Comparability of pulse oximeters used in sleep medicine for the screening of OSA

Deep learning for obstructive sleep apnea diagnosis based on single channel oximetry

Obstructive sleep apnea (OSA) is a serious medical condition with a high prevalence, although diagnosis remains a challenge. Existing home sleep tests may provide acceptable diagnosis performance but have shown several limitations. In this retrospective study, we used 12,923 polysomnography recordings from six independent databases to develop and evaluate a deep learning model, called OxiNet, for the estimation of the apnea-hypopnea index from the oximetry signal. We evaluated OxiNet performance across ethnicity, age, sex, and comorbidity. OxiNet missed 0.2% of all test set moderate-to-severe OSA patients against 21% for the best benchmark.

International Consensus Statement on Obstructive Sleep Apnea

BACKGROUND

Evaluation and interpretation of the literature on obstructive sleep apnea (OSA) allows for consolidation and determination of the key factors important for clinical management of the adult OSA patient. Toward this goal, an international collaborative of multidisciplinary experts in sleep apnea evaluation and treatment have produced the International Consensus statement on Obstructive Sleep Apnea (ICS:OSA).

METHODS

Using previously defined methodology, focal topics in OSA were assigned as literature review (LR), evidence-based review (EBR), or evidence-based review with recommendations (EBR-R) formats. Each topic incorporated the available and relevant evidence which was summarized and graded on study quality. Each topic and section underwent iterative review and the ICS:OSA was created and reviewed by all authors for consensus.

RESULTS

The ICS:OSA addresses OSA syndrome definitions, pathophysiology, epidemiology, risk factors for disease, screening methods, diagnostic testing types, multiple treatment modalities, and effects of OSA treatment on multiple OSA-associated comorbidities. Specific focus on outcomes with positive airway pressure (PAP) and surgical treatments were evaluated.

CONCLUSION

This review of the literature consolidates the available knowledge and identifies the limitations of the current evidence on OSA. This effort aims to create a resource for OSA evidence-based practice and identify future research needs. Knowledge gaps and research opportunities include improving the metrics of OSA disease, determining the optimal OSA screening paradigms, developing strategies for PAP adherence and longitudinal care, enhancing selection of PAP alternatives and surgery, understanding health risk outcomes, and translating evidence into individualized approaches to therapy.

Screening for Obstructive Sleep Apnea Risk by Using Machine Learning Approaches and Anthropometric Features

Obstructive sleep apnea (OSA) is a global health concern and is typically diagnosed using in-laboratory polysomnography (PSG). However, PSG is highly time-consuming and labor-intensive. We, therefore, developed machine learning models based on easily accessed anthropometric features to screen for the risk of moderate to severe and severe OSA. We enrolled 3503 patients from Taiwan and determined their PSG parameters and anthropometric features. Subsequently, we compared the mean values among patients with different OSA severity and considered correlations among all participants. We developed models based on the following machine learning approaches: logistic regression, k-nearest neighbors, naïve Bayes, random forest (RF), support vector machine, and XGBoost. Collected data were first independently split into two data sets (training and validation: 80%; testing: 20%). Thereafter, we adopted the model with the highest accuracy in the training and validation stage to predict the testing set. We explored the importance of each feature in the OSA risk screening by calculating the Shapley values of each input variable. The RF model achieved the highest accuracy for moderate to severe (84.74%) and severe (72.61%) OSA. The level of visceral fat was found to be a predominant feature in the risk screening models of OSA with the aforementioned levels of severity. Our machine learning models can be employed to screen for OSA risk in the populations in Taiwan and in those with similar craniofacial structures.

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.

