to guide clinical therapy. From the strategy of predictive, preventive, and personalized medicine (PPPM/3PM), we proposed that risk assessment based on clinical indicators could prompt primary prediction, targeted prevention, and personalized interventions to improve the management of sleep disorders present in patients with burn scars.

Methods

This retrospective study recruited patients with burn scars and healthy volunteers from the Shanghai Burn Treatment Center between 2017 and 2022. Relevant information and data, including demographic characteristics, scar evaluation, and sleep quality, were obtained through the hospital information system, classical scar scale, and self-report questionnaires. Sleep quality was assessed using the Pittsburgh Sleep Quality Index (PSQI) and monitored using a cardiopulmonary-coupled electrocardiograph. Pain and pruritus were assessed using the visual analog scale (VAS). Scar appearance was assessed using the modified Vancouver scar scale (mVSS).

Results

The sample was comprised of 128 hypertrophic scar (HS) patients, with 61.7% males, a mean age of 41.1 ± 11.6 years, and burn area of 46.2 ± 27.9% total body surface area (TBSA). Patients with PSQI ≥ 7 accounted for 76.6%, and the global PSQI score was 9.4 ± 4.1. Objective sleep data showed that initial enter deep sleep time, light sleep time, awakening time, light sleep efficiency, and sleep apnea index were higher but deep sleep time, sleep efficiency, and deep sleep efficiency were lower in HS patients than that in healthy controls. Preliminary univariate analysis showed that age, hyperplasia time of scar, narrow airway, microstomia, VAS for pain and pruritus, and mVSS total (comprised of pigmentation, vascularity, height and pliability) were associated with the PSQI score (p < 0.1). Multivariable linear regression showed narrow airway, VAS for pain and pruritus, and mVSS specifically height, were the risk factors for PSQI score (p < 0.1).

Conclusions

This study model identified that narrow airway, pain, pruritus and scar appearance specifically height may provide excellent predictors for sleep disorders in HS patients. Our results provided a basis for the predictive diagnostics, targeted prevention, and individualized therapy of somnipathy predisposition and progression of HS patients in the setting of PPPM/3PM health care system, which contributed to a paradigm shift from reactive cure to advanced therapy.

Deep-Learning based Sleep Apnea Detection using SpO2 and Pulse Rate

This work presents automated apnea event de-tection using blood oxygen saturation (SpO2) and pulse rate (PR), conveniently recorded with a pulse oximeter. A large, diverse cohort of patients (n=8068, age≥40 years) from the sleep heart health study dataset with annotated sleep events have been employed in this study. A deep-learning model is trained to detect apnea in successive 30 s epochs and performances are assessed on two independent sub-cohorts of test data. The proposed algorithm showcases the highest test performance of 90.4 % area under the receiver operating characteristic curve and 58.9% area under the precision-recall curve for epoch-based apnea detection. Additionally, the model consistently performs well across various apnea subtypes, with the highest sensitivity of 93.4 % for obstructive apnea detection followed by 90.5 % for central apnea and 89.1 % for desaturation associated hypopnea. Overall, the proposed algorithm provides a robust and sensitive approach for sleep apnea event detection using a noninvasive pulse oximeter sensor. Clinical Relevance - The study establishes high sensitivity for automated epoch-based apnea detection across a diverse study cohort with various comorbidities using simply a pulse oximeter. This highly cost-effective approach could also enable convenient sleep and health monitoring over long-term.

