Oximetry use in obstructive sleep apnea

The use of heart rate variability, oxygen saturation, and anthropometric data with machine learning to predict the presence and severity of obstructive sleep apnea

Introduction

Obstructive sleep apnea (OSA) is a prevalent sleep disorder with a high rate of undiagnosed patients, primarily due to the complexity of its diagnosis made by polysomnography (PSG). Considering the severe comorbidities associated with OSA, especially in the cardiovascular system, the development of early screening tools for this disease is imperative. Heart rate variability (HRV) is a simple and non-invasive approach used as a probe to evaluate cardiac autonomic modulation, with a variety of newly developed indices lacking studies with OSA patients.

Objectives

We aimed to evaluate numerous HRV indices, derived from linear but mainly nonlinear indices, combined or not with oxygen saturation indices, for detecting the presence and severity of OSA using machine learning models.

Methods

ECG waveforms were collected from 291 PSG recordings to calculate 34 HRV indices. Minimum oxygen saturation value during sleep (SatMin), the percentage of total sleep time the patient spent with oxygen saturation below 90% (T90), and patient anthropometric data were also considered as inputs to the models. The Apnea-Hypopnea Index (AHI) was used to categorize into severity classes of OSA (normal, mild, moderate, severe) to train multiclass or binary (normal-to-mild and moderate-to-severe) classification models, using the Random Forest (RF) algorithm. Since the OSA severity groups were unbalanced, we used the Synthetic Minority Over-sampling Technique (SMOTE) to oversample the minority classes.

Results

Multiclass models achieved a mean area under the ROC curve (AUROC) of 0.92 and 0.86 in classifying normal individuals and severe OSA patients, respectively, when using all attributes. When the groups were dichotomized into normal-to-mild OSA vs. moderate-to-severe OSA, an AUROC of 0.83 was obtained. As revealed by RF, the importance of features indicates that all feature modalities (HRV, SpO2, and anthropometric variables) contribute to the top 10 ranks.

Conclusion

The present study demonstrates the feasibility of using classification models to detect the presence and severity of OSA using these indices. Our findings have the potential to contribute to the development of rapid screening tools aimed at assisting individuals affected by this condition, to expedite diagnosis and initiate timely treatment.

Tongue Ultrasonography in the Screening of Severe Obstructive Sleep Apnea Syndrome-Promising Potential for Overloaded Sleep Centers

Obstructive sleep apnea syndrome (OSAS) is a frequently underdiagnosed sleep disorder marked by recurrent episodes of apnea and/or hypopnea during sleep, primarily resulting from the partial or complete collapse of the upper airway. OSAS significantly affects patients' health and quality of life. Additionally, it is a recognized risk factor for inducing microsleep episodes during daily activities, particularly in occupations such as professional driving, where sustained attention is critical. The aim of our study was to identify an effective screening test for use in outpatient settings, capable of distinguishing patients with a severe form of OSAS. Patients who test positive with this screening tool would subsequently be prioritized for polysomnographic evaluation in a sleep laboratory. A total of 64 patients who underwent polysomnography (PSG) or polygraphy (PG) examination at our clinic were subsequently examined by USG of the tongue with measurements of tongue base thickness (TBT) and the distance between lingual arteries (DLA) during wakefulness and in a relaxed tongue position. The measurements of TBT and DLA were subsequently correlated with the apnea-hypopnea index (AHI) obtained from PSG or PG. In our cohort of patients diagnosed with severe OSAS, a TBT threshold of ≥65 mm served as an effective cutoff value. A TBT value of ≥65 mm reached an AUC value of 78.1%, sensitivity of 74.4%, specificity of 61.9%, positive predictive value of 80%, negative predictive value of 54.2% and overall accuracy of 70.3%. A DLA value of ≥30 mm in our sample of patients with severe OSAS showed an AUC of 76.5%, sensitivity of 69.8%, specificity of 71.1%, positive predictive value of 83.3%, negative predictive value of 53.6%, and overall accuracy of 70.3%. Tongue USG markers, particularly TBT and DLA measurements during wakefulness and in a relaxed tongue position, show potential as effective screening tools for identifying severe OSAS in European populations. These markers demonstrate improved accuracy over traditional screening questionnaires by reducing the likelihood of false-negative results. Patients with a positive screening should preferably be referred for polysomnography. In this way, patients with a serious illness could receive adequate therapy sooner.

Morphometric measures and desaturations: Proposal for an index with improved accuracy for obstructive sleep apnea screening

STUDY OBJECTIVE

To evaluate the sensitivity and specificity of the combined Kushida morphometric model (KMM) and the oxygen desaturation index (ODI) for screening individuals with obstructive sleep apnea.

METHODS

Diagnostic test study with adults >18 years, both sexes, polysomnography, body mass index, neck circumference and intraoral measurements.

