Multidimensional phenotyping to distinguish among distinct obstructive sleep apnea, chronic obstructive pulmonary disease, and overlap syndrome phenotypes.

OBJECTIVE/BACKGROUND: Chronic obstructive pulmonary disease (COPD), obstructive sleep apnea (OSA) and their comorbid association called Overlap Syndrome (OS) are frequent chronic diseases with high individual and societal burdens. Precise descriptions of the respective symptoms, comorbidities, and medications associated with these three conditions are lacking. We used a multidimensional phenotyping approach to identify relevant phenotypes characterizing these 3 disorders. PATIENTS/METHODS: 308 patients with OSA, COPD and OS were prospectively assessed using a combination of body shape measurements and multidimensional questionnaires evaluating sleep, fatigue, depression and respiratory symptoms. Comorbidities and medications were confirmed by physicians. Patients made home blood pressure self-measurements using a connected wearable device to identify undiagnosed or uncontrolled hypertension. RESULTS: Three distinct relevant phenotypes were identified. OSA patients were round in shape with a balanced waist-to-hip ratio, frequent witnessed apneas, nocturia, daytime sleepiness, depression, and high diastolic blood pressure. COPD patients had a thinner body shape with a high waist-to-hip ratio, complained mainly of fatigue, and exhibited a higher resting heart rate. OS patients were round in shape with a balanced waist-to-hip ratio, reported little sleepiness and depression, but had impaired sleep and the highest rate of cardio-metabolic comorbidities. Diminished fitness-to-drive was most apparent in patients with OSA and OS. Home blood pressure measurements identified undiagnosed hypertension in 80 % of patients and in nearly 80 % of those with hypertension it was uncontrolled by their current medications. CONCLUSIONS: Our systematic multidimensional phenotyping approach identified distinct body shapes, symptoms, and comorbidity profiles among patients with OSA, COPD, and OS.

The Future of Telemedicine for Obstructive Sleep Apnea Treatment: A Narrative Review.

Obstructive sleep apnea is a common type of sleep-disordered breathing associated with multiple comorbidities. Nearly a billion people are estimated to have obstructive sleep apnea, which carries a substantial economic burden, but under-diagnosis is still a problem. Continuous positive airway pressure (CPAP) is the first-line treatment for OSAS. Telemedicine-based interventions (TM) have been evaluated to improve access to diagnosis, increase CPAP adherence, and contribute to easing the follow-up process, allowing healthcare facilities to provide patient-centered care. This narrative review summarizes the evidence available regarding the potential future of telemedicine in the management pathway of OSA. The potential of home sleep studies to improve OSA diagnosis and the importance of remote monitoring for tracking treatment adherence and failure and to contribute to developing patient engagement tools will be presented. Further studies are needed to explore the impact of shifting from teleconsultations to collaborative care models where patients are placed at the center of their care.

Temporal association of ventricular arrhythmias and respiratory events in heart failure patients with central sleep apnoea.

In contrast to obstructive sleep apnoea, the peak of sympathetic tone in central sleep apnoea occurs during the hyperventilation phase. To explore the temporal association of premature ventricular complex (PVC) burden in the context of the apnoea/hypopnoea-hyperpnoea cycle, the duration of apnoea/hypopnoea was defined as 100 %. We assessed the PVC burden throughout the apnoea/hypopnoea-hyperpnoea cycle during the periods of ±150 % in 50 % increments before and after the apnoea/hypopnoea phase. In this subanalysis of 54 SERVE-HF patients, PVC burden was 32 % higher in the late hyperventilation period (50-100 % after apnoea/hypopnoea) compared to the apnoea/hypopnoea phase.

Central sleep apnoea: not just one phenotype.

Recent scientific findings in the field of sleep disordered breathing have characterised a variety of phenotypes in obstructive sleep apnoea. These findings have prompted investigations aiming to achieve a more precise differentiation and description of the entities of central sleep apnoea (CSA). There is increasing evidence for the heterogeneity of CSA in terms of underlying aetiology, pathophysiological concepts, treatment response and outcome. Assigning patients to these phenotypes allows for the selection of individualised therapies. Major pathophysiological characteristics include loop gain, apnoeic threshold, breathing regulation and neuromuscular mechanics. Chronic heart failure is the most important underlying disease, leading to nonhypercapnic CSA based on increased loop and controller gain. Although many questions remain, this review tries to describe the current knowledge on the pathophysiology of the clinical entities. The description of prognostic aspects may guide treatment indication and the selection of pharmacotherapy and invasive options. In addition, the paper provides an update on the current understanding of adaptive servo-ventilation and its role in the treatment of CSA.

Sociological determinants of adherence to continuous positive airway pressure in the management of sleep apnoea syndrome: protocol for a transdisciplinary, prospective observational study.

