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

Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea

Scoring polysomnography for obstructive sleep apnea diagnosis is a laborious, long, and costly process. Machine learning approaches, such as deep neural networks, can reduce scoring time and costs. However, most methods require prior filtering and preprocessing of the raw signal. Our work presents a novel method for diagnosing obstructive sleep apnea using a transformer neural network with learnable positional encoding, which outperforms existing state-of-the-art solutions. This approach has the potential to improve the diagnostic performance of oximetry for obstructive sleep apnea and reduce the time and costs associated with traditional polysomnography. Contrary to existing approaches, our approach performs annotations at one-second granularity. Allowing physicians to interpret the model's outcome. In addition, we tested different positional encoding designs as the first layer of the model, and the best results were achieved using a learnable positional encoding based on an autoencoder with structural novelty. In addition, we tried different temporal resolutions with various granularity levels from 1 to 360 s. All experiments were carried out on an independent test set from the public OSASUD dataset and showed that our approach outperforms current state-of-the-art solutions with a satisfactory AUC of 0.89, accuracy of 0.80, and F1-score of 0.79.

Application of artificial intelligence in the diagnosis of sleep apnea

STUDY OBJECTIVES

Machine learning (ML) models have been employed in the setting of sleep disorders. This review aims to summarize the existing data about the role of ML techniques in the diagnosis, classification, and treatment of sleep-related breathing disorders.

METHODS

A systematic search in Medline, EMBASE, and Cochrane databases through January 2022 was performed.

RESULTS

Our search strategy revealed 132 studies that were included in the systematic review. Existing data show that ML models have been successfully used for diagnostic purposes. Specifically, ML models showed good performance in diagnosing sleep apnea using easily obtained features from the electrocardiogram, pulse oximetry, and sound signals. Similarly, ML showed good performance for the classification of sleep apnea into obstructive and central categories, as well as predicting apnea severity. Existing data show promising results for the ML-based guided treatment of sleep apnea. Specifically, the prediction of outcomes following surgical treatment and optimization of continuous positive airway pressure therapy can be guided by ML models.

CONCLUSIONS

The adoption and implementation of ML in the field of sleep-related breathing disorders is promising. Advancements in wearable sensor technology and ML models can help clinicians predict, diagnose, and classify sleep apnea more accurately and efficiently.

CITATION

Bazoukis G, Bollepalli SC, Chung CT, et al. Application of artificial intelligence in the diagnosis of sleep apnea. J Clin Sleep Med. 2023;19(7):1337-1363.

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.

Pulse oximetrySpO2signal for automated identification of sleep apnea: a review and future trends

Sleep apnea (SA) is characterized by intermittent episodes of apnea or hypopnea paused or reduced breathing, respectively each lasting at least ten seconds that occur during sleep. SA has an estimated global prevalence of 200 million and is associated with medical comorbidity, and sufferers are also more likely to sustain traffic- and work-related injury due to daytime somnolence. SA is amenable to treatment if detected early. Polysomnography (PSG) involving multi-channel signal acquisition is the reference standard for diagnosing SA but is onerous and costly. For home-based detection of SA, single-channelSpO₂signal acquisition using portable pulse oximeters is feasible. Machine (ML) and deep learning (DL) models have been developed for automated classification of SA versus no SA usingSpO₂signals alone. In this work, we review studies published between 2012 and 2022 on the use of ML and DL forSpO₂signal-based diagnosis of SA. A literature search based on PRISMA recommendations yielded 297 publications, of which 31 were selected after considering the inclusion and exclusion criteria. There were 20 ML and 11 DL models; their methods, differences, results, merits, and limitations were discussed. Many studies reported encouraging performance, which indicates the utility ofSpO₂signals in wearable devices for home-based SA detection.

ABOSA - Freely available automatic blood oxygen saturation signal analysis software: Structure and validation

BACKGROUND AND OBJECTIVE

Many sleep recording software used in clinical settings have some tools to automatically analyze the blood oxygen saturation (SpO₂) signal by detecting desaturations. However, these tools are often inadequate for scientific research as they do not provide SpO₂ signal-based parameters which are superior in the estimation of sleep apnea severity and related medical consequences. In addition, these software require expensive licenses and they lack batch analysis tools. Thus, we developed the first freely available automatic blood oxygen saturation analysis software (ABOSA) that provides sophisticated SpO₂ signal-based parameters and enables batch analysis of large datasets.