The uses of overnight pulse oximetry

Overnight pulse oximetry (OPO) has proven to be an effective and beneficial technique to determine the cardiorespiratory status of patients in both the inpatient and outpatient settings. It is a cheap, safe, reliable, simple, and accurate method of patient monitoring as compared to the expensive and labor-intensive method of multichannel polysomnography for detecting sleep-disordered breathing. It provides accurate information about patient's oxygenation status and also helps in monitoring the response to continuous positive airway pressure and in the surgical treatment of obstructive sleep apnea (OSA). Nocturnal hypoxemia portends a poor prognosis in patients of chronic obstructive pulmonary disease (COPD), interstitial lung disease (ILD), and neuromuscular diseases. OPO can help its early detection and management.

Sleep-wake stages classification using heart rate signals from pulse oximetry

The most important index of obstructive sleep apnea/hypopnea syndrome (OSAHS) is the apnea/hyponea index (AHI). The AHI is the number of apnea/hypopnea events per hour of sleep. Algorithms for the screening of OSAHS from pulse oximetry estimate an approximation to AHI counting the desaturation events without consider the sleep stage of the patient. This paper presents an automatic system to determine if a patient is awake or asleep using heart rate (HR) signals provided by pulse oximetry. In this study, 70 features are estimated using entropy and complexity measures, frequency domain and time-scale domain methods, and classical statistics. The dimension of feature space is reduced from 70 to 40 using three different schemes based on forward feature selection with support vector machine and feature importance with random forest. The algorithms were designed, trained and tested with 5000 patients from the Sleep Heart Health Study database. In the test stage, 10-fold cross validation method was applied obtaining performances up to 85.2% accuracy, 88.3% specificity, 79.0% sensitivity, 67.0% positive predictive value, and 91.3% negative predictive value. The results are encouraging, showing the possibility of using HR signals obtained from the same oximeter to determine the sleep stage of the patient, and thus potentially improving the estimation of AHI based on only pulse oximetry.

Oximetry as an Accurate Tool for Identifying Moderate to Severe Sleep Apnea in Patients With Acute Stroke

STUDY OBJECTIVES

Sleep-disordered breathing (SDB) is highly prevalent in patients with acute stroke. SDB is often underdiagnosed and associated with neurological deterioration and stroke recurrence. Polysomnography or home sleep apnea testing (HSAT) is typically used as the diagnostic modality; however, it may not be feasible to use regularly in patients with acute stroke. We investigated the predictive performance of pulse oximetry, a simpler alternative, to identify SDB.

METHODS

The records of 254 patients, who were admitted to Boston Medical Center for acute stroke and underwent HSAT, were retrospectively reviewed. Oxygen desaturation index (ODI) from pulse oximetry channel were compared to respiratory event index (REI) obtained from HSAT devices. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of ODI were calculated, and different ODI cutoff values to predict SDB were proposed.

RESULTS

ODI had a strong correlation (r = .902) and agreement with REI. ODI was accurate in predicting SDB at different REI thresholds (REI ≥ 5, REI ≥ 15, and REI ≥ 30 events/h) with the area under the curve (AUC) of .965, .974, and .951, respectively. An ODI ≥ 5 events/h rules in the presence of SDB (specificity 91.7%, PPV 96.3%). An ODI ≥ 15 events/h rules in moderate to severe SDB (specificity 96.4%, PPV 95%) and an ODI < 5 events/h rules out moderate to severe SDB (sensitivity 100%, NPV 100%).

CONCLUSIONS

Nocturnal pulse oximetry has a high diagnostic accuracy in predicting moderate to severe SDB in patients with acute stroke. Oximetry can be a simple modality to rapidly recognize patients with more severe SDB and facilitate the referral to the confirmation sleep study.

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.

Sleep devices: wearables and nearables, informational and interventional, consumer and clinical

The field of sleep is in many ways ideally positioned to take full advantage of advancements in technology and analytics that is fueling the mobile health movement. Combining hardware and software advances with increasingly available big datasets that contain scored data obtained under gold standard sleep laboratory conditions completes the trifecta of this perfect storm. This review highlights recent developments in consumer and clinical devices for sleep, emphasizing the need for validation at multiple levels, with the ultimate goal of using personalized data and advanced algorithms to provide actionable information that will improve sleep health.

