Endotyping Sleep Apnea One Breath at a Time: An Automated Approach for Separating Obstructive from Central Sleep Disordered Breathing

REM sleep breathing: Insights beyond conventional respiratory metrics

Breathing and sleep state are tightly linked. The traditional approach to evaluation of breathing in rapid eye movement sleep has been to focus on apneas and hypopneas, and associated hypoxia or hypercapnia. However, rapid eye movement sleep breathing offers novel insights into sleep physiology and pathology, secondary to complex interactions of rapid eye movement state and cardiorespiratory biology. In this review, morphological analysis of clinical polysomnogram data to assess respiratory patterns and associations across a range of health and disease is presented. There are several relatively unique insights that may be evident by assessment of breathing during rapid eye movement sleep. These include the original discovery of rapid eye movement sleep and scoring of neonatal sleep, control of breathing in rapid eye movement sleep, rapid eye movement sleep homeostasis, sleep apnea endotyping and pharmacotherapy, rapid eye movement sleep stability, non-electroencephalogram sleep staging, influences on cataplexy, mimics of rapid eye movement behaviour disorder, a reflection of autonomic health, and insights into cardiac arrhythmogenesis. In summary, there is rich clinically actionable information beyond sleep apnea encoded in the respiratory patterns of rapid eye movement sleep.

The Past and Future of Sleep Medicine

The past of sleep medicine is rich with seminal discoveries, from the recognition of clinical syndromes to measurement of sleep itself to classic and novel therapeutics. Advances in neurobiology have mapped a number of sleep circuits, described the central and peripheral circadian system, and identified the cause of narcolepsy with cataplexy. Sleep apnea endotypes and phenotypes now have established clinical relevance, though treatment implications are a work in progress. Artificial intelligence will continue to change sleep medicine in a number of domains from aiding scoring to health outcome predictions. There is a large gap between the known science and clinical translational.

Artificial Intelligence Can Drive Sleep Medicine

This article explores the transformative role of artificial intelligence (AI) in sleep medicine, highlighting its applications in detecting sleep microstructure patterns and integrating novel metrics. AI enhances diagnostic accuracy and objectivity, addressing inter-rater variability. AI also facilitates the classification of sleep disorders and the prediction of health outcomes. AI can drive sleep medicine to achieve deeper insights into sleep's impact on health, leading to personalized treatment strategies and improved patient care.

Insights, recommendations, and research priorities for central sleep apnea: report from an expert panel

Central sleep apnea (CSA) is commonly encountered among patients with sleep-disordered breathing; however, its clinical consequences are less well-characterized. The senior author (A.M.) therefore convened an expert panel to discuss the common presentations of CSA, as well as challenges and knowledge gaps in the diagnosis and management of CSA. The panel identified several key research priorities essential for advancing our understanding of the disorder. Within the diagnostic realm, panel members discussed the utility of multinight assessments and importance of the development and validation of novel metrics and automated assessments for differentiating central vs obstructive hypopneas, such that their impact on clinical outcomes and management may be better evaluated. The panel also discussed the current therapeutic landscape for the management of CSA and agreed that therapies should primarily aim to alleviate sleep-related symptoms, after optimizing treatment to address the underlying cause. Most importantly, the panel concluded that there is a need to further investigate the clinical consequences of CSA, as well as the implications of therapy on clinical outcomes, particularly among those who are asymptomatic. Future research should focus on endo-phenotyping central events for a better mechanistic understanding of the disease, validating novel diagnostic methods for implementation in routine clinical practice, as well as the use of combination therapy and comparative effectiveness trials in elucidating the most efficacious interventions for managing CSA.

CITATION

Kundel V, Ahn A, Arzt M, et al. Insights, recommendations, and research priorities for central sleep apnea: report from an expert panel. J Clin Sleep Med. 2025;21(2):405-416.