RESULTS

144 patients were invited; of these, 75 met the exclusion criteria. 55 individuals presented AHI ≥5 ev/h and 14, an AHI <5 ev/h. Three AHI cut-off points were evaluated: AHI ≥5, ≥15, ≥30 ev/h. When adopting the cut-off point of AHI ≥5 ev/h, the KMM showed sensitivity (SE) = 60.0 %, specificity (SP) = 71.4 % and 95 % confidence interval of the area under the curve (95 % CI of AUC) = 0.655; the combination of KMM and ODI (KMM + ODI) revealed SE = 73.0 %, SP = 71.4 % (95 % CI of AUC = 0.779) and the ODI showed SE = 76.4 % and SP = 92.9 % (95 % CI of AUC = 0.815). At the cut-off point of AHI ≥15 ev/h, the KMM presented SE = 64.1 %, SP = 76.7 % (95 % CI of AUC = 0.735); the KMM + ODI showed SE = 82.1 %, SP = 83.3 % (95 % CI of AUC = 0.895); and the ODI presented SE = 76.9 %, SP = 100.0 % (95 % CI of AUC = 0.903). For the cut-off point of AHI ≥30 ev/h, the KMM showed SE = 56.0 %, SP = 77.2 % (95 % CI of AUC = 0.722); the KMM + ODI revealed SE = 92.0 %, SP = 79.5 % (95 % CI of AUC = 0.926); and the ODI showed SE = 92.0 %, SP = 90.9 % (95 % CI of AUC = 0.941).

CONCLUSION

The combination of oxygen desaturation index and Kushida morphometric model improved the sensitivity and specificity of this model regardless of obstructive sleep apnea severity suggesting greater effectiveness in risk prediction.

A narrative review on obstructive sleep apnoea syndrome in paediatric population

Obstructive sleep apnoea syndrome is a respiratory sleep disorder that affects 1-5% of children. It occurs equally in males and females, with higher incidence in school age and adolescence. OSAS may be caused by several factors, but in children, adenotonsillar hypertrophy, obesity, and maxillo-mandibular deficits are the most common. In general, there is a reduction in the diameter of the airway with reduced airflow. This condition worsens during sleep due to the muscular hypotonia, resulting in apnoeas or hypoventilation. While snoring is the primary symptom, OSAS-related manifestations have a wide spectrum. Some of these symptoms relate to the nocturnal phase, including disturbed sleep, frequent changes of position, apnoeas and oral respiration. Other symptoms concern the daytime hours, such as drowsiness, irritability, inattention, difficulties with learning and memorisation, and poor school performance, especially in patient suffering from overlapping syndromes (e.g., Down syndrome). In some cases, the child's general growth may also be affected. Early diagnosis of this condition is crucial in limiting associated symptoms that can significantly impact a paediatric patient's quality of life, with the potential for the condition to persist into adulthood. Diagnosis involves evaluating several aspects, beginning with a comprehensive anamnesis that includes specific questionnaires, followed by an objective examination. This is followed by instrumental diagnosis, for which polysomnography is considered the gold standard, assessing several parameters, including the apnoea-hypopnoea index (AHI) and oxygen saturation. However, it is not the sole tool for assessing the characteristics of this condition. Other possibilities, such as night-time video recording, nocturnal oximetry, can be chosen when polysomnography is not available and even tested at home, even though with a lower diagnostic accuracy. The treatment of OSAS varies depending on the cause. In children, the most frequent therapies are adenotonsillectomy or orthodontic therapies, specifically maxillary expansion.

Yield of overnight pulse oximetry in screening commercial drivers for obstructive sleep apnea

PURPOSE

To assess the efficacy of overnight pulse oximetry in screening male commercial drivers (CDs) for obstructive sleep apnea (OSA).

METHODS

Consecutive male CDs undergoing their annual scheduled occupational health visit were enrolled from ten transportation facilities. All subjects underwent a home sleep apnea test (HSAT) to determine the Respiratory Event Index (REI). Oxygen desaturation indices (ODIs) below the 3% and 4% thresholds were computed using the built-in HSAT pulse oximeter. We then assessed the association between ODI values and the presence of OSA (defined as an REI ≥ 5 events/hour) as well as moderate to severe OSA (REI ≥ 15 events/hour).

RESULTS

Of 331 CDs recruited, 278 (84%) completed the study protocol and 53 subjects were excluded due to inadequate HSAT quality. The included and excluded subjects were comparable in demographics and clinical characteristics. The included CDs had a median age of 49 years (interquartile range (IQR) = 15 years) and a median body mass index of 27 kg/m2 (IQR = 5 kg/m2). One hundred ninety-nine (72%) CDs had OSA, of which 48 (17%) were with moderate OSA and 45 (16%) with severe OSA. The ODI3 and ODI4 receiving operating characteristic curve value were 0.95 for predicting OSA and 0.98-0.96 for predicting moderate to severe OSA.

CONCLUSION

Overnight oxygen oximetry may be an effective means to screen CDs for OSA.

Proposal of a diagnostic algorithm based on the use of pulse oximetry in obstructive sleep apnea

PURPOSE

The aims of this study were to assess the cut-off values for oxygen desaturation index ≥ 3% (ODI3) to confirm obstructive sleep apnea (OSA) in subjects undergoing polysomnography (PSG) and home-based respiratory polygraphy (RP), and to propose an algorithm based on pulse oximetry (PO) for initial management of patients with suspected OSA.

METHODS

This was an observational, cross-sectional, retrospective study. ODI3 was used to classify subjects as healthy (no OSA = AHI < 5 or < 15 events/h) or unhealthy (OSA = AHI ≥ 5 or ≥ 15 events/h). On the PSG or experimental group (Exp-G), we determined ODI3 cut-off values with 100% specificity (Sp) for both OSA definitions. ODI3 values without false positives in the Exp-G were applied to a validation group (Val-G) to assess their performance. A strategy based on PO was proposed in patients with suspected OSA.