METHODS

ABOSA was programmed with MATLAB. ABOSA automatically detects desaturation and recovery events from the SpO₂ signals (EDF files) and calculates numerous parameters, such as oxygen desaturation index (ODI) and desaturation severity (DesSev). The accuracy of the ABOSA software was evaluated by comparing its desaturation scorings to manual scorings in Kuopio (n = 1981) and Loewenstein (n = 930) sleep apnea patient datasets. Validation was performed in a second-by-second manner by calculating Matthew's correlation coefficients (MCC) and median differences in parameter values. Finally, the performance of the ABOSA software was compared to two commercial software, Noxturnal and Profusion, in 100 patient subpopulations. As Noxturnal or Profusion does not calculate novel desaturation parameters, these were calculated with custom-made functions.

RESULTS

The agreements between ABOSA and manual scorings were great in both Kuopio (MCC = 0.801) and Loewenstein (MCC = 0.898) datasets. However, ABOSA slightly overestimated the desaturation parameter values. The median differences in ODIs were 0.8 (Kuopio) and 0.0 (Loewenstein) events/h. Similarly, the median differences in DesSevs were 0.02 (Kuopio) and 0.01 (Loewenstein) percentage points. In a second-by-second analysis, ABOSA performed very similarly to Noxturnal and Profusion software in both Kuopio (MCC_ABOSA = 0.807, MCC_Noxturnal = 0.807, MCC_Profusion = 0.811) and Loewenstein (MCC_ABOSA = 0.904, MCC_Noxturnal = 0.911, MCC_Profusion = 0.871) datasets. Based on Noxturnal and Profusion scorings, the desaturation parameter values were similarly overestimated compared to ABOSA.

CONCLUSIONS

ABOSA is an accurate and freely available software that calculates both traditional clinical parameters and novel parameters, provides a detailed characterization of desaturation and recovery events, and enables batch analysis of large datasets. These are features that no other software currently provides making ABOSA uniquely suitable for scientific research use.

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.

Conventional Machine Learning Methods Applied to the Automatic Diagnosis of Sleep Apnea

The overnight polysomnography shows a range of drawbacks to diagnose obstructive sleep apnea (OSA) that have led to the search for artificial intelligence-based alternatives. Many classic machine learning methods have been already evaluated for this purpose. In this chapter, we show the main approaches found in the scientific literature along with the most used data to develop the models, useful and large easily available databases, and suitable methods to assess performances. In addition, a range of results from selected studies are presented as examples of these methods. Very high diagnostic performances are reported in these results regardless of the approaches taken. This leads us to conclude that conventional machine learning methods are useful techniques to develop new OSA diagnosis simplification proposals and to act as benchmark for other more recent methods such as deep learning.

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.

AIOSA: An approach to the automatic identification of obstructive sleep apnea events based on deep learning

Obstructive Sleep Apnea Syndrome (OSAS) is the most common sleep-related breathing disorder. It is caused by an increased upper airway resistance during sleep, which determines episodes of partial or complete interruption of airflow. The detection and treatment of OSAS is particularly important in patients who suffered a stroke, because the presence of severe OSAS is associated with higher mortality, worse neurological deficits, worse functional outcome after rehabilitation, and a higher likelihood of uncontrolled hypertension. The gold standard test for diagnosing OSAS is polysomnography (PSG). Unfortunately, performing a PSG in an electrically hostile environment, like a stroke unit, on neurologically impaired patients is a difficult task; moreover, the number of strokes per day vastly outnumbers the availability of polysomnographs and dedicated healthcare professionals. Hence, a simple and automated recognition system to identify OSAS cases among acute stroke patients, relying on routinely recorded vital signs, is highly desirable. The vast majority of the work done so far focuses on data recorded in ideal conditions and highly selected patients, and thus it is hardly exploitable in real-life circumstances, where it would be of actual use. In this paper, we propose a novel convolutional deep learning architecture able to effectively reduce the temporal resolution of raw waveform data, like physiological signals, extracting key features that can be used for further processing. We exploit models based on such an architecture to detect OSAS events in stroke unit recordings obtained from the monitoring of unselected patients. Unlike existing approaches, annotations are performed at one-second granularity, allowing physicians to better interpret the model outcome. Results are considered to be satisfactory by the domain experts. Moreover, through tests run on a widely-used public OSAS dataset, we show that the proposed approach outperforms current state-of-the-art solutions.