Nocturnal Oximetry-based Evaluation of Habitually Snoring Children

RATIONALE

The vast majority of children around the world undergoing adenotonsillectomy for obstructive sleep apnea-hypopnea syndrome (OSA) are not objectively diagnosed by nocturnal polysomnography because of access availability and cost issues. Automated analysis of nocturnal oximetry (nSp_O2), which is readily and globally available, could potentially provide a reliable and convenient diagnostic approach for pediatric OSA.

METHODS

Deidentified nSp_O2 recordings from a total of 4,191 children originating from 13 pediatric sleep laboratories around the world were prospectively evaluated after developing and validating an automated neural network algorithm using an initial set of single-channel nSp_O2 recordings from 589 patients referred for suspected OSA.

MEASUREMENTS AND MAIN RESULTS

The automatically estimated apnea-hypopnea index (AHI) showed high agreement with AHI from conventional polysomnography (intraclass correlation coefficient, 0.785) when tested in 3,602 additional subjects. Further assessment on the widely used AHI cutoff points of 1, 5, and 10 events/h revealed an incremental diagnostic ability (75.2, 81.7, and 90.2% accuracy; 0.788, 0.854, and 0.913 area under the receiver operating characteristic curve, respectively).

CONCLUSIONS

Neural network-based automated analyses of nSp_O2 recordings provide accurate identification of OSA severity among habitually snoring children with a high pretest probability of OSA. Thus, nocturnal oximetry may enable a simple and effective diagnostic alternative to nocturnal polysomnography, leading to more timely interventions and potentially improved outcomes.

The watch-pat in pediatrics sleep disordered breathing: Pilot study on children with negative nocturnal pulse oximetry

OBJECTIVES

The main purpose of this study was to determine the efficacy of Watch-PAT in Pediatric Sleep Disordered Breathing (PSDB) diagnosis in children with symptoms suggestive of PSDB, in which the nocturnal pulse oximetry was negative according to the Brouilette criteria.

METHODS

We enrolled 28 patients aged between 5 and 12 years (mean age: 7.75 ± 1.69), who underwent the registration with Watch-PAT, that utilizes the Peripheral Arterial Tone (PAT), AHI, RDI, body position, snoring, pulse oximetry and actigraphy.

RESULTS

Recording Watch-PAT was indicative of PSDB in 10/28 (35.7%) patients; when it was placed the threshold of AHI > 1 the number of positive patients for PSDB increased to 17/28 (60.7%). Exists a positive correlation between pat-RDI (rho = 0.798, p = 0.005) and the snoring > 40% of the time (rho = 0.656, p < 0.001) were correlated with the pat-AHI values.

CONCLUSION

The recording Watch-PAT appears to permit the defection of a certain number of SDB that might escape to the clinical evaluation and pulse oximetry only.

Automated Screening of Children With Obstructive Sleep Apnea Using Nocturnal Oximetry: An Alternative to Respiratory Polygraphy in Unattended Settings

STUDY OBJECTIVES

Nocturnal oximetry has become known as a simple, readily available, and potentially useful diagnostic tool of childhood obstructive sleep apnea (OSA). However, at-home respiratory polygraphy (HRP) remains the preferred alternative to polysomnography (PSG) in unattended settings. The aim of this study was twofold: (1) to design and assess a novel methodology for pediatric OSA screening based on automated analysis of at-home oxyhemoglobin saturation (SpO₂), and (2) to compare its diagnostic performance with HRP.

METHODS

SpO₂ recordings were parameterized by means of time, frequency, and conventional oximetric measures. Logistic regression models were optimized using genetic algorithms (GAs) for three cutoffs for OSA: 1, 3, and 5 events/h. The diagnostic performance of logistic regression models, manual obstructive apnea-hypopnea index (OAHI) from HRP, and the conventional oxygen desaturation index ≥ 3% (ODI3) were assessed.