RESULTS

In Exp-G (PSG) 1141 patients and in Val-G (RP) 1141 patients were included. In Exp-G, ODI3 > 12 (OSA = AHI ≥ 5) had a sensitivity of 69.5% (CI95% 66.1-72.7) and Sp of 100% (CI95% 99-100), while an ODI3 ≥ 26 had a 53.8% sensitivity (CI95% 49.3-58.2) and Sp of 100% (CI95% 99.4-100) for AHI ≥ 15. A high pretest probability for OSA by Berlin questionaire (≥ 2 categories) had a lower diagnostic performance than by STOP-BANG questionnaire ≥ 5 points (AHI ≥ 5: 0.856 vs. 0.899, p < 0.001; AHI ≥ 15: 0.783 vs. 0.807, p 0.026).

CONCLUSION

We propose the initial use of PO at home in cases of moderate-to-high pretest probability of OSA. This algorithm considers PO as well as RP and PSG for more challenging cases or in case of doubt.

Information Based Similarity Analysis of Oxygen Saturation Recordings to Detect Pulmonary Hypertension in Preterm Infants

Pulmonary hypertension (PH) is a complex cardiovascular condition associated with multiple morbidities and mortality risk in preterm infants. PH often complicates the clinical course of infants who have bronchopulmonary dysplasia (BPD), a more common lung disease in these neonates, causing respiratory deterioration and an even higher risk of mortality. While risk factors and prevalence of PH are not yet well defined, early screening and management of PH in infants with BPD are recommended by consensus guidelines from the American Heart Association. In this study, we propose a screening method for PH by applying a signal analysis technique to oxygen saturation in infants. Oxygen saturation data from infant groups with BPD (41 with and 60 without PH), recorded prior to their clinical PH diagnosis were analyzed in this study. An information-based similarity approach was applied to quantify the regularity of SpO2 fluctuations represented as binary words between adjacent five-minute segments. Similarity indices (SI) were observed to be lower in subjects with PH compared to those with BPD alone (p<0.001). These measures were also assessed for performance in screening for PH. SI of 7-bit words, exhibited 80% detection accuracy, 76% sensitivity and specificity of 83%. This index also exhibited a cross-validated mean (SD) F1-score of 0.80 (0.08) ensuring that sensitivity and recall of the screening were balanced. Similarity analysis of oxygen saturation patterns is a novel technique that can be potentially developed into a signal based early PH detection method to support clinical decision and care in this vulnerable population.

A deep learning model based on the combination of convolutional and recurrent neural networks to enhance pulse oximetry ability to classify sleep stages in children with sleep apnea

Characterization of sleep stages is essential in the diagnosis of sleep-related disorders but relies on manual scoring of overnight polysomnography (PSG) recordings, which is onerous and labor-intensive. Accordingly, we aimed to develop an accurate deep-learning model for sleep staging in children suffering from pediatric obstructive sleep apnea (OSA) using pulse oximetry signals. For this purpose, pulse rate (PR) and blood oxygen saturation (SpO2) from 429 childhood OSA patients were analyzed. A CNN-RNN architecture fed with PR and SpO2 signals was developed to automatically classify wake (W), non-Rapid Eye Movement (NREM), and REM sleep stages. This architecture was composed of: (i) a convolutional neural network (CNN), which learns stage-related features from raw PR and SpO2 data; and (ii) a recurrent neural network (RNN), which models the temporal distribution of the sleep stages. The proposed CNN-RNN model showed a high performance for the automated detection of W/NREM/REM sleep stages (86.0% accuracy and 0.743 Cohen's kappa). Furthermore, the total sleep time estimated for each children using the CNN-RNN model showed high agreement with the manually derived from PSG (intra-class correlation coefficient = 0.747). These results were superior to previous works using CNN-based deep-learning models for automatic sleep staging in pediatric OSA patients from pulse oximetry signals. Therefore, the combination of CNN and RNN allows to obtain additional information from raw PR and SpO2 data related to sleep stages, thus being useful to automatically score sleep stages in pulse oximetry tests for children evaluated for suspected OSA.Clinical Relevance-This research establishes the usefulness of a CNN-RNN architecture to automatically score sleep stages in pulse oximetry tests for pediatric OSA diagnosis.

Machine learning approach for obstructive sleep apnea screening using brain diffusion tensor imaging

Patients with obstructive sleep apnea (OSA) show autonomic, mood, cognitive, and breathing dysfunctions that are linked to increased morbidity and mortality, which can be improved with early screening and intervention. The gold standard and other available methods for OSA diagnosis are complex, require whole-night data, and have significant wait periods that potentially delay intervention. Our aim was to examine whether using faster and less complicated machine learning models, including support vector machine (SVM) and random forest (RF), with brain diffusion tensor imaging (DTI) data can classify OSA from healthy controls. We collected two DTI series from 59 patients with OSA [age: 50.2 ± 9.9 years; body mass index (BMI): 31.5 ± 5.6 kg/m2 ; apnea-hypopnea index (AHI): 34.1 ± 21.2 events/h 23 female] and 96 controls (age: 51.8 ± 9.7 years; BMI: 26.2 ± 4.1 kg/m2 ; 51 female) using a 3.0-T magnetic resonance imaging scanner. Using DTI data, mean diffusivity maps were calculated from each series, realigned and averaged, normalised to a common space, and used to conduct cross-validation for model training and selection and to predict OSA. The RF model showed 0.73 OSA and controls classification accuracy and 0.85 area under the curve (AUC) value on the receiver-operator curve. Cross-validation showed the RF model with comparable fitting over SVM for OSA and control data (SVM; accuracy, 0.77; AUC, 0.84). The RF ML model performs similar to SVM, indicating the comparable statistical fitness to DTI data. The findings indicate that RF model has similar AUC and accuracy over SVM, and either model can be used as a faster OSA screening tool for subjects having brain DTI data.