3D Camera and Pulse Oximeter for Respiratory Events Detection

OBJECTIVE

The purpose of this study was to derive a respiratory movement signal from a 3D time-of-flight camera and to investigate if it can be used in combination with SpO₂ to detect respiratory events comparable to polysomnography (PSG) based detection.

METHODS

We derived a respiratory signal from a 3D camera and developed a new algorithm that detects reduced respiratory movement and SpO₂ desaturation to score respiratory events. The method was tested on 61 patients' synchronized 3D video and PSG recordings. The predicted apnea-hypopnea index (AHI), calculated based on total sleep time, and predicted severity were compared to manual PSG annotations (manualPSG). Predicted AHI evaluation, measured by intraclass correlation (ICC), and severity classification were performed. Furthermore, the results were evaluated by 30-second epoch analysis, labelled either as respiratory event or normal breathing, wherein the accuracy, sensitivity, specificity and Cohen's kappa were calculated.

RESULTS

The predicted AHI scored an ICC r = 0.94 (0.90 - 0.96 at 95% confidence interval, p < 0.001) compared to manualPSG. Severity classification scored 80% accuracy, with no misclassification by more than one severity level. Based on 30-second epoch analysis, the method scored a Cohen's kappa = 0.72, accuracy = 0.88, sensitivity = 0.80, and specificity = 0.91.

CONCLUSION

Our detection method using SpO₂ and 3D camera had excellent reliability and substantial agreement with PSG-based scoring.

SIGNIFICANCE

This method showed the potential to reliably detect respiratory events without airflow and respiratory belt sensors, sensors that can be uncomfortable to patients and susceptible to movement artefacts.

Patch validation: an observational study protocol for the evaluation of a multisignal wearable sensor in patients during anaesthesia and in the postanaesthesia care unit

INTRODUCTION

Except for operating rooms, postanaesthesia care units and intensive care units, where the monitoring of vital signs is continuous, intermittent care is standard practice. However, at a time when only the patients with the most serious conditions are hospitalised and only a fraction of these patients are in intensive care units, this type of monitoring is no longer sufficient. Wireless monitoring has been proposed, but it requires rigorous validation. The aim of this observational study is to compare vital signs obtained from a precordial patch sensor to those obtained with conventional monitoring.

METHODS AND ANALYSIS

This patch validation trial will be an observational, prospective, single-centre open study of 115 anaesthetised adult patients monitored with both a wireless sensor (myAngel VitalSigns, Devinnova, Montpellier, France) and a standard bedside monitor (Carescape Monitor B850, GE Healthcare, Chicago, Illinois). Both sensors will be used to record peripheral oxygen saturation, respiratory rate, heart rate, body temperature and blood pressure (systolic and diastolic). The main objective will be to assess the degree of agreement between the two systems during the patients' stay in the postanaesthesia care unit, both at the raw signal level and at the clinical parameter level. The secondary objectives will be to assess the same performance under anaesthesia, the frequency of missing data or artefacts, the diagnostic performance of the systems, the influence of patients' characteristics on agreement between the two systems, the adverse events and the acceptability of the patch to patients. Bland-Altman plots will be used in the main analysis to detect discrepancies and estimate the limits of agreement.

ETHICS AND DISSEMINATION

Ethics approval was obtained from the Ethical Committee (Toulouse, France) on 10 April 2020. We are not yet recruiting subjects for this study. The results will be submitted for publication in peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NCT04344093.