RESULTS

For a cutoff of 1 event/h, the optimal logistic regression model significantly outperformed both conventional HRP-derived ODI3 and OAHI: 85.5% accuracy (HRP 74.6%; ODI3 65.9%) and 0.97 area under the receiver operating characteristics curve (AUC) (HRP 0.78; ODI3 0.75) were reached. For a cutoff of 3 events/h, the logistic regression model achieved 83.4% accuracy (HRP 85.0%; ODI3 74.5%) and 0.96 AUC (HRP 0.93; ODI3 0.85) whereas using a cutoff of 5 events/h, oximetry reached 82.8% accuracy (HRP 85.1%; ODI3 76.7) and 0.97 AUC (HRP 0.95; ODI3 0.84).

CONCLUSIONS

Automated analysis of at-home SpO₂ recordings provide accurate detection of children with high pretest probability of OSA. Thus, unsupervised nocturnal oximetry may enable a simple and effective alternative to HRP and PSG in unattended settings.

Oxygen Desaturation Index Differs Significantly Between Types of Sleep Software

STUDY OBJECTIVES

The aim of this study was to compare the oxygen desaturation index (ODI) generated by two different sleep software systems.

METHODS

Participants undergoing diagnostic polysomnography for suspected obstructive sleep apnea underwent simultaneous oximetry recording using the ResMed ApneaLink Plus device (AL) and Compumedics Profusion PSG3 system (Comp). The ODI was calculated by the algorithms in the respective software of each system. To determine if differences were due to algorithm or recording devices, the Comp software was also used to generate ODI values using oximetry data from the AL.

RESULTS

In 106 participants, there was good correlation but poor agreement in the ODI generated by the two systems. AL ODI values tended to be higher than Comp ODI values, but with significant variability. For ODI4%, bias was 4.4 events/h (95% limits of agreement -5.8 to 14.6 events/h). There was excellent correlation and agreement when the same oximetry raw data was analyzed by both systems. For ODI4%, bias was 0.03 events/h (95% limits of agreement -2.7 to 2.8 events/h). Similar results were evident when the ODI3% was used.

CONCLUSIONS

There is a clinically significant difference in ODI values generated by the two systems, likely due to device signal processing, rather than difference in ODI calculation algorithms.

Obstructive sleep apnoea in the general population: highly prevalent but minimal symptoms

The aim was to assess the prevalence of obstructive sleep apnoea (OSA) as defined by an apnoea-hypopnea index (AHI) ≥15 in the middle-aged general population, and the interrelationship between OSA, sleep-related symptoms, sleepiness and vigilance.A general population sample of 40-65-year-old Icelanders was invited to participate in a study protocol that included a type 3 sleep study, questionnaire and a psychomotor vigilance test (PVT).Among the 415 subjects included in the study, 56.9% had no OSA (AHI <5), 24.1% had mild OSA (AHI 5-14.9), 12.5% had moderate OSA (AHI 15-29.9), 2.9% had severe OSA (AHI ≥30) and 3.6% were already diagnosed and receiving OSA treatment. However, no significant relationship was found between AHI and subjective sleepiness or clinical symptoms. A relationship with objective vigilance assessed by PVT was only found for those with AHI ≥30. Subjects already on OSA treatment and those accepting OSA treatment after participating in the study were more symptomatic and sleepier than others with similar OSA severity, as assessed by the AHI.In a middle-aged general population, approximately one in five subjects had moderate-to-severe OSA, but the majority of them were neither symptomatic nor sleepy and did not have impaired vigilance.

