Defining Extreme Phenotypes of OSA Across International Sleep Centers

Can intraoral and facial photos predict obstructive sleep apnea in the general and clinical population?

STUDY OBJECTIVES

This study aimed to evaluate and compare measurements of standardized craniofacial and intraoral photographs between clinical and general population samples, between groups of individuals with an apnea-hypopnea index (AHI) ≥ 15 and AHI < 15, and their interaction, as well as the relationship with the presence and severity of obstructive sleep apnea (OSA).

METHODS

We used data from 929 participants from Sleep Apnea Global Interdisciplinary Consortium, in which 309 patients from a clinical setting and 620 volunteers from a general population.

RESULTS

AHI ≥ 15 were observed in 30.3% of the total sample and there were some interactions between facial/intraoral measures with OSA and both samples. Mandibular volume (p < 0.01) and lateral face height (p = 0.04) were higher in the AHI ≥ 15 group in the clinical sample compared to the AHI ≥ 15 group in the general population and AHI < 15 group in the clinical sample. When adjusted for sex and age, greater mandible width (p < 0.01) differed both in the clinical and in the general population samples, reflecting AHI severity and the likelihood of OSA. The measure of smaller tongue curvature (p < 0.01) reflected the severity and probability of OSA in the clinical sample and the higher posterior mandibular height (p = 0.04) showed a relationship with higher AHI and higher risk of OSA in the general population. When adjusted for sex, age, and body mass index, only smaller tongue curvature (p < 0.01) was associated with moderate/severe OSA.

CONCLUSIONS

Measures of greater tongue and mandible were associated with increased OSA risk in the clinical sample and craniofacial measurement was associated in the general population sample.

Obstructive sleep apnea heterogeneity and autonomic function: a role for heart rate variability in therapy selection and efficacy monitoring

Obstructive sleep apnea is a highly prevalent sleep-related breathing disorder, resulting in a disturbed breathing pattern, changes in blood gases, abnormal autonomic regulation, metabolic fluctuation, poor neurocognitive performance, and increased cardiovascular risk. With broad inter-individual differences recognised in risk factors, clinical symptoms, gene expression, physiological characteristics, and health outcomes, various obstructive sleep apnea subtypes have been identified. Therapeutic efficacy and its impact on outcomes, particularly for cardiovascular consequences, may also vary depending on these features in obstructive sleep apnea. A number of interventions such as positive airway pressure therapies, oral appliance, surgical treatment, and pharmaceutical options are available in clinical practice. Selecting an effective obstructive sleep apnea treatment and therapy is a challenging medical decision due to obstructive sleep apnea heterogeneity and numerous treatment modalities. Thus, an objective marker for clinical evaluation is warranted to estimate the treatment response in patients with obstructive sleep apnea. Currently, while the Apnea-Hypopnea Index is used for severity assessment of obstructive sleep apnea and still considered a major guide to diagnosis and managements of obstructive sleep apnea, the Apnea-Hypopnea Index is not a robust marker of symptoms, function, or outcome improvement. Abnormal cardiac autonomic modulation can provide additional insight to better understand obstructive sleep apnea phenotyping. Heart rate variability is a reliable neurocardiac tool to assess altered autonomic function and can also provide cardiovascular information in obstructive sleep apnea. Beyond the Apnea-Hypopnea Index, this review aims to discuss the role of heart rate variability as an indicator and predictor of therapeutic efficacy to different modalities in order to optimise tailored treatment for obstructive sleep apnea.

Consensus Statements among European Sleep Surgery Experts on Snoring and Obstructive Sleep Apnea: Part 1 Definitions and Diagnosis

Seeking consensus on definitions and diagnosis of snoring and obstructive sleep apnea (OSA) among sleep surgeons is important, particularly in this relatively new field with variability in knowledge and practices. A set of statements was developed based on the literature and circulated among eight panel members of European experts, utilizing the Delphi method. Responses in agreement and disagreement on each statement and the comments were used to assess the level of consensus and develop a revised version. The new version with the level of consensus and anonymized comments was sent to each panel member as the second round. This was repeated a total of five rounds. The total number of statements included in the initial set was 112. In the first round, of all eight panelists, the percentage of questions that had consensus among the eight, seven, and six panelists were 45%, 4.5%, and 7.1%, respectively. In the final set of statements consisting of 99, the percentage of questions that had consensus among the 8, 7, and 6 panelists went up to 66.7%, 24.2%, and 6.1%, respectively. Delphi's method demonstrated an efficient method of interaction among experts and the establishment of consensus on a specific set of statements.

Deep learning technique to detect craniofacial anatomical abnormalities concentrated on middle and anterior of face in patients with sleep apnea

OBJECTIVES

The aim of this study is to propose a deep learning-based model using craniofacial photographs for automatic obstructive sleep apnea (OSA) detection and to perform design explainability tests to investigate important craniofacial regions as well as the reliability of the method.