Improving the management of patients with chronic cardiac and respiratory diseases by extending pulse-oximeter uses: the dynamic pulse-oximetry

Respiratory and cardio-vascular chronic diseases are among the most common noncommunicable diseases (NCDs) worldwide, accounting for a large portion of health-care costs in terms of mortality and disability. Their prevalence is expected to rise further in the coming years as the population ages. The current model of care for diagnosing and monitoring NCDs is out of date because it results in late medical interventions and/or an unfavourable cost-effectiveness balance based on reported symptoms and subsequent inpatient tests and treatments. Health projects and programs are being implemented in an attempt to move the time of an NCD's diagnosis, as well as its monitoring and follow up, out of hospital settings and as close to real life as possible, with the goal of benefiting both patients' quality of life and health system budgets. Following the SARS-CoV-2 pandemic, this implementation received additional impetus. Pulseoximeters (POs) are currently used in a variety of clinical settings, but they can also aid in the telemonitoring of certain patients. POs that can measure activities as well as pulse rate and oxygen saturation as proxies of cardio-vascular and respiratory function are now being introduced to the market. To obtain these data, the devices must be absolutely reliable, that is, accurate and precise, and capable of recording for a long enough period of time to allow for diagnosis. This paper is a review of current pulse-oximetry (POy) use, with the goal of investigating how its current use can be expanded to manage not only cardio-respiratory NCDs, but also acute emergencies with telemonitoring when hospitalization is not required but the patients' situation is debatable. Newly designed devices, both "consumer" and "professional," will be scrutinized, particularly those capable of continuously recording vital parameters on a 24-hour basis and coupling them with daily activities, a practice known as dynamic pulse-oximetry.

Association between various breathing indexes during sleep and the Epworth Sleepiness Scale score in adults

Some breathing indexes during sleep, including the apnea-hypopnea index, oxygen desaturation index, and oxygen saturation during sleep, can be recorded by overnight polysomnography. We aimed to investigate the association of various breathing indexes during sleep with the Epworth Sleepiness Scale (ESS) score in adults. We retrospectively collected the clinical and overnight polysomnography data of 2829 adults aged 20 years or older from November 2011 to June 2017. The association of various breathing indexes during sleep and ESS score was analyzed using univariate and multivariate logistic regression analysis for all adults (20-91 years), and in each sex and of body mass index (<26 kg/m2 vs ≥26 kg/m2). The mean ESS score was 6.2 (standard deviation = 4.3; range = 0-24) for all adults. After adjustment for age, sex, many common diseases, and health-related habits, apnea-hypopnea index, oxygen desaturation index, percentage of oxygen saturation below 90% during sleep, and percentage of oxygen saturation below 85% during sleep were significantly positively associated with ESS score in all adults, whereas mean oxygen saturation during sleep, minimal oxygen saturation during sleep, and awake oxygen saturation during sleep were significantly negatively associated with ESS score in all adults. In subgroup analysis, we found that the association between breathing indexes during sleep and ESS score was similar in both sex, but was significant in subjects of body mass index ≥ 26 kg/m2. All breathing indexes during sleep had significant positive or negative correlation with ESS score in all adults, especially in obese subjects.

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.

Brazilian Thoracic Association Consensus on Sleep-disordered Breathing

Sleep is essential for the proper functioning of all individuals. Sleep-disordered breathing can occur at any age and is a common reason for medical visits. The objective of this consensus is to update knowledge about the main causes of sleep-disordered breathing in adult and pediatric populations, with an emphasis on obstructive sleep apnea. Obstructive sleep apnea is an extremely prevalent but often underdiagnosed disease. It is often accompanied by comorbidities, notably cardiovascular, metabolic, and neurocognitive disorders, which have a significant impact on quality of life and mortality rates. Therefore, to create this consensus, the Sleep-Disordered Breathing Department of the Brazilian Thoracic Association brought together 14 experts with recognized, proven experience in sleep-disordered breathing.

Diagnosis of Obstructive Sleep Apnea in Patients with Associated Comorbidity

Obstructive sleep apnea (OSA) is a heterogeneous disease with many physiological implications. OSA is associated with a great diversity of diseases, with which it shares common and very often bidirectional pathophysiological mechanisms, leading to significantly negative implications on morbidity and mortality. In these patients, underdiagnosis of OSA is high. Concerning cardiorespiratory comorbidities, several studies have assessed the usefulness of simplified screening tests for OSA in patients with hypertension, COPD, heart failure, atrial fibrillation, stroke, morbid obesity, and in hospitalized elders.The key question is whether there is any benefit in the screening for the existence of OSA in patients with comorbidities. In this regard, there are few studies evaluating the performance of the various diagnostic procedures in patients at high risk for OSA. The purpose of this chapter is to review the existing literature about diagnosis in those diseases with a high risk for OSA, with special reference to artificial intelligence-related 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.