Physiologic Consequences of Upper Airway Obstruction in Sleep Apnea

OSA is diagnosed and managed by a metric called the apnea-hypopnea index (AHI). The AHI quantifies the number of respiratory events (apnea or hypopnea), disregarding important information on the characteristics and physiologic consequences of respiratory events, including degrees of ventilatory deficit and associated hypoxemia, cardiac autonomic response, and cortical activity. The oversimplification of the disorder by the AHI is considered one of the reasons for divergent findings on the associations of OSA and cardiovascular disease (CVD) in observational and randomized controlled trial studies. Prospective observational cohort studies have demonstrated strong associations of OSA with several cardiovascular diseases, and randomized controlled trials of CPAP intervention have not been able to detect a benefit of CPAP to reduce the risk of CVD. Over the last several years, novel methodologies have been proposed to better quantify the magnitude of OSA-related breathing disturbance and its physiologic consequences. As a result, stronger associations with cardiovascular and neurocognitive outcomes have been observed. In this review, we focus on the methods that capture polysomnographic heterogeneity of OSA.

Achieving Better Understanding of Obstructive Sleep Apnea Treatment Effects on Cardiovascular Disease Outcomes through Machine Learning Approaches: A Narrative Review

Obstructive sleep apnea (OSA) affects almost a billion people worldwide and is associated with a myriad of adverse health outcomes. Among the most prevalent and morbid are cardiovascular diseases (CVDs). Nonetheless, randomized controlled trials (RCTs) of OSA treatment have failed to show improvements in CVD outcomes. A major limitation in our field is the lack of precision in defining OSA and specifically subgroups with the potential to benefit from therapy. Further, this has called into question the validity of using the time-honored apnea-hypopnea index as the ultimate defining criteria for OSA. Recent applications of advanced statistical methods and machine learning have brought to light a variety of OSA endotypes and phenotypes. These methods also provide an opportunity to understand the interaction between OSA and comorbid diseases for better CVD risk stratification. Lastly, machine learning and specifically heterogeneous treatment effects modeling can help uncover subgroups with differential outcomes after treatment initiation. In an era of data sharing and big data, these techniques will be at the forefront of OSA research. Advanced data science methods, such as machine-learning analyses and artificial intelligence, will improve our ability to determine the unique influence of OSA on CVD outcomes and ultimately allow us to better determine precision medicine approaches in OSA patients for CVD risk reduction. In this narrative review, we will highlight how team science via machine learning and artificial intelligence applied to existing clinical data, polysomnography, proteomics, and imaging can do just that.

Long-term health outcomes for patients with obstructive sleep apnea: placing the Agency for Healthcare Research and Quality report in context-a multisociety commentary

This multisociety commentary critically examines the Agency for Healthcare Research and Quality (AHRQ) final report and systematic review on long-term health outcomes in obstructive sleep apnea. The AHRQ report was commissioned by the Centers for Medicare & Medicaid Services and particularly focused on the long-term patient-centered outcomes of continuous positive airway pressure, the variability of sleep-disordered breathing metrics, and the validity of these metrics as surrogate outcomes. This commentary raises concerns regarding the AHRQ report conclusions and their potential implications for policy decisions. A major concern expressed in this commentary is that the AHRQ report inadequately acknowledges the benefits of continuous positive airway pressure for several established, long-term clinically important outcomes including excessive sleepiness, motor vehicle accidents, and blood pressure. While acknowledging the limited evidence for the long-term benefits of continuous positive airway pressure treatment, especially cardiovascular outcomes, as summarized by the AHRQ report, this commentary reviews the limitations of recent randomized controlled trials and nonrandomized controlled studies and the challenges of conducting future randomized controlled trials. A research agenda to address these challenges is proposed including study designs that may include both high quality randomized controlled trials and nonrandomized controlled studies. This commentary concludes by highlighting implications for the safety and quality of life for the millions of people living with obstructive sleep apnea if the AHRQ report alone was used by payers to limit coverage for the treatment of obstructive sleep apnea while not considering the totality of available evidence.

CITATION

Patil SP, Billings ME, Bourjeily G, et al. Long-term health outcomes for patients with obstructive sleep apnea: placing the Agency for Healthcare Research and Quality report in context-a multisociety commentary. J Clin Sleep Med. 2024;20(1):135-149.

