Nonlinear characteristics of blood oxygen saturation from nocturnal oximetry for obstructive sleep apnoea detection

MFS-DBF: A trustworthy multichannel feature sieve and decision boundary formulation system for Obstructive Sleep Apnea detection

The fine identification of sleep apnea events is instrumental in Obstructive Sleep Apnea (OSA) diagnosis. The development of sleep apnea event detection algorithms based on polysomnography is becoming a research hotspot in medical signal processing. In this paper, we propose an Inverse-Projection based Visualization System (IPVS) for sleep apnea event detection algorithms. The IPVS consists of a feature dimensionality reduction module and a feature reconstruction module. First, features of blood oxygen saturation and nasal airflow are extracted and used as input data for event analysis. Then, visual analysis is conducted on the feature distribution for apnea events. Next, dimensionality reduction and reconstruction methods are combined to achieve the dynamic visualization of sleep apnea event feature sets and the visual analysis of classifier decision boundaries. Moreover, the decision-making consistency is explored for various sleep apnea event detection classifiers, which provides researchers and users with an intuitive understanding of the detection algorithm. We applied the IPVS to an OSA detection algorithm with an accuracy of 84% and a diagnostic accuracy of 92% on a publicly available dataset. The experimental results show that the consistency between our visualization results and prior medical knowledge provides strong evidence for the practicality of the proposed system. For clinical practice, the IPVS can guide users to focus on samples with higher uncertainty presented by the OSA detection algorithm, reducing the workload and improving the efficiency of clinical diagnosis, which in turn increases the value of trust.

Predicting Alzheimer's disease CSF core biomarkers: a multimodal Machine Learning approach

Introduction

Alzheimer's disease (AD) is a progressive neurodegenerative disorder. Current core cerebrospinal fluid (CSF) AD biomarkers, widely employed for diagnosis, require a lumbar puncture to be performed, making them impractical as screening tools. Considering the role of sleep disturbances in AD, recent research suggests quantitative sleep electroencephalography features as potential non-invasive biomarkers of AD pathology. However, quantitative analysis of comprehensive polysomnography (PSG) signals remains relatively understudied. PSG is a non-invasive test enabling qualitative and quantitative analysis of a wide range of parameters, offering additional insights alongside other biomarkers. Machine Learning (ML) gained interest for its ability to discern intricate patterns within complex datasets, offering promise in AD neuropathology detection. Therefore, this study aims to evaluate the effectiveness of a multimodal ML approach in predicting core AD CSF biomarkers.

Methods

Mild-moderate AD patients were prospectively recruited for PSG, followed by testing of CSF and blood samples for biomarkers. PSG signals underwent preprocessing to extract non-linear, time domain and frequency domain statistics quantitative features. Multiple ML algorithms were trained using four subsets of input features: clinical variables (CLINVAR), conventional PSG parameters (SLEEPVAR), quantitative PSG signal features (PSGVAR) and a combination of all subsets (ALL). Cross-validation techniques were employed to evaluate model performance and ensure generalizability. Regression models were developed to determine the most effective variable combinations for explaining variance in the biomarkers.

Results

On 49 subjects, Gradient Boosting Regressors achieved the best results in estimating biomarkers levels, using different loss functions for each biomarker: least absolute deviation (LAD) for the Aβ42, least squares (LS) for p-tau and Huber for t-tau. The ALL subset demonstrated the lowest training errors for all three biomarkers, albeit with varying test performance. Specifically, the SLEEPVAR subset yielded the best test performance in predicting Aβ42, while the ALL subset most accurately predicted p-tau and t-tau due to the lowest test errors.

Conclusions

Multimodal ML can help predict the outcome of CSF biomarkers in early AD by utilizing non-invasive and economically feasible variables. The integration of computational models into medical practice offers a promising tool for the screening of patients at risk of AD, potentially guiding clinical decisions.

Transforming neonatal care with artificial intelligence: challenges, ethical consideration, and opportunities

Artificial intelligence (AI) offers tremendous potential to transform neonatology through improved diagnostics, personalized treatments, and earlier prevention of complications. However, there are many challenges to address before AI is ready for clinical practice. This review defines key AI concepts and discusses ethical considerations and implicit biases associated with AI. Next we will review literature examples of AI already being explored in neonatology research and we will suggest future potentials for AI work. Examples discussed in this article include predicting outcomes such as sepsis, optimizing oxygen therapy, and image analysis to detect brain injury and retinopathy of prematurity. Realizing AI's potential necessitates collaboration between diverse stakeholders across the entire process of incorporating AI tools in the NICU to address testability, usability, bias, and transparency. With multi-center and multi-disciplinary collaboration, AI holds tremendous potential to transform the future of neonatology.

Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients

In this paper, we thoroughly analyze the detection of sleep apnea events in the context of Obstructive Sleep Apnea (OSA), which is considered a public health problem because of its high prevalence and serious health implications. We especially evaluate patients who do not always show desaturations during apneic episodes (non-desaturating patients). For this purpose, we use a database (HuGCDN2014-OXI) that includes desaturating and non-desaturating patients, and we use the widely used Physionet Apnea Dataset for a meaningful comparison with prior work. Our system combines features extracted from the Heart-Rate Variability (HRV) and SpO₂, and it explores their potential to characterize desaturating and non-desaturating events. The HRV-based features include spectral, cepstral, and nonlinear information (Detrended Fluctuation Analysis (DFA) and Recurrence Quantification Analysis (RQA)). SpO₂-based features include temporal (variance) and spectral information. The features feed a Linear Discriminant Analysis (LDA) classifier. The goal is to evaluate the effect of using these features either individually or in combination, especially in non-desaturating patients. The main results for the detection of apneic events are: (a) Physionet success rate of 96.19%, sensitivity of 95.74% and specificity of 95.25% (Area Under Curve (AUC): 0.99); (b) HuGCDN2014-OXI of 87.32%, 83.81% and 88.55% (AUC: 0.934), respectively. The best results for the global diagnosis of OSA patients (HuGCDN2014-OXI) are: success rate of 95.74%, sensitivity of 100%, and specificity of 89.47%. We conclude that combining both features is the most accurate option, especially when there are non-desaturating patterns among the recordings under study.

Dynamic Bayesian Model for Detecting Obstructive Respiratory Events by Using an Experimental Model

In this study, we propose a model-based tool for the detection of obstructive apnea episodes by using ECG features from a single lead channel. Several sequences of recurrent apnea were provoked in separate 15-min periods in anesthetized rats during an experimental model of obstructive sleep apnea (OSA). Morphology-based ECG markers and the beat-to-beat interval (RR) were assessed in each sequence. These markers were used to train dynamic Bayesian networks (DBN) with different orders and feature combinations to find a good tradeoff between network complexity and apnea-detection performance. By using a filtering approach, the resulting DBNs were used to infer the apnea probability signal for subsequent episodes in the same rat. These signals were then processed using by 15-s epochs to determine whether epochs were classified as apneic or nonapneic. Our results showed that fifth-order models provided suitable RMSE values, since higher order models become significantly more complex and present worse generalization. A global threshold of 0.2 gave the best overall performance for all combinations tested, with Acc = 81.3%, Se = 69.8% and Sp = 81.5%, using only two parameters including the RR and Ds (R-wave downslope) markers. We concluded that multivariate models using DBNs represent a powerful tool for detecting obstructive apnea episodes in short segments, which may also serve to estimate the number of total events in a given time period.

Development and validation of a metabolite index for obstructive sleep apnea across race/ethnicities

Obstructive sleep apnea (OSA) is a common disorder characterized by recurrent episodes of upper airway obstruction during sleep resulting in oxygen desaturation and sleep fragmentation, and associated with increased risk of adverse health outcomes. Metabolites are being increasingly used for biomarker discovery and evaluation of disease processes and progression. Studying metabolomic associations with OSA in a diverse community-based cohort may provide insights into the pathophysiology of OSA. We aimed to develop and replicate a metabolite index for OSA and identify individual metabolites associated with OSA. We studied 219 metabolites and their associations with the apnea hypopnea index (AHI) and with moderate-severe OSA (AHI ≥ 15) in the Hispanic Community Health Study/Study of Latinos (HCHS/SOL) (n = 3507) using two methods: (1) association analysis of individual metabolites, and (2) least absolute shrinkage and selection operator (LASSO) regression to identify a subset of metabolites jointly associated with OSA, which was used to develop a metabolite index for OSA. Results were validated in the Multi-Ethnic Study of Atherosclerosis (MESA) (n = 475). When assessing the associations with individual metabolites, we identified seven metabolites significantly positively associated with OSA in HCHS/SOL (FDR p < 0.05), of which four associations-glutamate, oleoyl-linoleoyl-glycerol (18:1/18:2), linoleoyl-linoleoyl-glycerol (18:2/18:2) and phenylalanine, were replicated in MESA (one sided-p < 0.05). The OSA metabolite index, composed of 14 metabolites, was associated with a 50% increased risk for moderate-severe OSA (OR = 1.50 [95% CI 1.21-1.85] per 1 SD of OSA metabolite index, p < 0.001) in HCHS/SOL and 55% increased risk (OR = 1.55 [95% CI 1.10-2.20] per 1 SD of OSA metabolite index, p = 0.013) in MESA, both adjusted for demographics, lifestyle, and comorbidities. Similar albeit less significant associations were observed for AHI. Replication of the metabolite index in an independent multi-ethnic dataset demonstrates the robustness of metabolomic-based OSA index to population heterogeneity. Replicated metabolite associations may provide insights into OSA-related molecular and metabolic mechanisms.

Identification of arterial oxygen intermittency in oximetry data

In patients with kidney failure treated by hemodialysis, intradialytic arterial oxygen saturation (SaO₂) time series present intermittent high-frequency high-amplitude oximetry patterns (IHHOP), which correlate with observed sleep-associated breathing disturbances. A new method for identifying such intermittent patterns is proposed. The method is based on the analysis of recurrence in the time series through the quantification of an optimal recurrence threshold ([Formula: see text]). New time series for the value of [Formula: see text] were constructed using a rolling window scheme, which allowed for real-time identification of the occurrence of IHHOPs. The results for the optimal recurrence threshold were confronted with standard metrics used in studies of obstructive sleep apnea, namely the oxygen desaturation index (ODI) and oxygen desaturation density (ODD). A high correlation between [Formula: see text] and the ODD was observed. Using the value of the ODI as a surrogate to the apnea-hypopnea index (AHI), it was shown that the value of [Formula: see text] distinguishes occurrences of sleep apnea with great accuracy. When subjected to binary classifiers, this newly proposed metric has great power for predicting the occurrences of sleep apnea-related events, as can be seen by the larger than 0.90 AUC observed in the ROC curve. Therefore, the optimal threshold [Formula: see text] from recurrence analysis can be used as a metric to quantify the occurrence of abnormal behaviors in the arterial oxygen saturation time series.