Deep-Learning Model Based on Convolutional Neural Networks to Classify Apnea–Hypopnea Events from the Oximetry Signal

Automated analysis of the blood oxygen saturation (SpO₂) signal from nocturnal oximetry has shown usefulness to simplify the diagnosis of obstructive sleep apnea (OSA), including the detection of respiratory events. However, the few preceding studies using SpO₂ recordings have focused on the automated detection of respiratory events versus normal respiration, without making any distinction between apneas and hypopneas. In this sense, the characteristics of oxygen desaturations differ between obstructive apnea and hypopnea episodes. In this chapter, we use the SpO₂ signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and hypopnea events. A total of 398 SpO₂ signals from adult OSA patients were used for this purpose. A CNN architecture was trained using 30-s epochs from the SpO₂ signal for the automatic classification of three classes: normal respiration, apnea, and hypopnea. Then, the apnea index (AI), the hypopnea index (HI), and the apnea-hypopnea index (AHI) were obtained by aggregating the outputs of the CNN for each subject (AI_CNN, HI_CNN, and AHI_CNN). This model showed a promising diagnostic performance in an independent test set, with 80.3% 3-class accuracy and 0.539 3-class Cohen's kappa for the classification of respiratory events. Furthermore, AI_CNN, HI_CNN, and AHI_CNN showed a high agreement with the values obtained from the standard PSG: 0.8023, 0.6774, and 0.8466 intra-class correlation coefficients (ICCs), respectively. This suggests that CNN can be used to analyze SpO₂ recordings for the automated diagnosis of OSA in at-home oximetry tests.

Automatic Sleep Staging in Children with Sleep Apnea using Photoplethysmography and Convolutional Neural Networks

Sleep staging is of paramount importance in children with suspicion of pediatric obstructive sleep apnea (OSA). Complexity, cost, and intrusiveness of overnight polysomnography (PSG), the gold standard, have led to the search for alternative tests. In this sense, the photoplethysmography signal (PPG) carries useful information about the autonomous nervous activity associated to sleep stages and can be easily acquired in pediatric sleep apnea home tests with a pulse oximeter. In this study, we use the PPG signal along with convolutional neural networks (CNN), a deep-learning technique, for the automatic identification of the three main levels of sleep: wake (W), rapid eye movement (REM), and non-REM sleep. A database of 366 PPG recordings from pediatric OSA patients is involved in the study. A CNN architecture was trained using 30-s epochs from the PPG signal for three-stage sleep classification. This model showed a promising diagnostic performance in an independent test set, with 78.2% accuracy and 0.57 Cohen's kappa for W/NREM/REM classification. Furthermore, the percentage of time in wake stage obtained for each subject showed no statistically significant differences with the manually scored from PSG. These results were superior to the only state-of-the-art study focused on the analysis of the PPG signal in the automated detection of sleep stages in children suffering from OSA. This suggests that CNN can be used along with PPG recordings for sleep stages scoring in pediatric home sleep apnea tests.

Ensemble-learning regression to estimate sleep apnea severity using at-home oximetry in adults

Overnight pulse oximetry has shown usefulness to simplify obstructive sleep apnea (OSA) diagnosis when combined with machine-learning approaches. However, the development and evaluation of a single model with ability to reach high diagnostic performance in both community-based non-referral and clinical referral cohorts are still pending. Since ensemble-learning algorithms are known for their generalization ability, we propose a least-squares boosting (LSBoost) model aimed at estimating the apnea-hypopnea index (AHI), as the correlate clinical measure of disease severity. A thorough characterization of 8,762 nocturnal blood-oxygen saturation signals (SpO2) obtained at home was conducted to extract the oximetric information subsequently used in the training, validation, and test stages. The estimated AHI derived from our model achieved high diagnostic ability in both referral and non-referral cohorts reaching intra-class correlation coefficients within 0.889-0.924, and Cohen's κ within 0.478-0.663 when considering the four OSA severity categories. These resulted in accuracies ranging 87.2%-96.6%, 81.1%-87.6%, and 91.6%-94.6% when assessing the three typical AHI severity thresholds, 5 events/hour (e/h), 15 e/h, and 30 e/h, respectively. Our model also revealed the importance of the SpO2 predictors, thereby minimizing the 'black box' perception traditionally attributed to the machine-learning approaches. Furthermore, a decision curve analysis emphasized the clinical usefulness of our proposal. Therefore, we conclude that the LSBoost-based model can foster development of clinically applicable and cost saving protocols for detection of patients attending primary care services, or to avoid full polysomnography in specialized sleep facilities, thus demonstrating the diagnostic usefulness of SpO2 signals obtained at home.

Getting More from the Sleep Recording

Sleep studies have typically followed criteria established many decades ago, but emerging technologies allow signal analyses that go far beyond the scoring rules for manual analysis of sleep recordings. These technologies may apply to the analysis of signals obtained in standard polysomnography in addition to novel signals more recently developed that provide both direct and indirect measures of sleep and breathing in the ambulatory setting. Automated analysis of signals such as electroencephalogram and oxygen saturation, in addition to heart rate and rhythm, provides a wealth of additional information on sleep and breathing disturbances and their potential for comorbidity.

Diagnostic accuracy of oximetry for obstructive sleep apnea: a study on older adults in a home setting

OBJECTIVES

Owing to the fact that obstructive sleep apnea (OSA) is an underreported disease, the strategy used for the diagnosis of OSA has been extensively dissected to devise a simplified process that can be accessed by the public health services. Polysomnography (PSG) type I, the gold standard for the diagnosis of OSA, is expensive and difficult to access by low-income populations. In this study, we aimed to verify the accuracy of the oxyhemoglobin desaturation index (ODI) in comparison to the apnea-hypopnea index (AHI) using a portable monitor.

METHODS

We evaluated 94 type III PSG home test results of 65 elderly patients (69.21±6.94 years old), along with information, such as the body mass index (BMI) and sex, using data obtained from a clinical trial database.