Ventilatory Burden as a Measure of Obstructive Sleep Apnea Severity Is Predictive of Cardiovascular and All-Cause Mortality

Rationale: The apnea-hypopnea index (AHI), used for the diagnosis of obstructive sleep apnea, captures only the frequency of respiratory events and has demonstrable limitations. Objectives: We propose a novel automated measure, termed "ventilatory burden" (VB), that represents the proportion of overnight breaths with less than 50% normalized amplitude, and we show its ability to overcome limitations of AHI. Methods: Data from two epidemiological cohorts (EPISONO [Sao Paolo Epidemiological Study] and SHHS [Sleep Heart Health Study]) and two retrospective clinical cohorts (DAYFUN; New York University Center for Brain Health) were used in this study to 1) derive the normative range of VB, 2) assess the relationship between degree of upper airway obstruction and VB, and 3) assess the relationship between VB and all-cause and cardiovascular disease (CVD) mortality with and without hypoxic burden that was derived using an in-house automated algorithm. Measurements and Main Results: The 95th percentiles of VB in asymptomatic healthy subjects across the EPISONO and the DAYFUN cohorts were 25.2% and 26.7%, respectively (median [interquartile range], VBEPISONO, 5.5 [3.5-9.7]%; VBDAYFUN, 9.8 [6.4-15.6]%). VB was associated with the degree of upper airway obstruction in a dose-response manner (VBuntreated, 31.6 [27.1]%; VBtreated, 7.2 [4.7]%; VBsuboptimally treated, 17.6 [18.7]%; VBoff-treatment, 41.6 [18.1]%) and exhibited low night-to-night variability (intraclass correlation coefficient [2,1], 0.89). VB was predictive of all-cause and CVD mortality in the SHHS cohort before and after adjusting for covariates including hypoxic burden. Although AHI was predictive of all-cause mortality, it was not associated with CVD mortality in the SHHS cohort. Conclusions: Automated VB can effectively assess obstructive sleep apnea severity, is predictive of all-cause and CVD mortality, and may be a viable alternative to the AHI.

Predictors of Initial CPAP Prescription and Subsequent Course with CPAP in Patients with Central Sleep Apneas at a Single Center

PURPOSE

Guidelines recommend considering an initial trial of continuous positive airway pressure (CPAP) to treat central sleep apnea (CSA). However, practice patterns vary widely. This study investigated predictors for an initial trial of CPAP in patients with central apneas and whether those factors predict adequate treatment response in patients receiving an initial CPAP trial.

METHODS

Charts of patients receiving a diagnostic code for CSA following a sleep study during 2016-2018 at a single center were reviewed. Patient factors, initial treatment prescriptions, and subsequent changes to therapy were extracted from electronic health records. Regression models were used to estimate factors associated with an initial CPAP prescription and the likelihood of an adequate CPAP response (no subsequent therapy change and no discontinuation of therapy) among patients prescribed CPAP.

RESULTS

429/588 (73%) patients with central apneas received an initial trial of CPAP. Younger age, diagnosis by home sleep testing, non-opiate etiology of central apneas, and a lower proportion of central apneas at diagnosis were independently associated with a higher likelihood of an initial CPAP trial. A lower proportion of central apneas was associated with a higher probability of adequate response, while current smoking and opiate-related central apneas predicted an unsuccessful CPAP trial. A new finding was that older age predicted a lower likelihood of an initial CPAP prescription but did not predict an unsatisfactory response to CPAP.

CONCLUSION

Clinicians may incorrectly weigh certain clinical and sleep study characteristics when deciding whether to trial CPAP for patients with central apneas.

Predictors of Initial CPAP Prescription and Subsequent Course with CPAP in Patients with Central Sleep Apneas

Purpose

Guidelines recommend considering an initial trial of continuous positive airway pressure (CPAP) to treat central sleep apnea (CSA). However, practice patterns vary widely. This study investigated predictors for an initial trial of CPAP in patients with central apneas and whether those factors predict adequate treatment response in patients receiving an initial CPAP trial.