A novel, simple, and accurate pulse oximetry indicator for screening adult obstructive sleep apnea

OBJECTIVE

The objective of the study was to develop a multiparametric oximetry indicator (IMp-SpO2) to diagnose obstructive sleep apnea in adults.

MATERIAL AND METHOD

This was an observational, retrospective study of diagnostic accuracy. We included adults who had had a diagnostic polysomnography with few artifacts and a total sleep time of at least 180 min in the sleep laboratory. Obstructive sleep apnea (OSA) was defined as an apnea-hypopnea index (AHI) ≥ 5. The database was randomly divided into an experimental (Exp-G) and validation (Val-G) group. The program calculated several parameters of oxygen saturation variability (Par-VarSpO2): (a) oxygen desaturation index (ODI ≥ 3, 4%) and (b) 90, 95, and 97.5 percentiles of both the number of oxygen desaturations ≥ 3 and 4% (P90-97.5 OD3/4 W5-60) and SpO2 standard deviations in moving windows from 5 to 60 min (P90-P97.5 SDSpO2 W5-10). Area under the ROC curve (AUC-ROC), sensitivity, specificity, positive/negative likelihood ratios, and accuracy were calculated.

RESULTS

Of 1141 adults included in the study, experimental (571) and validation group (570) were similar (women 47% vs 45%, BMI 27.5 kg/m² vs 27.2 kg/m², and AHI 11.7 vs 12, p NS). The IMp-SpO2 developed in the experimental group consisted of a combination of 10 parameters of oxygen saturation variability. The presence of at least one IMp-SpO2 variable had a high diagnostic performance for OSA (sensitivity/specificity/accuracy: Exp-G: 92.8/94/93.2%; Val-G: 93/95.2/93.7%). The IMp-SpO2 AUC-ROC was higher (Exp-G 0.934, Val-G 0.941) than most of the Par-VarSpO2 (0.898-0.929, p < 0.05).

CONCLUSION

The IMp-SpO2 showed a > 90% accuracy for OSA diagnosis in adults.

Detection of Sleep Apnea from Electrocardiogram and Pulse Oximetry Signals Using Random Forest

Sleep apnea (SA) is a common sleep disorder which could impair the human physiological system. Therefore, early diagnosis of SA is of great interest. The traditional method of diagnosing SA is an overnight polysomnography (PSG) evaluation. When PSG has limited availability, automatic SA screening with a fewer number of signals should be considered. The primary purpose of this study is to develop and evaluate a SA detection model based on electrocardiogram (ECG) and blood oxygen saturation (SpO2). We adopted a multimodal approach to fuse ECG and SpO2 signals at the feature level. Then, feature selection was conducted using the recursive feature elimination with cross-validation (RFECV) algorithm and random forest (RF) classifier used to discriminate between apnea and normal events. Experiments were conducted on the Apnea-ECG database. The introduced algorithm obtained an accuracy of 97.5%, a sensitivity of 95.9%, a specificity of 98.4% and an AUC of 0.992 in per-segment classification, and outperformed previous works. The results showed that ECG and SpO2 are complementary in detecting SA, and that the combination of ECG and SpO2 enhances the ability to diagnose SA. Therefore, the proposed method has the potential to be an alternative to conventional detection methods.

Oximetry Indices in the Management of Sleep Apnea: From Overnight Minimum Saturation to the Novel Hypoxemia Measures

Obstructive sleep apnea (OSA) is a multidimensional disease often underdiagnosed due to the complexity and unavailability of its standard diagnostic method: the polysomnography. Among the alternative abbreviated tests searching for a compromise between simplicity and accurateness, oximetry is probably the most popular. The blood oxygen saturation (SpO₂) signal is characterized by a near-constant profile in healthy subjects breathing normally, while marked drops (desaturations) are linked to respiratory events. Parameterization of the desaturations has led to a great number of indices of severity assessment commonly used to assist in OSA diagnosis. In this chapter, the main methodologies used to characterize the overnight oximetry profile are reviewed, from visual inspection and simple statistics to complex measures involving signal processing and pattern recognition techniques. We focus on the individual performance of each approach, but also on the complementarity among the great amount of indices existing in the state of the art, looking for the most relevant oximetric feature subset. Finally, a quick overview of SpO₂-based deep learning applications for OSA management is carried out, where the raw oximetry signal is analyzed without previous parameterization. Our research allows us to conclude that all the methodologies (conventional, time, frequency, nonlinear, and hypoxemia-based) demonstrate high ability to provide relevant oximetric indices, but only a reduced set provide non-redundant complementary information leading to a significant performance increase. Finally, although oximetry is a robust tool, greater standardization and prospective validation of the measures derived from complex signal processing techniques are still needed to homogenize interpretation and increase generalizability.

Automated Scoring of Respiratory Events in Sleep with a Single Effort Belt and Deep Neural Networks

OBJECTIVE

Automatic detection and analysis of respiratory events in sleep using a single respiratory effort belt and deep learning.