Sleep apnea detection from ECG using variational mode decomposition

Sleep apnea is a pervasive breathing problem during night sleep, and its repetitive occurrence causes various health problems. Polysomnography is commonly used for apnea screening which is an expensive, time-consuming, and complex process. In this paper, a simple but efficient technique based on the variational mode decomposition (VMD) for automated detection of sleep apnea from single-lead ECG is proposed. The heart rate variability and ECG-derived respiration signals obtained from ECG are decomposed into different modes using the VMD, and these modes are used for extracting different features including spectral entropies, interquartile range, and energy. The principal component analysis is employed to reduce the dimension of the feature vector. The experiments are conducted using the Apnea-ECG dataset, and the classification performance of various classifiers is investigated. In per-segment classification, an accuracy of about 87.5% (Sens: 84.9%, Spec: 88.2%) is achieved using the K-nearest neighbor classifier. In per-recording classification, the proposed technique using the linear discriminant analysis model outperformed the existing apnea detection approaches by achieving the accuracy of 100%. The algorithm also provided the best agreement between the estimated and reference apnea-hypopnea index (AHI) values. These results show that the algorithm has the potential to be used for home-based apnea screening systems.

Detection of Sleep Apnea from Single-Lead ECG Signal Using a Time Window Artificial Neural Network

Sleep apnea (SA) is a ubiquitous sleep-related respiratory disease. It can occur hundreds of times at night, and its long-term occurrences can lead to some serious cardiovascular and neurological diseases. Polysomnography (PSG) is a commonly used diagnostic device for SA. But it requires suspected patients to sleep in the lab for one to two nights and records about 16 signals through expert monitoring. The complex processes hinder the widespread implementation of PSG in public health applications. Recently, some researchers have proposed using a single-lead ECG signal for SA detection. These methods are based on the hypothesis that the SA relies only on the current ECG signal segment. However, SA has time dependence; that is, the SA of the ECG segment at the previous moment has an impact on the current SA diagnosis. In this study, we develop a time window artificial neural network that can take advantage of the time dependence between ECG signal segments and does not require any prior assumptions about the distribution of training data. By verifying on a real ECG signal dataset, the performance of our method has been significantly improved compared to traditional non-time window machine learning methods as well as previous works.

Sleep apnea detection from a single-lead ECG signal with automatic feature-extraction through a modified LeNet-5 convolutional neural network

Sleep apnea (SA) is the most common respiratory sleep disorder, leading to some serious neurological and cardiovascular diseases if left untreated. The diagnosis of SA is traditionally made using Polysomnography (PSG). However, this method requires many electrodes and wires, as well as an expert to monitor the test. Several researchers have proposed instead using a single channel signal for SA diagnosis. Among these options, the ECG signal is one of the most physiologically relevant signals of SA occurrence, and one that can be easily recorded using a wearable device. However, existing ECG signal-based methods mainly use features (i.e. frequency domain, time domain, and other nonlinear features) acquired from ECG and its derived signals in order to construct the model. This requires researchers to have rich experience in ECG, which is not common. A convolutional neural network (CNN) is a kind of deep neural network that can automatically learn effective feature representation from training data and has been successfully applied in many fields. Meanwhile, most studies have not considered the impact of adjacent segments on SA detection. Therefore, in this study, we propose a modified LeNet-5 convolutional neural network with adjacent segments for SA detection. Our experimental results show that our proposed method is useful for SA detection, and achieves better or comparable results when compared with traditional machine learning methods.

Wearable Finger Pulse Oximetry for Continuous Oxygen Saturation Measurements During Daily Home Routines of Patients With Chronic Obstructive Pulmonary Disease (COPD) Over One Week: Observational Study

BACKGROUND

Chronic obstructive pulmonary disease (COPD) patients can suffer from low blood oxygen concentrations. Peripheral blood oxygen saturation (SpO2), as assessed by pulse oximetry, is commonly measured during the day using a spot check, or continuously during one or two nights to estimate nocturnal desaturation. Sampling at this frequency may overlook natural fluctuations in SpO2.