RESULTS

A significant linear positive correlation (r=0.93, p<0.05) was observed between ODI and AHI, without any interference from sex, BMI, and positional component. The sensitivity of ODI compared to that of AHI increased with an increase in the severity of OSA, while the specificity of ODI in comparison to that of AHI was high for all degrees of severity. The accuracy of ODI was 80.7% for distinguishing between patients with mild and moderate apnea and 84.4% for distinguishing between patients with moderate and severe apnea.

CONCLUSION

The ODI values obtained in uncontrolled conditions exhibited high sensitivity for identifying severe apnea compared to the AHI values, and correctly identified the severity of OSA in more than 80% of the cases. Thus, oximetry is promising strategy for diagnosing OSA.

Nocturnal oximetry in bariatric surgery patients referred to overnight in-lab polysomnography

OBJECTIVE

This study aimed to evaluate nocturnal oximetry approaches in identifying obstructive sleep apnea (OSA) among bariatric surgical candidates.

METHODS

This was a cross-sectional study involving adult bariatric patients who were undergoing in-lab polysomnography and who were previously screened with the GOAL questionnaire. OSA severity was established as any OSA, moderate/severe OSA, and severe OSA. Oximetry data were evaluated as oxygen saturation (average and nadir), oxygen desaturation index (ODI) at 3%, and proportion of time spent with oxygen saturation <90%. Associations between oximetry data and the apnea-hypopnea index (AHI) were assessed by Spearman correlation index (r), linear regression, logistic regression, and discrimination.

RESULTS

All oximetry values were significantly correlated with the AHI among 1,178 individuals, with the ODI emerging as the better parameter (r = 0.911, p < 0.001). Using linear regression, the ODI was the only predictor of the AHI (β = 0.952, p < 0.001). In the multivariate analysis, the ODI was the only independent parameter predicting OSA at all severity levels. In addition, the ODI exhibited excellent discrimination to predict OSA and displayed improved performance among individuals screened as being at high risk versus those at low risk with the GOAL instrument.

CONCLUSIONS

The ODI emerges as a valid surrogate predictor of the AHI, particularly among those screened as being at high risk for OSA.

A Convolutional Neural Network Architecture to Enhance Oximetry Ability to Diagnose Pediatric Obstructive Sleep Apnea

This study aims at assessing the usefulness of deep learning to enhance the diagnostic ability of oximetry in the context of automated detection of pediatric obstructive sleep apnea (OSA). A total of 3196 blood oxygen saturation (SpO2) signals from children were used for this purpose. A convolutional neural network (CNN) architecture was trained using 20-min SpO2 segments from the training set (859 subjects) to estimate the number of apneic events. CNN hyperparameters were tuned using Bayesian optimization in the validation set (1402 subjects). This model was applied to three test sets composed of 312, 392, and 231 subjects from three independent databases, in which the apnea-hypopnea index (AHI) estimated for each subject (AHICNN) was obtained by aggregating the output of the CNN for each 20-min SpO2 segment. AHICNN outperformed the 3% oxygen desaturation index (ODI3), a clinical approach, as well as the AHI estimated by a conventional feature-engineering approach based on multi-layer perceptron (AHIMLP). Specifically, AHICNN reached higher four-class Cohen's kappa in the three test databases than ODI3 (0.515 vs 0.417, 0.422 vs 0.372, and 0.423 vs 0.369) and AHIMLP (0.515 vs 0.377, 0.422 vs 0.381, and 0.423 vs 0.306). In addition, our proposal outperformed state-of-the-art studies, particularly for the AHI severity cutoffs of 5 e/h and 10 e/h. This suggests that the information automatically learned from the SpO2 signal by deep-learning techniques helps to enhance the diagnostic ability of oximetry in the context of pediatric OSA.

Screening of obstructive sleep apnea in patients who snore using a patch-type device with electrocardiogram and 3-axis accelerometer

STUDY OBJECTIVES

People with obstructive sleep apnea (OSA) remain undiagnosed because of the lack of easy and comfortable screening tools. Through this study, we aimed to compare the diagnostic accuracy of chest wall motion and cyclic variation of heart rate (CVHR) in detecting OSA by using a single-lead electrocardiogram (ECG) patch with a 3-axis accelerometer.

METHODS

In total, 119 patients who snore simultaneously underwent polysomnography with a single-lead ECG patch. Signals of chest wall motion and CVHR from the single-lead ECG patch were collected. The chest effort index (CEI) was calculated using the chest wall motion recorded by a 3-axis accelerometer in the device. The ability of CEI and CVHR indices in diagnosing moderate-to-severe OSA (apnea-hypopnea index ≥ 15) was compared using the area under the curve (AUC) by using the DeLong test.

RESULTS

CVHR detected moderate-to-severe OSA with 52.9% sensitivity and 94.1% specificity (AUC: 0.76, 95% confidence interval: 0.67-0.84, optimal cutoff: 21.2 events/h). By contrast, CEI identified moderate-to-severe OSA with 80% sensitivity and 79.4% specificity (AUC: 0.87, 95% confidence interval: 0.80-0.94, optimal cutoff: 7.1 events/h). CEI significantly outperformed CVHR regarding the discrimination ability for moderate-to-severe OSA (ΔAUC: 0.11, 95% confidence interval: 0.009-0.21, P = .032). For determining severe OSA, the performance of discrimination ability was greater (AUC = 0.90, 95% confidence interval: 0.85-0.95) when combining these two signals.