METHODS

Using 9,656 polysomnography recordings from the Massachusetts General Hospital (MGH), we trained a neural network (WaveNet) to detect obstructive apnea, central apnea, hypopnea and respiratory-effort related arousals. Performance evaluation included event-based analysis and apnea-hypopnea index (AHI) stratification. The model was further evaluated on a public dataset, the Sleep-Heart-Health-Study-1, containing 8,455 polysomnographic recordings.

RESULTS

For binary apnea event detection in the MGH dataset, the neural network obtained a sensitivity of 68%, a specificity of 98%, a precision of 65%, a F1-score of 67%, and an area under the curve for the receiver operating characteristics curve and precision-recall curve of 0.93 and 0.71, respectively. AHI prediction resulted in a mean difference of 0.417.8 and a r² of 0.90. For the multiclass task, we obtained varying performances: 84% of all labeled central apneas were correctly classified, whereas this metric was 51% for obstructive apneas, 40% for respiratory effort related arousals and 23% for hypopneas.

CONCLUSION

Our fully automated method can detect respiratory events and assess the AHI accurately. Differentiation of event types is more difficult and may reflect in part the complexity of human respiratory output and some degree of arbitrariness in the criteria used during manual annotation.

SIGNIFICANCE

The current gold standard of diagnosing sleep-disordered breathing, using polysomnography and manual analysis, is time-consuming, expensive, and only applicable in dedicated clinical environments. Automated analysis using a single effort belt signal overcomes these limitations.

Complex Relationship Between Daily Partner Violence and Alcohol Use Among Violent Heterosexual Men

Although alcohol use and partner violence are consistently associated, the nature of the alcohol-violence relationship is still unclear. The purpose of this pilot study was to use longitudinal daily assessments of male partners' alcohol use and violent events to identify the nature of the alcohol-violence relationship, employing both linear and nonlinear analyses. The participants were 20 adult heterosexual couples of whom the woman reported experiencing partner violence in the prior 30 days. Each partner provided a separate daily telephone report for 8 weeks via an automated interactive voice response (IVR), concerning the previous day's violence, alcohol use, stressors, emotional reactions, and concerns for children. Individual IVR databases were merged to form a combined couple's IVR time series. Time series were analyzed using graphic, linear, and nonlinear methods. Graphic analysis using state space grids found no consistent pattern across couples. Similarly, linear analysis using same-day cross-correlation and prior-day beta statistics found no significant group-level alcohol-violence relationship. Using cross-approximate entropy statistics and differential structural equation modeling, no nonlinear relationships between alcohol use and violence were noted either. Whether applying linear or nonlinear analytic methods, there is no group-level relationship between alcohol use by male perpetrators and their violent acts. The implications are significant. First, the alcohol-violence relationship may differ among subgroups. Second, couples need to be assessed thoroughly to determine their unique relationship with alcohol use, so that couple-specific interventions can be designed. Third, if perpetrators believe that their violence is facilitated by their alcohol use, then alcohol reduction should be encouraged despite any evidence suggesting a different alcohol-violence relationship. Finally, the accepted alcohol-causes-violence belief held by many providers needs to be reconsidered. Because the nature of the alcohol-violence relationship varies considerably across couples, clinicians should seek to understand their unique relationship applying across-the-board management approaches.

Ensemble of Deep Learning Models for Sleep Apnea Detection: An Experimental Study

Sleep Apnea is a breathing disorder occurring during sleep. Older people suffer most from this disease. In-time diagnosis of apnea is needed which can be observed by the application of a proper health monitoring system. In this work, we focus on Obstructive Sleep Apnea (OSA) detection from the Electrocardiogram (ECG) signals obtained through the body sensors. Our work mainly consists of an experimental study of different ensemble techniques applied on three deep learning models—two Convolutional Neural Network (CNN) based models, and a combination of CNN and Long Short-Term Memory (LSTM) models, which were previously proposed in the OSA detection domain. We have chosen four ensemble techniques—majority voting, sum rule and Choquet integral based fuzzy fusion and trainable ensemble using Multi-Layer Perceptron (MLP) for our case study. All the experiments are conducted on the benchmark PhysioNet Apnea-ECG Database. Finally, we have achieved highest OSA detection accuracy of 85.58% using the MLP based ensemble approach. Our best result is also able to surpass many of state-of-the-art methods.

Digital oximetry biomarkers for assessing respiratory function: standards of measurement, physiological interpretation, and clinical use

Pulse oximetry is routinely used to non-invasively monitor oxygen saturation levels. A low oxygen level in the blood means low oxygen in the tissues, which can ultimately lead to organ failure. Yet, contrary to heart rate variability measures, a field which has seen the development of stable standards and advanced toolboxes and software, no such standards and open tools exist for continuous oxygen saturation time series variability analysis. The primary objective of this research was to identify, implement and validate key digital oximetry biomarkers (OBMs) for the purpose of creating a standard and associated reference toolbox for continuous oximetry time series analysis. We review the sleep medicine literature to identify clinically relevant OBMs. We implement these biomarkers and demonstrate their clinical value within the context of obstructive sleep apnea (OSA) diagnosis on a total of n = 3806 individual polysomnography recordings totaling 26,686 h of continuous data. A total of 44 digital oximetry biomarkers were implemented. Reference ranges for each biomarker are provided for individuals with mild, moderate, and severe OSA and for non-OSA recordings. Linear regression analysis between biomarkers and the apnea hypopnea index (AHI) showed a high correlation, which reached [Formula: see text]. The resulting python OBM toolbox, denoted "pobm", was contributed to the open software PhysioZoo ( physiozoo.org ). Studying the variability of the continuous oxygen saturation time series using pbom may provide information on the underlying physiological control systems and enhance our understanding of the manifestations and etiology of diseases, with emphasis on respiratory diseases.