METHODS

Five hundred and thirty participants with suspected OSA are subjected to polysomnography. Front and profile craniofacial photographs are captured and randomly segregated into training, validation, and test sets for model development and evaluation. Photographic occlusion tests and visual observations are performed to determine regions at risk of OSA. The number of positive regions in each participant is identified and their associations with OSA is assessed.

RESULTS

The model using craniofacial photographs alone yields an accuracy of 0.884 and an area under the receiver operating characteristic curve of 0.881 (95% confidence interval, 0.839-0.922). Using the cutoff point with the maximum sum of sensitivity and specificity, the model exhibits a sensitivity of 0.905 and a specificity of 0.941. The bilateral eyes, nose, mouth and chin, pre-auricular area, and ears contribute the most to disease detection. When photographs that increase the weights of these regions are used, the performance of the model improved. Additionally, different severities of OSA become more prevalent as the number of positive craniofacial regions increases.

CONCLUSIONS

The results suggest that the deep learning-based model can extract meaningful features that are primarily concentrated in the middle and anterior regions of the face.

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.

Cluster analysis of clinical phenotypic heterogeneity in obstructive sleep apnea assessed using photoplethysmography

BACKGROUND

We evaluated heterogeneity in clinical phenotypes among patients with obstructive sleep apnea syndrome (OSAHS) using photoplethysmography (PPG) in cluster analysis.

METHODS

All enrolled patients underwent polysomnography (PSG) monitoring while wearing a PPG device. Pulse wave signals were recorded with a modified pulse oximetry probe in the PPG device. The pulse wave-derived cardiac risk composite parameter (CRI) and eight derived signal parameters were used to assess OSAHS phenotype. We defined a high cardiovascular risk OSAHS group (CRI ≥0.5) and low cardiovascular risk OSAHS group (CRI <0.5). K-means clustering was performed for analysis of clinical phenotype heterogeneity in OSAHS by combining the CRI and its derived signals.

RESULTS

The OSAHS group had high cardiovascular risk for sex, age, body mass index, systolic and diastolic blood pressure, apnea hypopnea index, and obstructive arousal index and higher risk of developing hypertension, diabetes, and cerebrovascular comorbidities. The low cardiovascular risk OSAHS group had higher blood oxygen levels. Three clinical phenotypes were identified in CRI clustering: 1) typical OSAHS with high risk of hypertension (characterized by middle age, obesity, hypertension with severe OSAHS); 2) older women and mild OSAHS; 3) older men and mild OSAHS. Three subtypes were obtained based on the eight cardiac risk-derived parameters: 1) hypoxia combined with decreased pulse wave amplitude variation; 2) decreased vascular pulse wave amplitude combined with decreased pulse frequency; 3) arrhythmia combined with hypoxia.

CONCLUSIONS

Establishing OSAHS clinical phenotypes with the CRI and derived parameters using PPG may help in establishing multi-dimensional assessment of cardiovascular risk in OSAHS.

Do brachycephaly and nose size predict the severity of obstructive sleep apnea (OSA)? A sample-based geometric morphometric analysis of craniofacial variation in relation to OSA syndrome and the role of confounding factors

Obstructive sleep apnea is a common disorder that leads to sleep fragmentation and is potentially bidirectionally related to a variety of comorbidities, including an increased risk of heart failure and stroke. It is often considered a consequence of anatomical abnormalities, especially in the head and neck, but its pathophysiology is likely to be multifactorial in origin. With geometric morphometrics, and a large sample of adults from the Study for Health in Pomerania, we explore the association of craniofacial morphology to the apnea-hypopnea index used as an estimate of obstructive sleep apnea severity. We show that craniofacial size and asymmetry, an aspect of morphological variation seldom analysed in obstructive sleep apnea research, are both uncorrelated to apnea-hypopnea index. In contrast, as in previous analyses, we find evidence that brachycephaly and larger nasal proportions might be associated to obstructive sleep apnea severity. However, this correlational signal is weak and completely disappears when age-related shape variation is statistically controlled for. Our findings suggest that previous work might need to be re-evaluated, and urge researchers to take into account the role of confounders to avoid potentially spurious findings in association studies.

Diagnostic Performance of Machine Learning-Derived OSA Prediction Tools in Large Clinical and Community-Based Samples

BACKGROUND

Prediction tools without patient-reported symptoms could facilitate widespread identification of OSA.

RESEARCH QUESTION

What is the diagnostic performance of OSA prediction tools derived from machine learning using readily available data without patient responses to questionnaires? Also, how do they compare with STOP-BANG, an OSA prediction tool, in clinical and community-based samples?