OBJECTIVE

This study used wearable finger pulse oximeters to continuously measure SpO2 during daily home routines of COPD patients and assess natural SpO2 fluctuations.

METHODS

A total of 20 COPD patients wore a WristOx2 pulse oximeter for 1 week to collect continuous SpO2 measurements. A SenseWear Armband simultaneously collected actigraphy measurements to provide contextual information. SpO2 time series were preprocessed and data quality was assessed afterward. Mean SpO2, SpO2 SD, and cumulative time spent with SpO2 below 90% (CT90) were calculated for every (1) day, (2) day in rest, and (3) night to assess SpO2 fluctuations.

RESULTS

A high percentage of valid SpO2 data (daytime: 93.27%; nocturnal: 99.31%) could be obtained during a 7-day monitoring period, except during moderate-to-vigorous physical activity (MVPA) (67.86%). Mean nocturnal SpO2 (89.9%, SD 3.4) was lower than mean daytime SpO2 in rest (92.1%, SD 2.9; P<.001). On average, SpO2 in rest ranged over 10.8% (SD 4.4) within one day. Highly varying CT90 values between different nights led to 50% (10/20) of the included patients changing categories between desaturator and nondesaturator over the course of 1 week.

CONCLUSIONS

Continuous SpO2 measurements with wearable finger pulse oximeters identified significant SpO2 fluctuations between and within multiple days and nights of patients with COPD. Continuous SpO2 measurements during daily home routines of patients with COPD generally had high amounts of valid data, except for motion artifacts during MVPA. The identified fluctuations can have implications for telemonitoring applications that are based on daily SpO2 spot checks. CT90 values can vary greatly from night to night in patients with a nocturnal mean SpO2 around 90%, indicating that these patients cannot be consistently categorized as desaturators or nondesaturators. We recommend using wearable sensors for continuous SpO2 measurements over longer time periods to determine the clinical relevance of the identified SpO2 fluctuations.

Oximetry use in obstructive sleep apnea

INTRODUCTION

Overnight oximetry has been proposed as an accessible, simple, and reliable technique for obstructive sleep apnea syndrome (OSAS) diagnosis. From visual inspection to advanced signal processing, several studies have demonstrated the usefulness of oximetry as a screening tool. However, there is still controversy regarding the general application of oximetry as a single screening methodology for OSAS. Areas covered: Currently, high-resolution portable devices combined with pattern recognition-based applications are able to achieve high performance in the detection of this disease. In this review, recent studies involving automated analysis of oximetry by means of advanced signal processing and machine learning algorithms are analyzed. Advantages and limitations are highlighted and novel research lines aimed at improving the screening ability of oximetry are proposed. Expert commentary: Oximetry is a cost-effective tool for OSAS screening in patients showing high pretest probability for the disease. Nevertheless, exhaustive analyses are still needed to further assess unattended oximetry monitoring as a single diagnostic test for sleep apnea, particularly in the pediatric population and in populations with significant comorbidities. In the following years, communication technologies and big data analyses will overcome current limitations of simplified sleep testing approaches, changing the detection and management of OSAS.

Automatic Detection of Obstructive Sleep Apnea Using Wavelet Transform and Entropy-Based Features From Single-Lead ECG Signal

Obstructive sleep apnea (OSA) is a prevalent sleep disorder and highly affects the quality of human life. Currently, gold standard for OSA detection is polysomnogram. Since this method is time consuming and cost inefficient, practical systems focus on the usage of electrocardiogram (ECG) signals for OSA detection. In this paper, a novel automatic OSA detection method using a single-lead ECG signal has been proposed. A nonlinear feature extraction using wavelet transform (WT) coefficients obtained by an ECG signal decomposition is employed. In addition, different classification methods are investigated. ECG signals are decomposed into eight levels using a Symlet function as a mother Wavelet function with third order. Then, the entropy-based features including fuzzy/approximate/sample/correct conditional entropy as well as other nonlinear features including interquartile range, mean absolute deviation, variance, Poincare plot, and recurrence plot are extracted from WT coefficients. The best features are chosen using the automatic sequential forward feature selection algorithm. In order to assess the introduced method, 95 single-lead ECG recordings are used. The support vector machine classifier having a radial basis function kernel leads to an accuracy of 94.63% (sensitivity: 94.43% and specificity: 94.77%) and 95.71% (sensitivity: 95.83% and specificity: 95.66%) for minute-by-minute and subject-by-subject classifications, respectively. The results show that applying entropy-based features for extracting hidden information of the ECG signals outperforms other available automatic OSA detection methods. The results indicate that a highly accurate OSA detection is attained by just exploiting the single-lead ECG signals. Furthermore, due to the low computational load in the proposed method, it can easily be applied to the home monitoring systems.