Using Lempel-Ziv complexity as effective classification tool of the sleep-related breathing disorders

BACKGROUND AND OBJECTIVE

People suffer from sleep disorders caused by work-related stress, irregular lifestyle or mental health problems. Therefore, development of effective tools to diagnose sleep disorders is important. Recently, to analyze biomedical signals Information Theory is exploited. We propose efficient classification method of sleep anomalies by applying entropy estimating algorithms to encoded ECGs signals coming from patients suffering from Sleep-Related Breathing Disorders (SRBD).

METHODS

First, ECGs were discretized using the encoding method which captures the biosignals variability. It takes into account oscillations of ECG measurements around signals averages. Next, to estimate entropy of encoded signals Lempel-Ziv complexity algorithm (LZ) which measures patterns generation rate was applied. Then, optimal encoding parameters, which allow distinguishing normal versus abnormal events during sleep with high sensitivity and specificity were determined numerically. Simultaneously, subjects' states were identified using acoustic signal of breathing recorded in the same period during sleep.

RESULTS

Random sequences show normalized LZ close to 1 while for more regular sequences it is closer to 0. Our calculations show that SRBDs have normalized LZ around 0.32 (on average), while control group has complexity around 0.85. The results obtained to public database are similar, i.e. LZ for SRBDs around 0.48 and for control group 0.7. These show that signals within the control group are more random whereas for the SRBD group ECGs are more deterministic. This finding remained valid for both signals acquired during the whole duration of experiment, and when shorter time intervals were considered. Proposed classifier provided sleep disorders diagnostics with a sensitivity of 93.75 and specificity of 73.00%. To validate our method we have considered also different variants as a training and as testing sets. In all cases, the optimal encoding parameter, sensitivity and specificity values were similar to our results above.

CONCLUSIONS

Our pilot study suggests that LZ based algorithm could be used as a clinical tool to classify sleep disorders since the LZ complexities for SRBD positives versus healthy individuals show a significant difference. Moreover, normalized LZ complexity changes are related to the snoring level. This study also indicates that LZ technique is able to detect sleep abnormalities in early disorders stage.

Oxygen saturation resolution influences regularity measurements

The measurement of regularity in the oxygen saturation (SpO(2)) signal has been suggested for use in identifying subjects with sleep disordered breathing (SDB). Previous work has shown that children with SDB have lower SpO(2) regularity than subjects without SDB (NonSDB). Regularity was measured using non-linear methods like approximate entropy (ApEn), sample entropy (SamEn) and Lempel-Ziv (LZ) complexity. Different manufacturer's pulse oximeters provide SpO(2) at various resolutions and the effect of this resolution difference on SpO(2) regularity, has not been studied. To investigate this effect, we used the SpO(2) signal of children with and without SDB, recorded from the Phone Oximeter (0.1% resolution) and the same SpO(2) signal rounded to the nearest integer (artificial 1% resolution). To further validate the effect of rounding, we also used the SpO(2) signal (1% resolution) recorded simultaneously from polysomnography (PSG), as a control signal. We estimated SpO(2) regularity by computing the ApEn, SamEn and LZ complexity, using a 5-min sliding window and showed that different resolutions provided significantly different results. The regularity calculated using 0.1% SpO(2) resolution provided no significant differences between SDB and NonSDB. However, the artificial 1% resolution SpO(2) provided significant differences between SDB and NonSDB, showing a more random SpO(2) pattern (lower SpO(2) regularity) in SDB children, as suggested in the past. Similar results were obtained with the SpO(2) recorded from PSG (1% resolution), which further validated that this SpO(2) regularity change was due to the rounding effect. Therefore, the SpO(2) resolution has a great influence in regularity measurements like ApEn, SamEn and LZ complexity that should be considered when studying the SpO(2) pattern in children with SDB.

Computer-Assisted Diagnosis of the Sleep Apnea-Hypopnea Syndrome: A Review

Automatic diagnosis of the Sleep Apnea-Hypopnea Syndrome (SAHS) has become an important area of research due to the growing interest in the field of sleep medicine and the costs associated with its manual diagnosis. The increment and heterogeneity of the different techniques, however, make it somewhat difficult to adequately follow the recent developments. A literature review within the area of computer-assisted diagnosis of SAHS has been performed comprising the last 15 years of research in the field. Screening approaches, methods for the detection and classification of respiratory events, comprehensive diagnostic systems, and an outline of current commercial approaches are reviewed. An overview of the different methods is presented together with validation analysis and critical discussion of the current state of the art.

Statistical and nonlinear analysis of oximetry from respiratory polygraphy to assist in the diagnosis of Sleep Apnea in children

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a sleep related breathing disorder that has important consequences in the health and development of infants and young children. To enhance the early detection of OSAHS, we propose a methodology based on automated analysis of nocturnal blood oxygen saturation (SpO(2)) from respiratory polygraphy (RP) at home. A database composed of 50 SpO(2) recordings was analyzed. Three signal processing stages were carried out: (i) feature extraction, where statistical features and nonlinear measures were computed and combined with conventional oximetric indexes, (ii) feature selection using genetic algorithms (GAs), and (iii) feature classification through logistic regression (LR). Leave-one-out cross-validation (loo-cv) was applied to assess diagnostic performance. The proposed method reached 80.8% sensitivity, 79.2% specificity, 80.0% accuracy and 0.93 area under the ROC curve (AROC), which improved the performance of single conventional indexes. Our results suggest that automated analysis of SpO(2) recordings from at-home RP provides essential and complementary information to assist in OSAHS diagnosis in children.