CONCLUSIONS

Both CEI and CVHR recorded from a patch-type device with ECG and a 3-axis accelerometer can be used to detect moderate-to-severe OSA. Thus, incorporation of CEI is helpful in the detection of sleep apnea by using a single-lead ECG with a 3-axis accelerometer.

Validation of the Withings ScanWatch as a Wrist-Worn Reflective Pulse Oximeter: Prospective Interventional Clinical Study

BACKGROUND

A decrease in the level of pulse oxygen saturation as measured by pulse oximetry (SpO2) is an indicator of hypoxemia that may occur in various respiratory diseases, such as chronic obstructive pulmonary disease (COPD), sleep apnea syndrome, and COVID-19. Currently, no mass-market wrist-worn SpO2 monitor meets the medical standards for pulse oximeters.

OBJECTIVE

The main objective of this monocentric and prospective clinical study with single-blind analysis was to test and validate the accuracy of the reflective pulse oximeter function of the Withings ScanWatch to measure SpO2 levels at different stages of hypoxia. The secondary objective was to confirm the safety of this device when used as intended.

METHODS

To achieve these objectives, we included 14 healthy participants aged 23-39 years in the study, and we induced several stable plateaus of arterial oxygen saturation (SaO2) ranging from 100%-70% to mimic nonhypoxic conditions and then mild, moderate, and severe hypoxic conditions. We measured the SpO2 level with a Withings ScanWatch on each participant's wrist and the SaO2 from blood samples with a co-oximeter, the ABL90 hemoximeter (Radiometer Medical ApS).

RESULTS

After removal of the inconclusive measurements, we obtained 275 and 244 conclusive measurements with the two ScanWatches on the participants' right and left wrists, respectively, evenly distributed among the 3 predetermined SpO2 groups: SpO2≤80%, 80%

CONCLUSIONS

In conclusion, the Withings ScanWatch is able to measure SpO2 levels with adequate accuracy at a clinical grade. No undesirable effects or adverse events were reported during the study.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04380389; http://clinicaltrials.gov/ct2/show/NCT04380389.

Collapse

Key Words

• COPD
• COVID-19
• SpO2
• Withings ScanWatch
• accuracy
• connected watch
• neural network
• oximeter
• oxygen
• pulse oxygen saturation
• reflective pulse oximeter
• respiratory
• respiratory disease
• safety
• sleep apnea syndrome
• validation
• wearable

Collapse

MESH Headings

• Adult
• Female
• Humans
• Male
• Young Adult
• COVID-19/blood
• COVID-19/complications
• Healthy Volunteers
• Hypoxia/blood
• Hypoxia/complications
• Lung Diseases/blood
• Lung Diseases/complications
• Monitoring, Physiologic
• Oximetry/adverse effects
• Oximetry/standards
• Oxygen/blood
• Prospective Studies
• Single-Blind Method
• Wrist

Collapse

Grants Collapse

Affiliation(s)

Romain Kirszenblat Withings, Issy-Les-Moulineaux, France
Paul Edouard Withings, Issy-Les-Moulineaux, France

Collapse

Correlation between nocturnal oxygen desaturation and glycemic control in diabetic patients with obstructive sleep apnea

Background

Nocturnal hypoxia occurring in obstructive sleep apnea (OSA) is associated with different metabolic disturbances. The present study aims to correlate between nocturnal oxygen desaturation and levels of glycemic control in patients with type 2 diabetes mellitus (T2DM) and undiagnosed OSA.

Results

The present study included 107 patients with T2DM referred for assessment of sleep-related breathing disorder, there were 62 males (57.94%) and 45 females (42.05%), and their age ranged from 42 to 72 years with an average age of 61.29 ± 6.68 years. The patients were divided into 2 groups according to the results of overnight pulse oximetry (OPO) and apnea-hypopnea index (AHI) detected by polysomnography. Group 1 included 68 patients, they had moderate to severe OSA and significant nocturnal desaturation, and group 2 included 39 patients with no or mild OSA. The baseline characteristics of the two groups were not significantly different. Group 1 patients showed significantly higher mean Epworth score and more symptoms related to OSA. There was statistically significant difference between the values of ODI (24.88 ± 9.21 versus 8.94 ± 2.38), AHI (27.10 ± 7.68 versus 9.02 ± 3.90), and hemoglobin A1c levels (8.04 ± 0.64 versus 6.79 ± 0.38) between the two groups. A positive correlation was found between nocturnal oxygen desaturation and levels of HbA1c in group 1 patients reflecting worse glycemic control in patients with moderate to severe OSA.

Conclusion

Nocturnal oxygen desaturation occurring in obstructive sleep apnea is associated with poor glycemic control in patients with type 2 diabetes mellitus.

Trial registration

ClinicalTrials.gov, Protocol ID: OPO10-18. Trial registry number: NCT04711083. Date of registration: 14 January 2021, retrospectively registered.

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.