Assessment of automated analysis of portable oximetry as a screening test for moderate-to-severe sleep apnea in patients with chronic obstructive pulmonary disease

BACKGROUND

The coexistence of obstructive sleep apnea syndrome (OSAS) and chronic obstructive pulmonary disease (COPD) leads to increased morbidity and mortality. The development of home-based screening tests is essential to expedite diagnosis. Nevertheless, there is still very limited evidence on the effectiveness of portable monitoring to diagnose OSAS in patients with pulmonary comorbidities.

OBJECTIVE

To assess the influence of suffering from COPD in the performance of an oximetry-based screening test for moderate-to-severe OSAS, both in the hospital and at home.

METHODS

A total of 407 patients showing moderate-to-high clinical suspicion of OSAS were involved in the study. All subjects underwent (i) supervised portable oximetry simultaneously to in-hospital polysomnography (PSG) and (ii) unsupervised portable oximetry at home. A regression-based multilayer perceptron (MLP) artificial neural network (ANN) was trained to estimate the apnea-hypopnea index (AHI) from portable oximetry recordings. Two independent validation datasets were analyzed: COPD versus non-COPD.

RESULTS

The portable oximetry-based MLP ANN reached similar intra-class correlation coefficient (ICC) values between the estimated AHI and the actual AHI for the non-COPD and the COPD groups either in the hospital (non-COPD: 0.937, 0.909-0.956 CI95%; COPD: 0.936, 0.899-0.960 CI95%) and at home (non-COPD: 0.731, 0.631-0.808 CI95%; COPD: 0.788, 0.678-0.864 CI95%). Regarding the area under the receiver operating characteristics curve (AUC), no statistically significant differences (p >0.01) between COPD and non-COPD groups were found in both settings, particularly for severe OSAS (AHI ≥30 events/h): 0.97 (0.92-0.99 CI95%) non-COPD vs. 0.98 (0.92-1.0 CI95%) COPD in the hospital, and 0.87 (0.79-0.92 CI95%) non-COPD vs. 0.86 (0.75-0.93 CI95%) COPD at home.

CONCLUSION

The agreement and the diagnostic performance of the estimated AHI from automated analysis of portable oximetry were similar regardless of the presence of COPD both in-lab and at-home. Particularly, portable oximetry could be used as an abbreviated screening test for moderate-to-severe OSAS in patients with COPD.

Sleep apnea: a review of diagnostic sensors, algorithms, and therapies

While public awareness of sleep related disorders is growing, sleep apnea syndrome (SAS) remains a public health and economic challenge. Over the last two decades, extensive controlled epidemiologic research has clarified the incidence, risk factors including the obesity epidemic, and global prevalence of obstructive sleep apnea (OSA), as well as establishing a growing body of literature linking OSA with cardiovascular morbidity, mortality, metabolic dysregulation, and neurocognitive impairment. The US Institute of Medicine Committee on Sleep Medicine estimates that 50-70 million US adults have sleep or wakefulness disorders. Furthermore, the American Academy of Sleep Medicine (AASM) estimates that more than 29 million US adults suffer from moderate to severe OSA, with an estimated 80% of those individuals living unaware and undiagnosed, contributing to more than $149.6 billion in healthcare and other costs in 2015. Although various devices have been used to measure physiological signals, detect apneic events, and help treat sleep apnea, significant opportunities remain to improve the quality, efficiency, and affordability of sleep apnea care. As our understanding of respiratory and neurophysiological signals and sleep apnea physiological mechanisms continues to grow, and our ability to detect and process biomedical signals improves, novel diagnostic and treatment modalities emerge.