Diagnostic approaches to respiratory sleep disorders

Sleep disordered breathing (SDB) comprises a number of breathing disturbances occurring during sleep including snoring, the obstructive sleep apnoea/hypopnea syndrome (OSAHS), central sleep apnoea (CSA) and hypoventilation syndromes. This review focuses on sleep disordered breathing and diagnostic approaches in adults, in particular clinical assessment and overnight assessment during sleep. Although diagnostic approaches to respiratory sleep disorders are reasonably straightforward, they do require a degree of clinical acumen when it comes to assessing severity and management options. Diagnosing respiratory sleep disorders on clinical features alone has limitations. Monitoring and measuring respiration during sleep has undergone many advances in the last 40 years in respect of quality and validity, largely regarding OSAHS. Despite the improvement in our diagnostic standards and recognition of sleep disordered breathing, many limitations still need to be overcome. Apart from assessing the individual patient, population screening for sleep disorders continues to preoccupy health professionals and policy makers in many countries. Research in the field is pushing current boundaries in terms of simplifying diagnosis and enhancing screening for sleep disordered breathing in large populations. At present, a number of these newer approaches require further validation.

Type III home sleep testing versus pulse oximetry: is the respiratory disturbance index better than the oxygen desaturation index to predict the apnoea-hypopnoea index measured during laboratory polysomnography?

OBJECTIVES

In its guidelines on the use of portable monitors to diagnose obstructive sleep apnoea, the American Academy of Sleep Medicine endorses home polygraphy with type III devices recording at a minimum airflow the respiratory effort and pulse oximetry, but advises against simple pulse oximetry. However, oximetry is widely available and simple to use in the home. This study was designed to compare the ability of the oxygen desaturation index (ODI) based on oximetry alone with a stand-alone pulse oximeter (SPO) and from the oximetry channel of the ApneaLink Plus (ALP), with the respiratory disturbance index (RDI) based on four channels from the ALP to predict the apnoea-hypopnoea index (AHI) from laboratory polysomnography.

DESIGN

Cross-sectional diagnostic accuracy study.

SETTING

Sleep medicine practice of a multispecialty clinic.

PARTICIPANTS

Patients referred for laboratory polysomnography with suspected sleep apnoea. We enrolled 135 participants with 123 attempting the home sleep testing and 73 having at least 4 hours of satisfactory data from SPO and ALP.

INTERVENTIONS

Participants had home testing performed simultaneously with both a SPO and an ALP. The 2 oximeter probes were worn on different fingers of the same hand. The ODI for the SPO was calculated using Profox software (ODI(SOX)). For the ALP, RDI and ODI were calculated using both technician scoring (RDI(MAN) and ODI(MAN)) and the ALP computer scoring (RDI(RAW) and ODI(RAW)).

RESULTS

The receiver-operator characteristic areas under the curve for AHI ≥ 5 were RDI(MAN) 0.88 (95% confidence limits 0.81-0.96), RDI(RAW) 0.86 (0.76-0.94), ODI(MAN) 0.86 (0.77-0.95), ODI(RAW) 0.84 (0.75-0.93) and ODI(SOX) 0.83 (0.73-0.93).

CONCLUSIONS

We conclude that the RDI and the ODI, measured at home on the same night, give similar predictions of the laboratory AHI, measured on a different night. The differences between the two methods are small compared with the reported night-to-night variation of the AHI.

Use of oximetry as a screening tool for obstructive sleep apnea: a case study in Taiwan

Obstructive sleep apnea (OSA) is a relatively common disease in the general population. Patients with OSA have a high risk of various comorbid medical diseases. Polysomnography (PSG) is the current gold standard for diagnosing OSA but is time consuming and expensive. This study aims to identify a sensitive screening parameter that can be used by clinicians to determine the time of referral for PSG examination in Taiwan. Eighty-seven patients, including 67 males and 20 females, were included in this study. We divided the patients into two groups: training data (n = 58) and testing group (n = 29). Pearson χ(2) test was used to perform bivariate analysis, and a decision tree was used to build a model. The decision model selected the frequency of desaturation > 4% per hour (DI4) as the indicator of OSA influence. The testing data accuracy of the C4.5 decision tree was 82.80%. External data were also used to validate the model reliability. The accuracy of the external data was 95.96%. Approximately one-third of patients with DI4 between 11 and 33 suffered from OSA. This population requires further diagnosis. Oximetry is an important and widely available screening method in Taiwan. This study proposes the need for PSG referral if DI4 is between 11 and 33.