Technologic advances in the assessment and management of obstructive sleep apnoea beyond the apnoea-hypopnoea index: a narrative review

Obstructive sleep apnoea (OSA) is a growing and serious worldwide health problem with significant health and socioeconomic consequences. Current diagnostic testing strategies are limited by cost, access to resources and over reliance on one measure, namely the apnoea-hypopnoea frequency per hour (AHI). Recent evidence supports moving away from the AHI as the principle measure of OSA severity towards a more personalised approach to OSA diagnosis and treatment that includes phenotypic and biological traits. Novel advances in technology include the use of signals such as heart rate variability (HRV), oximetry and peripheral arterial tonometry (PAT) as alternative or additional measures. Ubiquitous use of smartphones and developments in wearable technology have also led to increased availability of applications and devices to facilitate home screening of at-risk populations, although current evidence indicates relatively poor accuracy in comparison with the traditional gold standard polysomnography (PSG). In this review, we evaluate the current strategies for diagnosing OSA in the context of their limitations, potential physiological targets as alternatives to AHI and the role of novel technology in OSA. We also evaluate the current evidence for using newer technologies in OSA diagnosis, the physiological targets such as smartphone applications and wearable technology. Future developments in OSA diagnosis and assessment will likely focus increasingly on systemic effects of sleep disordered breathing (SDB) such as changes in nocturnal oxygen and blood pressure (BP); and may also include other factors such as circulating biomarkers. These developments will likely require a re-evaluation of the diagnostic and grading criteria for clinically significant OSA.

Assessment of Airflow and Oximetry Signals to Detect Pediatric Sleep Apnea-Hypopnea Syndrome Using AdaBoost

The reference standard to diagnose pediatric Obstructive Sleep Apnea (OSA) syndrome is an overnight polysomnographic evaluation. When polysomnography is either unavailable or has limited availability, OSA screening may comprise the automatic analysis of a minimum number of signals. The primary objective of this study was to evaluate the complementarity of airflow (AF) and oximetry (SpO₂) signals to automatically detect pediatric OSA. Additionally, a secondary goal was to assess the utility of a multiclass AdaBoost classifier to predict OSA severity in children. We extracted the same features from AF and SpO₂ signals from 974 pediatric subjects. We also obtained the 3% Oxygen Desaturation Index (ODI) as a common clinically used variable. Then, feature selection was conducted using the Fast Correlation-Based Filter method and AdaBoost classifiers were evaluated. Models combining ODI 3% and AF features outperformed the diagnostic performance of each signal alone, reaching 0.39 Cohens's kappa in the four-class classification task. OSA vs. No OSA accuracies reached 81.28%, 82.05% and 90.26% in the apnea-hypopnea index cutoffs 1, 5 and 10 events/h, respectively. The most relevant information from SpO₂ was redundant with ODI 3%, and AF was complementary to them. Thus, the joint analysis of AF and SpO₂ enhanced the diagnostic performance of each signal alone using AdaBoost, thereby enabling a potential screening alternative for OSA in children.

A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow

The most appropriate physiological signals to develop simplified as well as accurate screening tests for obstructive sleep apnoea (OSA) remain unknown. This study aimed at assessing whether joint analysis of at-home oximetry and airflow recordings by means of machine-learning algorithms leads to a significant diagnostic performance increase compared to single-channel approaches. Consecutive patients showing moderate-to-high clinical suspicion of OSA were involved. The apnoea-hypopnoea index (AHI) from unsupervised polysomnography was the gold standard. Oximetry and airflow from at-home polysomnography were parameterised by means of 38 time, frequency, and non-linear variables. Complementarity between both signals was exhaustively inspected via automated feature selection. Regression support vector machines were used to estimate the AHI from single-channel and dual-channel approaches. A total of 239 patients successfully completed at-home polysomnography. The optimum joint model reached 0.93 (95%CI 0.90–0.95) intra-class correlation coefficient between estimated and actual AHI. Overall performance of the dual-channel approach (kappa: 0.71; 4-class accuracy: 81.3%) significantly outperformed individual oximetry (kappa: 0.61; 4-class accuracy: 75.0%) and airflow (kappa: 0.42; 4-class accuracy: 61.5%). According to our findings, oximetry alone was able to reach notably high accuracy, particularly to confirm severe cases of the disease. Nevertheless, oximetry and airflow showed high complementarity leading to a remarkable performance increase compared to single-channel approaches. Consequently, their joint analysis via machine learning enables accurate abbreviated screening of OSA at home.

Feasibility of Single Channel Oximetry for Mass Screening of Obstructive Sleep Apnea

BACKGROUND

The growing awareness for the high prevalence of obstructive sleep apnea (OSA) coupled with the dramatic proportion of undiagnosed individuals motivates the elaboration of a simple but accurate screening test. This study assesses, for the first time, the performance of oximetry combined with demographic information as a screening tool for identifying OSA in a representative (i.e. non-referred) population sample.

METHODS

A polysomnography (PSG) clinical database of 887 individuals from a representative population sample of São Paulo's city (Brazil) was used. Using features derived from the oxygen saturation signal during sleep periods and demographic information, a logistic regression model (termed OxyDOSA) was trained to distinguish between non-OSA and OSA individuals (mild, moderate, and severe). The OxyDOSA model performance was assessed against the PSG-based diagnosis of OSA (AASM 2017) and compared to the NoSAS and STOP-BANG questionnaires.

FINDINGS

The OxyDOSA model had mean AUROC = 0.94 ± 0.02, Se = 0.87 ± 0.04 and Sp = 0.85 ± 0.03. In particular, it did not miss any of the 75 severe OSA individuals. In comparison, the NoSAS questionnaire had AUROC = 0.83 ± 0.03, and missed 23/75 severe OSA individuals. The STOP-BANG had AUROC = 0.77 ± 0.04 and missed 14/75 severe OSA individuals.

INTERPRETATION

We provide strong evidence on a representative population sample that oximetry biomarkers combined with few demographic information, the OxyDOSA model, is an effective screening tool for OSA. Our results suggest that sleep questionnaires should be used with caution for OSA screening as they fail to identify many moderate and even some severe cases. The OxyDOSA model will need to be further validated on data recorded using overnight portable oximetry.