OBJECTIVE

This article reviews the current engineering approaches for the detection and treatment of sleep apnea.

APPROACH

It discusses signal acquisition and processing, highlights the current nonsurgical and nonpharmacological treatments, and discusses potential new therapeutic approaches.

MAIN RESULTS

This work has led to an array of validated signal and sensor modalities for acquiring, storing and viewing sleep data; a broad class of computational and signal processing approaches to detect and classify SAS disease patterns; and a set of distinctive therapeutic technologies whose use cases span the continuum of disease severity.

SIGNIFICANCE

This review provides a current perspective of the classes of tools at hand, along with a sense of their relative strengths and areas for further improvement.

An Obstructive Sleep Apnea Detection Approach Using a Discriminative Hidden Markov Model From ECG Signals

Obstructive sleep apnea (OSA) syndrome is a common sleep disorder suffered by an increasing number of people worldwide. As an alternative to polysomnography (PSG) for OSA diagnosis, the automatic OSA detection methods used in the current practice mainly concentrate on feature extraction and classifier selection based on collected physiological signals. However, one common limitation in these methods is that the temporal dependence of signals are usually ignored, which may result in critical information loss for OSA diagnosis. In this study, we propose a novel OSA detection approach based on ECG signals by considering temporal dependence within segmented signals. A discriminative hidden Markov model (HMM) and corresponding parameter estimation algorithms are provided. In addition, subject-specific transition probabilities within the model are employed to characterize the subject-to-subject differences of potential OSA patients. To validate our approach, 70 recordings obtained from the Physionet Apnea-ECG database were used. Accuracies of 97.1% for per-recording classification and 86.2% for per-segment OSA detection with satisfactory sensitivity and specificity were achieved. Compared with other existing methods that simply ignore the temporal dependence of signals, the proposed HMM-based detection approach delivers more satisfactory detection performance and could be extended to other disease diagnosis applications.

A REVIEW OF ECG-BASED DIAGNOSIS SUPPORT SYSTEMS FOR OBSTRUCTIVE SLEEP APNEA

Humans need sleep. It is important for physical and psychological recreation. During sleep our consciousness is suspended or least altered. Hence, our ability to avoid or react to disturbances is reduced. These disturbances can come from external sources or from disorders within the body. Obstructive Sleep Apnea (OSA) is such a disorder. It is caused by obstruction of the upper airways which causes periods where the breathing ceases. In many cases, periods of reduced breathing, known as hypopnea, precede OSA events. The medical background of OSA is well understood, but the traditional diagnosis is expensive, as it requires sophisticated measurements and human interpretation of potentially large amounts of physiological data. Electrocardiogram (ECG) measurements have the potential to reduce the cost of OSA diagnosis by simplifying the measurement process. On the down side, detecting OSA events based on ECG data is a complex task which requires highly skilled practitioners. Computer algorithms can help to detect the subtle signal changes which indicate the presence of a disorder. That approach has the following advantages: computers never tire, processing resources are economical and progress, in the form of better algorithms, can be easily disseminated as updates over the internet. Furthermore, Computer-Aided Diagnosis (CAD) reduces intra- and inter-observer variability. In this review, we adopt and support the position that computer based ECG signal interpretation is able to diagnose OSA with a high degree of accuracy.

Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome

The relationship between sleep apnoea-hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea-hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.

Automated detection of sleep apnea in infants using minimally invasive sensors

To address the difficult and necessity of early detection of sleep apnea hypopnea syndrome in infants, we present a study into the effectiveness of pulse oximetry as a minimally invasive means of automated diagnosis of sleep apnea in infants. Overnight polysomnogram data from 328 infants were used to extract time-domain based oximetry features and scored arousal data for each subject. These records were then used to determine apnea events and to train a classifier model based on linear discriminants. Performance of the classifier was evaluated using a leave-one-out cross-validation scheme and an accuracy of 68% was achieved, with a specificity of 68.6% and a sensitivity of 55.9%.