Obstructive sleep apnoea in people with Type 1 diabetes: prevalence and association with micro- and macrovascular complications

AIMS

Few reports have assessed the relationship between Type 1 diabetes and sleep disorders. The purposes of our study were to determine the prevalence of obstructive sleep apnoea in Type 1 diabetes and to compare the clinical profile of people with Type 1 diabetes with or without obstructive sleep apnoea.

METHODS

In this cross sectional study of 67 consecutive people with Type 1 diabetes, we performed polysomnography as part of their yearly check-ups.

RESULTS

In our cohort, with a mean BMI of 25.8 ± 4.7 kg/m(2), the prevalence of obstructive sleep apnoea [apnoea-hypopnoea index (AHI) > 10/h] was 46%. Severe obstructive sleep apnoea (AHI ≥ 30/h) was present in 19% of the patients. We found no significant differences in age, sex, body mass index, HbA1c or Epworth sleepiness scale score between people with or without obstructive sleep apnoea. People with obstructive sleep apnoea had a longer course of diabetes mellitus (P < 0.01) and a higher prevalence of retinopathy (P < 0.01), neuropathy (P = 0.05), cardiovascular disease (P < 0.01) and hypertension (P < 0.01). The occurrence of macrovascular complications was independently associated with the presence of OSA [odds ratio (OR) 8.28; 95% confidence interval (CI), 1.56-43.97; P = 0.013] and the duration of diabetes (OR 1.08; 95% CI, 1.02-1.15; P = 0.01). Moreover, retinopathy was independently associated with OSA (OR 4.54; 95% CI, 1.09-18.82; P = 0.04) and the duration of diabetes (OR 1.09; 95% CI, 1.04-1.15; P = 0.001).

CONCLUSIONS

The prevalence of obstructive sleep apnoea was high in people with Type 1 diabetes. Obstructive sleep apnoea was independently associated with macrovascular complications and retinopathy. Obesity and excessive daytime sleepiness were uncommon in this population.

Consumer sleep monitors: is there a baby in the bathwater?

The rapid expansion of consumer sleep devices is outpacing the validation data necessary to assess the potential use of these devices in clinical and research settings. Common sleep monitoring devices utilize a variety of sensors to track movement as well as cardiac and respiratory physiology. The variety of sensors and user-specific factors offer the potential, at least theoretically, for clinically relevant information. We describe the current challenges for interpretation of consumer sleep monitoring data, since the devices are mainly used in non-medical contexts (consumer use) although medically-definable sleep disorders may commonly occur in this setting. A framework for addressing questions of how certain devices might be useful is offered. We suggest that multistage validation efforts are crucially needed, from the level of sensor data and algorithm output, to extrapolations beyond healthy adults and into other populations and real-world environments.

Screening of obstructive sleep apnea with empirical mode decomposition of pulse oximetry

Detection of desaturations on the pulse oximetry signal is of great importance for the diagnosis of sleep apneas. Using the counting of desaturations, an index can be built to help in the diagnosis of severe cases of obstructive sleep apnea-hypopnea syndrome. It is important to have automatic detection methods that allows the screening for this syndrome, reducing the need of the expensive polysomnography based studies. In this paper a novel recognition method based on the empirical mode decomposition of the pulse oximetry signal is proposed. The desaturations produce a very specific wave pattern that is extracted in the modes of the decomposition. Using this information, a detector based on properly selected thresholds and a set of simple rules is built. The oxygen desaturation index constructed from these detections produces a detector for obstructive sleep apnea-hypopnea syndrome with high sensitivity (0.838) and specificity (0.855) and yields better results than standard desaturation detection approaches.