Development of a screening tool for sleep disordered breathing in children using the phone Oximeter™

Background

Sleep disordered breathing (SDB) can lead to daytime sleepiness, growth failure and developmental delay in children. Polysomnography (PSG), the gold standard to diagnose SDB, is a highly resource-intensive test, confined to the sleep laboratory.

Aim

To combine the blood oxygen saturation (SpO₂) characterization and cardiac modulation, quantified by pulse rate variability (PRV), to identify children with SDB using the Phone Oximeter, a device integrating a pulse oximeter with a smartphone.

Methods

Following ethics approval and informed consent, 160 children referred to British Columbia Children's Hospital for overnight PSG were recruited. A second pulse oximeter sensor applied to the finger adjacent to the one used for standard PSG was attached to the Phone Oximeter to record overnight pulse oximetry (SpO₂ and photoplethysmogram (PPG)) alongside the PSG.

Results

We studied 146 children through the analysis of the SpO₂ pattern, and PRV as an estimate of heart rate variability calculated from the PPG. SpO₂ variability and SpO₂ spectral power at low frequency, was significantly higher in children with SDB due to the modulation provoked by airway obstruction during sleep (p-value ). PRV analysis reflected a significant augmentation of sympathetic activity provoked by intermittent hypoxia in SDB children. A linear classifier was trained with the most discriminating features to identify children with SDB. The classifier was validated with internal and external cross-validation, providing a high negative predictive value (92.6%) and a good balance between sensitivity (88.4%) and specificity (83.6%). Combining SpO₂ and PRV analysis improved the classification performance, providing an area under the receiver operating characteristic curve of 88%, beyond the 82% achieved using SpO₂ analysis alone.

Conclusions

These results demonstrate that the implementation of this algorithm in the Phone Oximeter will provide an improved portable, at-home screening tool, with the capability of monitoring patients over multiple nights.

An effective model for screening obstructive sleep apnea: a large-scale diagnostic study

BACKGROUND

Obstructive sleep apnea (OSA) causes high morbidity and mortality and is independently associated with an increased likelihood of multiple complications. The diagnosis of OSA is presently time-consuming, labor-intensive and inaccessible.

AIM

This study sought to develop a simple and efficient model for identifying OSA in Chinese adult population.

METHODS

In this study, the efficiency of Epworth Sleepiness Scale (ESS) and a new established prediction model for screening OSA were evaluated in the test cohort (2,032 participants) and confirmed in an independent validation cohort (784 participants).

RESULTS

In the test cohort, a high specificity (82.77%, 95% confidence interval [CI], 77.36-87.35) and a moderate sensitivity (61.65%, 95% CI, 59.35-63.91) were obtained at the threshold of nine for the ESS alone. Notably, sex-stratified analysis revealed different optimum cut-off points: nine for males and six for females. The new generated screening model, including age, waist circumference, ESS score, and minimum oxygen saturation (SaO2) as independent variables, revealed a higher sensitivity (89.13%, 95% CI, 87.60-90.53) and specificity (90.34%, 95% CI, 85.85-93.77) at the best cut-off point. Through receiver operating characteristics curve analysis, the area under the receiver operating characteristics curve of the model was found significantly larger than that of the ESS alone (0.955 vs. 0.774, P<0.0001). All these results were confirmed in the validation cohort.

CONCLUSIONS

A practical screening model comprising minimum SaO2 and other parameters could efficiently identify undiagnosed OSA from the high-risk patients. Additionally, a sex-specific difference should be considered if the ESS alone is used.

Assessment of feature selection and classification approaches to enhance information from overnight oximetry in the context of apnea diagnosis

This study is aimed at assessing the usefulness of different feature selection and classification methodologies in the context of sleep apnea hypopnea syndrome (SAHS) detection. Feature extraction, selection and classification stages were applied to analyze blood oxygen saturation (SaO2) recordings in order to simplify polysomnography (PSG), the gold standard diagnostic methodology for SAHS. Statistical, spectral and nonlinear measures were computed to compose the initial feature set. Principal component analysis (PCA), forward stepwise feature selection (FSFS) and genetic algorithms (GAs) were applied to select feature subsets. Fisher's linear discriminant (FLD), logistic regression (LR) and support vector machines (SVMs) were applied in the classification stage. Optimum classification algorithms from each combination of these feature selection and classification approaches were prospectively validated on datasets from two independent sleep units. FSFS + LR achieved the highest diagnostic performance using a small feature subset (4 features), reaching 83.2% accuracy in the validation set and 88.7% accuracy in the test set. Similarly, GAs + SVM also achieved high generalization capability using a small number of input features (7 features), with 84.2% accuracy on the validation set and 84.5% accuracy in the test set. Our results suggest that reduced subsets of complementary features (25% to 50% of total features) and classifiers with high generalization ability could provide high-performance screening tools in the context of SAHS.