STUDY DESIGN AND METHODS

Logistic regression and machine learning techniques, including artificial neural network (ANN), random forests (RF), and kernel support vector machine, were used to determine the ability of age, sex, BMI, and race to predict OSA status. A retrospective cohort of 17,448 subjects from sleep clinics within the international Sleep Apnea Global Interdisciplinary Consortium (SAGIC) were randomly split into training (n = 10,469) and validation (n = 6,979) sets. Model comparisons were performed by using the area under the receiver-operating curve (AUC). Trained models were compared with the STOP-BANG questionnaire in two prospective testing datasets: an independent clinic-based sample from SAGIC (n = 1,613) and a community-based sample from the Sleep Heart Health Study (n = 5,599).

RESULTS

The AUCs (95% CI) of the machine learning models were significantly higher than logistic regression (0.61 [0.60-0.62]) in both the training and validation datasets (ANN, 0.68 [0.66-0.69]; RF, 0.68 [0.67-0.70]; and kernel support vector machine, 0.66 [0.65-0.67]). In the SAGIC testing sample, the ANN (0.70 [0.68-0.72]) and RF (0.70 [0.68-0.73]) models had AUCs similar to those of the STOP-BANG (0.71 [0.68-0.72]). In the Sleep Heart Health Study testing sample, the ANN (0.72 [0.71-0.74]) had AUCs similar to those of STOP-BANG (0.72 [0.70-0.73]).

INTERPRETATION

OSA prediction tools using machine learning without patient-reported symptoms provide better diagnostic performance than logistic regression. In clinical and community-based samples, the symptomless ANN tool has diagnostic performance similar to that of a widely used prediction tool that includes patient symptoms. Machine learning-derived algorithms may have utility for widespread identification of OSA.

Landscape of biomedical informatics standards and terminologies for clinical sleep medicine research: A systematic review

A systematic literature review was conducted to understand the current landscape of standards and terminologies used in clinical sleep medicine. Literature search on PubMed, EMBASE, Medline and Web of Science was performed in March 2021 using terms related to sleep, terminologies, standards, harmonization, semantics, ontology, and electronic health records (EHR). Systematic review was carried out according to PRISMA. Among 128 included studies, 35 were eligible for review. Articles were broadly classified into six topics: standard terminology efforts, reporting standards, databases and resources, data integration efforts, EHR abstraction and standards for automated sleep scoring. This review highlights the progress and challenges related to establishing computable terminologies in sleep medicine, and identifies gaps, limitations and research opportunities related to data integration that could improve adoption of clinical research informatics in this field. There is a need for the systematic adoption of standardized terminologies in all areas of sleep medicine. Existing data aggregation resources could be leveraged to support the development of an integrated infrastructure and subsequent deployment in EHR systems within sleep centers. Ultimately, the adoption of standardized practices for documenting sleep disorders and related traits facilitates data sharing, thus accelerating discovery and clinical translation of informatics approaches applied to sleep medicine.

Simple and Unbiased OSA Prescreening: Introduction of a New Morphologic OSA Prediction Score

PURPOSE

An early prescreening in suspected obstructive sleep apnea (OSA) patients is desirable to expedite diagnosis and treatment. However, the accuracy and applicability of current prescreening tools is insufficient. We developed and tested an unbiased scoring system based solely on objective variables, which focuses on the diagnosis of severe OSA and exclusion of OSA.

PATIENTS AND METHODS

The OSA prediction score was developed (n = 150) and validated (n = 50) within German sleep center patients that were recruited as part of the Sleep Apnea Global Interdisciplinary Consortium (SAGIC). Six objective variables that were easy to assess and highly correlated with the apnea-hypopnea index were chosen for the score, including some known OSA risk factors: body-mass index, neck circumference, waist circumference, tongue position, male gender, and age (for women only). To test the predictive ability of the score and identify score thresholds, the receiver-operating characteristics (ROC) and curve were calculated.

RESULTS

A score ≥8 for predicting severe OSA resulted in an area under the ROC curve (ROC-AUC) of 90% (95% confidence interval: 84%, 95%), test accuracy of 82% (75%, 88%), sensitivity of 82% (65%, 93%), specificity of 82% (74%, 88%), and positive likelihood ratio of 4.55 (3.00, 6.90). A score ≤5 for predicting the absence of OSA resulted in a ROC-AUC of 89% (83%, 94%), test accuracy of 80% (73%, 86%), sensitivity of 72% (55%, 85%), specificity of 83% (75%, 89%), and positive likelihood ratio of 4.20 (2.66, 6.61). Performance characteristics were comparable in the small validation sample.

CONCLUSION

We introduced a novel prescreening tool combining easily obtainable objective measures with predictive power and high general applicability. The proposed tool successfully predicted severe OSA (important due to its high risk of cardiovascular disease) and the exclusion of OSA (rarely a feature of previous screening instruments, but important for better differential diagnosis and treatment).