Automatic Detection of the Cyclic Alternating Pattern of Sleep and Diagnosis of Sleep-Related Pathologies Based on Cardiopulmonary Resonance Indices

The cyclic alternating pattern is the periodic electroencephalogram activity occurring during non-rapid eye movement sleep. It is a marker of sleep instability and is correlated with several sleep-related pathologies. Considering the connection between the human heart and brain, our study explores the feasibility of using cardiopulmonary features to automatically detect the cyclic alternating pattern of sleep and hence diagnose sleep-related pathologies. By statistically analyzing and comparing the cardiopulmonary characteristics of a healthy group and groups with sleep-related diseases, an automatic recognition scheme of the cyclic alternating pattern is proposed based on the cardiopulmonary resonance indices. Using the Hidden Markov and Random Forest, the scheme combines the variation and stability of measurements of the coupling state of the cardiopulmonary system during sleep. In this research, the F1 score of the sleep-wake classification reaches 92.0%. In terms of the cyclic alternating pattern, the average recognition rate of A-phase reaches 84.7% on the CAP Sleep Database of 108 cases of people. The F1 score of disease diagnosis is 87.8% for insomnia and 90.0% for narcolepsy.

Transfer learning for non-image data in clinical research: A scoping review

BACKGROUND

Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature.

METHODS AND FINDINGS

We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%).

CONCLUSIONS

In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research.

An LSTM Network for Apnea and Hypopnea Episodes Detection in Respiratory Signals

One of the most common sleep disorders is sleep apnea. It manifests itself by episodes of shallow breathing or pauses in breathing during the night. Diagnosis of this disease involves polysomnography examination, which is expensive. Alternatively, diagnostic doctors can be supported with recordings from the in-home polygraphy sensors. Furthermore, numerous attempts for providing an automated apnea episodes annotation algorithm have been made. Most of them, however, do not distinguish between apnea and hypopnea episodes. In this work, a novel solution for epoch-based annotation problem is presented. Utilizing an architecture based on the long short-term memory (LSTM) networks, the proposed model provides locations of sleep disordered breathing episodes and identifies them as either apnea or hypopnea. To achieve this, special pre- and postprocessing steps have been designed. The obtained labels can be then used for calculation of the respiratory event index (REI), which serves as a disease severity indicator. The input for the model consists of the oronasal airflow along with the thoracic and abdominal respiratory effort signals. Performance of the proposed architecture was verified on the SHHS-1 and PhysioNet Sleep databases, obtaining mean REI classification error of 9.24/10.52 with standard deviation of 11.61/7.92 (SHHS-1/PhysioNet). Normal breathing, hypopnea and apnea differentiation accuracy is assessed on both databases, resulting in the correctly classified samples percentage of 86.42%/84.35%, 49.30%/58.28% and 68.20%/69.50% for normal breathing, hypopnea and apnea classes, respectively. Overall accuracies are 80.66%/82.04%. Additionally, the effect of wake periods is investigated. The results show that the proposed model can be successfully used for both episode classification and REI estimation tasks.

Wearable monitoring of sleep-disordered breathing: estimation of the apnea-hypopnea index using wrist-worn reflective photoplethysmography

A large part of the worldwide population suffers from obstructive sleep apnea (OSA), a disorder impairing the restorative function of sleep and constituting a risk factor for several cardiovascular pathologies. The standard diagnostic metric to define OSA is the apnea-hypopnea index (AHI), typically obtained by manually annotating polysomnographic recordings. However, this clinical procedure cannot be employed for screening and for long-term monitoring of OSA due to its obtrusiveness and cost. Here, we propose an automatic unobtrusive AHI estimation method fully based on wrist-worn reflective photoplethysmography (rPPG), employing a deep learning model exploiting cardiorespiratory and sleep information extracted from the rPPG signal trained with 250 recordings. We tested our method with an independent set of 188 heterogeneously disordered clinical recordings and we found it estimates the AHI with a good agreement to the gold standard polysomnography reference (correlation = 0.61, estimation error = 3±10 events/h). The estimated AHI was shown to reliably assess OSA severity (weighted Cohen's kappa = 0.51) and screen for OSA (ROC-AUC = 0.84/0.86/0.85 for mild/moderate/severe OSA). These findings suggest that wrist-worn rPPG measurements that can be implemented in wearables such as smartwatches, have the potential to complement standard OSA diagnostic techniques by allowing unobtrusive sleep and respiratory monitoring.