Methods

Charts of patients receiving a diagnostic code for CSA following a sleep study during 2016-2018 at a single center were reviewed. Patient factors, initial treatment prescriptions, and subsequent changes to therapy were extracted from electronic health records. Regression models were used to estimate factors associated with an initial CPAP prescription and the likelihood of an adequate CPAP response (no subsequent therapy change or nonadherence) among patients prescribed CPAP.

Results

429/588 (73%) patients with central apneas received an initial trial of CPAP. Younger age, diagnosis by home sleep testing, non-opiate etiology of central apneas, and a lower proportion of central apneas at diagnosis were independently associated with a higher likelihood of an initial CPAP trial. A lower proportion of central apneas was associated with a higher probability of adequate response, while current smoking and opiate-related central apneas predicted an unsuccessful CPAP trial. A new finding was that older age predicted a lower likelihood of an initial CPAP prescription but did not predict a suboptimal response to CPAP.

Conclusion

Clinicians may incorrectly weigh certain clinical and sleep study characteristics when deciding whether to trial CPAP for patients with central apneas.

Nasal Pressure Derived Airflow Limitation and Ventilation Measurements are Resilient to Reduced Signal Quality

Obstructive sleep apnea is a disorder characterized by partial or complete airway obstructions during sleep. Our previously published algorithms use the minimally invasive nasal pressure signal routinely collected during diagnostic polysomnography (PSG) to segment breaths and estimate airflow limitation (using flow:drive) and minute ventilation for each breath. The first aim of this study was to investigate the effect of airflow signal quality on these algorithms, which can be influenced by oronasal breathing and signal-to-noise ratio (SNR). It was hypothesized that these algorithms would make inaccurate estimates when the expiratory portion of breaths is attenuated to simulate oronasal breathing, and pink noise is added to the airflow signal to reduce SNR. At maximum SNR and 0% expiratory amplitude, the average error was 2.7% for flow:drive, -0.5% eupnea for ventilation, and 19.7 milliseconds for breath duration (n = 257,131 breaths). At 20 dB and 0% expiratory amplitude, the average error was -15.1% for flow:drive, 0.1% eupnea for ventilation, and 28.4 milliseconds for breath duration (n = 247,160 breaths). Unexpectedly, simulated oronasal breathing had a negligible effect on flow:drive, ventilation, and breath segmentation algorithms across all SNRs. Airflow SNR ≥ 20 dB had a negligible effect on ventilation and breath segmentation, whereas airflow SNR ≥ 30 dB had a negligible effect on flow:drive. The second aim of this study was to explore the possibility of correcting these algorithms to compensate for airflow signal asymmetry and low SNR. An offset based on estimated SNR applied to individual breath flow:drive estimates reduced the average error to ≤ 1.3% across all SNRs at patient and breath levels, thereby facilitating for flow:drive to be more accurately estimated from PSGs with low airflow SNR.Clinical Relevance- This study demonstrates that our airflow limitation, ventilation, and breath segmentation algorithms are robust to reduced airflow signal quality.

Distinguishing central from obstructive hypopneas on a clinical polysomnogram

Among sleep-related disordered breathing events, hypopneas are the most frequent. Like obstructive and central apneas, hypopneas may be obstructive or central (reduced drive) in origin. Nevertheless, unlike apneas, categorizing hypopneas as either "obstructive" or "central" is often difficult or ambiguous. It has been suggested that hypopneas could be categorized as obstructive when associated with snoring, inspiratory flow limitation, or paradoxical thoraco-abdominal excursions. This approach, however, has not been extensively tested and misclassification of hypopneas is unavoidable. Yet, much rides on the accurate distinction of these events to guide therapy with medical devices or pharmacological therapy in each patient. Additionally, accurate hypopnea classification is critical for design of clinical trials, because therapeutic responses differ depending on the subtype of hypopnea. Correctly classifying hypopneas can also allay concerns about obtaining coverage for therapies that specifically target either central or obstructive sleep-disordered breathing events. The present paper expands on the current criteria for differentiating obstructive from central hypopneas and provides illustrative tracings that can help classify these events.

CITATION

Javaheri S, Rapoport DM, Schwartz AR. Distinguishing central from obstructive hypopneas on a clinical polysomnogram. J Clin Sleep Med. 2023;19(4):823-834.