A hybrid symplectic principal component analysis and central tendency measure method for detection of determinism in noisy time series with application to mechanomyography

We present a hybrid symplectic geometry and central tendency measure (CTM) method for detection of determinism in noisy time series. CTM is effective for detecting determinism in short time series and has been applied in many areas of nonlinear analysis. However, its performance significantly degrades in the presence of strong noise. In order to circumvent this difficulty, we propose to use symplectic principal component analysis (SPCA), a new chaotic signal de-noising method, as the first step to recover the system dynamics. CTM is then applied to determine whether the time series arises from a stochastic process or has a deterministic component. Results from numerical experiments, ranging from six benchmark deterministic models to 1/f noise, suggest that the hybrid method can significantly improve detection of determinism in noisy time series by about 20 dB when the data are contaminated by Gaussian noise. Furthermore, we apply our algorithm to study the mechanomyographic (MMG) signals arising from contraction of human skeletal muscle. Results obtained from the hybrid symplectic principal component analysis and central tendency measure demonstrate that the skeletal muscle motor unit dynamics can indeed be deterministic, in agreement with previous studies. However, the conventional CTM method was not able to definitely detect the underlying deterministic dynamics. This result on MMG signal analysis is helpful in understanding neuromuscular control mechanisms and developing MMG-based engineering control applications.

Fuzzy central tendency measure for time series variability analysis with application to fatigue electromyography signals

A new method, namely fuzzy central tendency measure (fCTM) analysis, that could enable measurement of the variability of a time series, is presented in this study. Tests on simulated data sets show that fCTM is superior to the conventional central tendency measure (CTM) in several respects, including improved relative consistency and robustness to noise. The proposed fCTM method was applied to electromyograph (EMG) signals recorded during sustained isometric contraction for tracking local muscle fatigue. The results showed that the fCTM increased significantly during the development of muscle fatigue, and it was more sensitive to the fatigue phenomenon than mean frequency (MNF), the most commonly-used muscle fatigue indicator.

Probabilistic neural network approach for the detection of SAHS from overnight pulse oximetry

Diagnosis of sleep apnea hypopnoea syndrome (SAHS) depends on the apnea-hypopnea index determined by the standard in-laboratory overnight polysomnography (PSG). PSG is a costly, labor intensive and, at times, inaccessible approach. Because of the high demand, the need for timely diagnosis and the associated costs, novel methods for SAHS detection are required. In this study, a novel multivariate system is proposed for SAHS detection from the analysis of overnight blood oxygen saturation (SpO2). 115 subjects with SAHS suspicion were studied. A starting set of 17 time domain, stochastic, frequency-domain and nonlinear features were initially computed from SpO2 recordings. Sequential forward feature selection and a probabilistic neural network with leave-one-out cross-validation were applied. Oxygen desaturations below a 4 % threshold within 30 s (ODI430), restorations of 4 % within 10 s (RES4), median value (Sat50), SD1 Poincaré descriptor and the relative power in the 0.013-0.067 Hz frequency band (PSD15/75) formed the optimum features subset. 92.4 % sensitivity and 95.9 % specificity were achieved. Results significantly outperformed the univariate and multivariate approaches reported in literature. The outcome is a simple cost-effective tool that could be used as an alternative or supplementary method in a domiciliary approach to early diagnosis of SAHS.

Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis

In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO(2)) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO(2) signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25% (81.25% sensitivity and 81.25% specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO(2) data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG).

Real-time sleep apnea detection by classifier combination

To find an efficient and valid alternative of polysomnography (PSG), this paper investigates real-time sleep apnea and hypopnea syndrome (SAHS) detection based on electrocardiograph (ECG) and saturation of peripheral oxygen (SpO(2)) signals, individually and in combination. We include ten machine-learning algorithms in our classification experiment. It is shown that our proposed SpO (2) features outperform the ECG features in terms of diagnostic ability. More importantly, we propose classifier combination to further enhance the classification performance by harnessing the complementary information provided by individual classifiers. With our selected SpO(2) and ECG features, the classifier combination using AdaBoost with Decision Stump, Bagging with REPTree, and either kNN or Decision Table achieves sensitivity, specificity, and accuracy all around 82% for a minute-based real-time SAHS detection over 25 sleep-disordered-breathing suspects' full overnight recordings.

Feature selection from nocturnal oximetry using genetic algorithms to assist in obstructive sleep apnoea diagnosis

Nocturnal pulse oximetry (NPO) has demonstrated to be a powerful tool to help in obstructive sleep apnoea (OSA) detection. However, additional analysis is needed to use NPO alone as an alternative to nocturnal polysomnography (NPSG), which is the gold standard for a definitive diagnosis. In the present study, we exhaustively analysed a database of blood oxygen saturation (SpO(2)) recordings (80 OSA-negative and 160 OSA-positive) to obtain further knowledge on the usefulness of NPO. Population set was randomly divided into training and test sets. A feature extraction stage was carried out: 16 features (time and frequency statistics and spectral and nonlinear features) were computed. A genetic algorithm (GA) approach was applied in the feature selection stage. Our methodology achieved 87.5% accuracy (90.6% sensitivity and 81.3% specificity) in the test set using a logistic regression (LR) classifier with a reduced number of complementary features (3 time domain statistics, 1 frequency domain statistic, 1 conventional spectral feature and 1 nonlinear feature) automatically selected by means of GAs. Our results improved diagnostic performance achieved with conventional oximetric indexes commonly used by physicians. We concluded that GAs could be an effective and robust tool to search for essential oximetric features that could enhance NPO in the context of OSA diagnosis.