Automated sleep apnea quantification based on respiratory movement

Obstructive sleep apnea (OSA) is a prevalent and treatable disorder of neurological and medical importance that is traditionally diagnosed through multi-channel laboratory polysomnography(PSG). However, OSA testing is increasingly performed with portable home devices using limited physiological channels. We tested the hypothesis that single channel respiratory effort alone could support automated quantification of apnea and hypopnea events. We developed a respiratory event detection algorithm applied to thoracic strain-belt data from patients with variable degrees of sleep apnea. We optimized parameters on a training set (n=57) and then tested performance on a validation set (n=59). The optimized algorithm correlated significantly with manual scoring in the validation set (R2=0.73 for training set, R2=0.55 for validation set; p<0.05). For dichotomous classification, the AUC was >0.92 and >0.85 using apnea-hypopnea index cutoff values of 5 and 15, respectively. Our findings demonstrate that manually scored AHI values can be approximated from thoracic movements alone. This finding has potential applications for automating laboratory PSG analysis as well as improving the performance of limited channel home monitors.

Automated frequency domain analysis of oxygen saturation as a screening tool for SAHS

Sleep apnea-hypopnea syndrome (SAHS) is significantly underdiagnosed and new screening systems are needed. The analysis of oxygen desaturation has been proposed as a screening method. However, when oxygen saturation (SpO(2)) is used as a standalone single channel device, algorithms working in time domain achieve either a high sensitivity or a high specificity, but not usually both. This limitation arises from the dependence of time-domain analysis on absolute SpO(2) values and the lack of standardized thresholds defined as pathological. The aim of this study is to assess the degree of concordance between SAHS screening using offline frequency domain processing of SpO(2) signals and the apnea-hypopnea index (AHI), and the diagnostic performance of such a new method. SpO(2) signals from 115 subjects were analyzed. Data were divided in a training data set (37) and a test set (78). Power spectral density was calculated and related to the desaturation index scored by physicians. A frequency desaturation index (FDI) was then estimated and its accuracy compared to the classical desaturation index and to the apnea-hypopnea index. The findings point to a high diagnostic agreement: the best sensitivity and specificity values obtained were 83.33% and 80.44%, respectively. Moreover, the proposed method does not rely on absolute SpO(2) values and is highly robust to artifacts.

Effects of obstructive sleep apnea on serum brain-derived neurotrophic factor protein, cortisol, and lipid levels

OBJECTIVES

Obstructive sleep apnea (OSA) is a sleep-disordered breathing leading to vascular endothelial cells dysfunction, cognitive impairment, and abnormal lipid metabolism. serum brain-derived neurotrophic factor (BDNF) protein, cortisol, and lipid levels in OSA were investigated.

MATERIALS AND METHODS

All middle-aged subjects including healthy individuals without signs and symptoms of apnea-hypopnea and ear nose throat (ENT) outpatients were randomly recruited and screened by overnight polysomnogram (PSG). Apnea-hypopnea index (AHI) was used as a criteria to determine subjects to enroll in this program. According to AHI, they were separated into control and OSA groups. A group of 39 OSA patients (AHI ≥ 10 events/h) and 24 control subjects (AHI < 5 events/h) were selected. Serum BDNF protein was analyzed by enzyme-linked immunosorbent assay (ELISA) from venous blood collection at 8:00 a.m. following PSG. Serum cortisol was assayed by enzyme-chemiluminescense immuno assay (ECLIA). Serum lipid profile levels were determined by enzymatic colorimetric and homogeneous method.

RESULTS

Characteristics of OSA patients and control groups including gender, age, AHI, body weight, height, and BMI showed significant differences. Serum BDNF protein, cortisol, triglyceride, and total cholesterol levels in OSA and control groups were not significantly different. High density lipoprotein-cholesterol (HDL-c) in OSA was significantly lower than that of control (p = 0.008) while low density lipoprotein-cholesterol (LDL-c) was significantly higher than that of control (p = 0.04).

CONCLUSIONS

OSA had no significant effect on serum BDNF, cortisol, triglyceride, or total cholesterol levels while LDL-c and HDL-c levels in OSA patients compared to control were significantly different at p = 0.04, and p = 0.008, respectively.