Automated detection of sleep apnea in infants: A multi-modal approach

This study explores the use and applicability of two minimally invasive sensors, electrocardiogram (ECG) and pulse oximetry, in addressing the high costs and difficulty associated with the early detection of sleep apnea hypopnea syndrome in infants. An existing dataset of 396 scored overnight polysomnography recordings were used to train and test a linear discriminants classifier. The dataset contained data from healthy infants, infants diagnosed with sleep apnea, infants with siblings who had died from sudden infant death syndrome (SIDS) and pre-term infants. Features were extracted from the ECG and pulse-oximetry data and used to train the classifier. The performance of the classifier was evaluated using a leave-one-out cross-validation scheme and an accuracy of 66.7% was achieved, with a specificity of 67.0% and a sensitivity of 58.1%. Although the performance of the system is not yet at the level required for clinical use, this work forms an important step in demonstrating the validity and potential for such low-cost and minimally invasive diagnostic systems.

Resting state functional magnetic resonance imaging and neural network classified autism and control

Although the neurodevelopmental and genetic underpinnings of autism spectrum disorder (ASD) have been investigated, the etiology of the disorder has remained elusive, and clinical diagnosis continues to rely on symptom-based criteria. In this study, to classify both control subjects and a large sample of patients with ASD, we used resting state functional magnetic resonance imaging (rs-fMRI) and a neural network. Imaging data from 312 subjects with ASD and 328 subjects with typical development was downloaded from the multi-center research project. Only subjects under 20 years of age were included in this analysis. Correlation matrices computed from rs-fMRI time-series data were entered into a probabilistic neural network (PNN) for classification. The PNN classified the two groups with approximately 90% accuracy (sensitivity = 92%, specificity = 87%). The accuracy of classification did not differ among the institutes, or with respect to experimental and imaging conditions, sex, handedness, or intellectual level. Medication status and degree of head movement did not affect accuracy values. The present study indicates that an intrinsic connectivity matrix produced from rs-fMRI data could yield a possible biomarker of ASD. These results support the view that altered network connectivity within the brain contributes to the neurobiology of ASD.

Empirical mode decomposition and neural network for the classification of electroretinographic data

The processing of biosignals is increasingly being utilized in ambulatory situations in order to extract significant signals' features that can help in clinical diagnosis. However, this task is hampered by the fact that biomedical signals exhibit a complex behavior characterized by strong nonlinear and non-stationary properties that cannot always be perceived by simple visual examination. New processing methods need be considered. In this context, we propose a signal processing method, based on empirical mode decomposition and artificial neural networks, to analyze electroretinograms, i.e., the retinal response to a light flash, with the aim to detect and classify retinal diseases. The present application focuses on two retinal pathologies: achromatopsia, which is a cone disease, and congenital stationary night blindness, which affects the photoreceptoral signal transmission. The results indicate that, under suitable conditions, the method proposed here has the potential to provide a powerful tool for routine clinical examinations, since it is able to recognize with high level of confidence the eventual presence of one of the two pathologies.

Application of gene expression programming and neural networks to predict adverse events of radical hysterectomy in cervical cancer patients

The aim of this article was to compare gene expression programming (GEP) method with three types of neural networks in the prediction of adverse events of radical hysterectomy in cervical cancer patients. One-hundred and seven patients treated by radical hysterectomy were analyzed. Each record representing a single patient consisted of 10 parameters. The occurrence and lack of perioperative complications imposed a two-class classification problem. In the simulations, GEP algorithm was compared to a multilayer perceptron (MLP), a radial basis function network neural, and a probabilistic neural network. The generalization ability of the models was assessed on the basis of their accuracy, the sensitivity, the specificity, and the area under the receiver operating characteristic curve (AUROC). The GEP classifier provided best results in the prediction of the adverse events with the accuracy of 71.96 %. Comparable but slightly worse outcomes were obtained using MLP, i.e., 71.87 %. For each of measured indices: accuracy, sensitivity, specificity, and the AUROC, the standard deviation was the smallest for the models generated by GEP classifier.