Automatic detection of apnoea of prematurity

The detection of the incidents of apnoea of prematurity (AP) in preterm infants is important in the intensive care unit, but this detection is often based on simple threshold techniques, which suffer from poor specificity. Three methods for the automatic detection of AP were designed, tested and evaluated using approximately 2426 h of continuous recording from 54 neonates (μ = 44 h and σ = 7 h). The first method was based on the cumulative sum of the time series of heart rate (HR), respiratory rate (RR) and oxygen saturation (SpO(2)) along with the sum of their Shannon entropy. The performance of this method gave 94.53% sensitivity, 74.72% specificity and 77.84% accuracy. The second method was based on the correlation between the time series of HR, RR and SpO(2), which were used as inputs to an artificial neural network. This gave 81.85% sensitivity, 75.83% specificity and 76.78% accuracy. The third method utilized the derivative of the three time series and yielded a performance of 100% sensitivity, 96.19% specificity and 96.79% accuracy. Although not optimized to work in real time, the latter method has the potential for forming the basis of a real time system for the detection of incidents of AP.

Early diagnosis of sleep related breathing disorders

Obstructive sleep apnea (OSA) being the most frequent sleep related breathing disorder results in non-restorative sleep, an increased cardiovascular morbidity and mortality as well as an elevated number of accidents. In Germany at least two million people have to be expected. If obstructive sleep apnea is diagnosed early enough then sleep may regain its restorative function, daytime performance may be improved and accident risk as well as cardiovascular risk may be normalised. This review critically evaluates anamnestic parameters, questionnaires, clinical findings and unattended recordings during sleep regarding their diagnostic accurracy in recognising OSA. There are numerous tools with insufficient results or too few data disqualifying them for screening for OSA. Promising preliminary results are published concerning neural network analysis of a high number of clinical parameters and non-linear analysis of oximetry itself or in combination with heart rate. Nasal pressure recordings can be used for risk estimation even without expertise in sleep medicine. More data is needed. Unattended portable monitoring used by qualified physicians is the gold standard procedure when screening methods for OSA are compared. It has a very high sensitivity and specificity well documented by several meta-analyses.

Multivariate analysis of blood oxygen saturation recordings in obstructive sleep apnea diagnosis

This study focuses on the analysis of blood oxygen saturation (SaO(2)) from nocturnal pulse oximetry (NPO) to help in the diagnosis of the obstructive sleep apnea (OSA) syndrome. A population of 148 patients suspected of suffering from OSA syndrome was studied. A wide set of 16 features was used to characterize changes in the SaO(2) profile during the night. Our feature set included common statistics in the time and frequency domains, conventional spectral characteristics from the power spectral density (PSD) function, and nonlinear features. We performed feature selection by means of a step-forward logistic regression (LR) approach with leave-one-out cross-validation. Second- and fourth-order statistical moments in the time domain (M2t and M4t), the relative power in the 0.014-0.033 Hz frequency band ( P(R)), and the Lempel-Ziv complexity (LZC) were automatically selected. 92.0% sensitivity, 85.4% specificity, and 89.7% accuracy were obtained. The optimum feature set significantly improved the diagnostic ability of each feature individually. Furthermore, our results outperformed classic oximetric indexes commonly used by physicians. We conclude that simultaneous analysis in the time and frequency domains by means of statistical moments, spectral and nonlinear features could provide complementary information from NPO to improve OSA diagnosis.

A classification algorithm based on spectral features from nocturnal oximetry and support vector machines to assist in the diagnosis of obstructive sleep apnea

The aim of this study is to develop and evaluate an algorithm to help in the diagnosis of the obstructive sleep apnea syndrome (OSAS). Arterial oxygen saturation (SaO(2)) signals from nocturnal pulse oximetry were used to identify OSAS patients. A total of 149 SaO(2) recordings from subjects suspected of OSAS were available. The initial population was divided into a training set (74 subjects) and a test set (75 subjects) to optimize and evaluate our algorithm. Support vector machines (SVM) with Gaussian kernel were used to classify spectral features from SaO(2) signals. Several configurations of SVM were assessed by varying the regularization (C) and the kernel width (sigma) parameters. Finally, the selected SVM classifier (C = 235 and sigma = 0.4) provided an accuracy of 88.00% (84.44% sensitivity and 93.33% specificity) and an AROC of 0.921. Our results suggest that the proposed algorithm could be useful for OSAS screening.

Real-time detection of apneas on a PDA

Patients suspected of suffering sleep apnea and hypopnea syndrome (SAHS) have to undergo sleep studies such as expensive polysomnographies to be diagnosed. Healthcare professionals are constantly looking for ways to improve the ease of diagnosis and comfort for this kind of patients as well as reducing both the number of sleep studies they need to undergo and the waiting times. Relating to this scenario, some research proposals and commercial products are appearing, but all of them record the physiological data of patients to portable devices and, in the morning, these data are loaded into hospital computers where physicians analyze them by making use of specialized software. In this paper, we present an alternative proposal that promotes not only a transmission of physiological data but also a real-time analysis of these data locally at a mobile device. For that, we have built a classifier that provides an accuracy of 93% and a receiver operating characteristic-area under the curve (ROC-AUC) of 98.5% on SpO(2) signals available in the annotated Apnea-ECG Database. This local analysis allows the detection of anomalous situations as soon as they are generated. The classifier has been implemented taking into consideration the restricted resources of mobile devices.