INTRODUCTION: Obstructive sleep apnoea syndrome (OSAS) is a chronic multiorgan pathology that has a negative impact on quality of life. Continuous positive airway pressure (CPAP) is the first-line treatment for OSAS. However, CPAP termination rates remain very high, and adherence to therapy is a major issue. To date, studies targeting predictive factors of CPAP adherence by OSAS patients mainly include clinical data. The social, socioeconomic, psychological, and home environment aspects have been far less studied and largely underestimated. This study aims to obtain solid quantitative results examining the relationship between the determinants of refusal, non-adherence, or termination of CPAP treatment, and in particular the pivotal role played by health literacy. METHODS AND ANALYSIS: This is a prospective, multicentre, observational study recruiting patients attending the sleep clinic of the Grenoble Alpes University Hospital, France. Consecutive adults (>18 years) recently diagnosed with OSAS and prescribed CPAP treatment with telemonitoring will be enrolled in the present study. They will benefit from home visits by a CPAP technician or nurse at CPAP initiation. Patients will then be followed up for 6 months through the telemonitoring platform of a home-care provider. The primary objective is to evaluate the impact of health literacy (health literacy, measured by the European Health Literacy Survey questionnaire (HLS-EU-16) on the refusal, non-adherence or termination of CPAP treatment in newly diagnosed OSAS patients, during the first 6 months after diagnosis. The target sample size is 250 participants. ETHICS AND DISSEMINATION: The study protocol, patient information, and the non-opposition form were approved by the French national ethics committee (CPP 2021-92, January 2022). All patients are required to have signed a written informed consent form permitting their anonymised personal and medical data to be used for clinical research purposes. We will publish the results in a peer-reviewed medical journal and on our institutional websites. TRIAL REGISTRATION NUMBER: NCT05385302.

Long-term intermittent hypoxia in mice induces inflammatory pathways implicated in sleep apnea and steatohepatitis in humans.

Obstructive sleep apnea (OSA) induces intermittent hypoxia (IH), an independent risk factor for non-alcoholic fatty liver disease (NAFLD). While the molecular links between IH and NAFLD progression are unclear, immune cell-driven inflammation plays a crucial role in NAFLD pathogenesis. Using lean mice exposed to long-term IH and a cohort of lean OSA patients (n = 71), we conducted comprehensive hepatic transcriptomics, lipidomics, and targeted serum proteomics. Significantly, we demonstrated that long-term IH alone can induce NASH molecular signatures found in human steatohepatitis transcriptomic data. Biomarkers (PPARs, NRFs, arachidonic acid, IL16, IL20, IFNB, TNF-α) associated with early hepatic and systemic inflammation were identified. This molecular link between IH, sleep apnea, and steatohepatitis merits further exploration in clinical trials, advocating for integrating sleep apnea diagnosis in liver disease phenotyping. Our unique signatures offer potential diagnostic and treatment response markers, highlighting therapeutic targets in the comorbidity of NAFLD and OSA.

Mandibular Jaw Movement Automated Analysis for Oral Appliance Monitoring in Obstructive Sleep Apnea: A Prospective Cohort Study.

Rationale: Oral appliances are second-line treatments after continuous positive airway pressure for obstructive sleep apnea (OSA) management. However, the need for oral appliance titration limits their use as a result of monitoring challenges to assess the treatment effect on OSA. Objectives: To assess the validity of mandibular jaw movement (MJM) automated analysis compared with polysomnography (PSG) and polygraphy (PG) in evaluating the effect of oral appliance treatment and the effectiveness of MJM monitoring for oral appliance titration at home in patients with OSA. Methods: This observational, prospective study included 135 patients with OSA eligible for oral appliance therapy. The primary outcome was the apnea-hypopnea index (AHI), measured through in-laboratory PSG/PG and MJM-based technology. Additionally, MJM monitoring at home was conducted at regular intervals during the titration process. The agreement between PSG/PG and MJM automated analysis was revaluated using Bland-Altman analysis. Changes in AHI during the home-based oral appliance titration process were evaluated using a generalized linear mixed model and a generalized estimating equation model. Results: The automated MJM analysis demonstrated strong agreement with PG in assessing AHI at the end of titration, with a median bias of 0.24/h (limits of agreement, -11.2 to 12.8/h). The improvement of AHI from baseline in response to oral appliance treatment was consistent across three evaluation conditions: in-laboratory PG (-59.6%; 95% confidence interval, -59.8% to -59.5%), in-laboratory automated MJM analysis (-59.2%; -65.2% to -52.2%), and at-home automated MJM analysis (-59.7%; -67.4% to -50.2%). Conclusions: Incorporating MJM automated analysis into the oral appliance titration process has the potential to optimize oral appliance therapy outcomes for OSA.

Trajectories of self-reported daytime sleepiness post-ischemic stroke and transient ischemic attack: A propensity score matching study versus non-stroke patients.

INTRODUCTION: Severe sleep apnea (SA) affects one-third of stroke patients. Sleepiness, one of the cardinal symptoms of SA, negatively impacts functional stroke outcomes. The impact of continuous positive airway pressure (CPAP) on post-stroke sleepiness is poorly described. We aimed to compare through a propensity score matching the trajectories of self-reported sleepiness post-stroke with matched individuals including SA patients adherent or not to CPAP. PATIENTS AND METHODS: Sixty five (80.2%) ischemic stroke and 16 (19.8%) TIA patients (median [Q1;Q3] age = 67.0 [58.0;74.0] years, 70.4% male, body mass index [BMI] = 26.1 [24.5;29.8] kg·m-2, admission NIHSS = 3.0 [1.0;5.0]), with polysomnography and an Epworth Sleepiness Scale (ESS) performed within 1 year following stroke and with a follow-up ESS (delay = 236 [147;399] days) were included in the analysis. A 2:1 propensity score matching based on age, gender, BMI, and the apnea-hypopnea index was performed to identify 162 matched individuals referred for SA suspicion, free of stroke or TIA. Multivariable negative binomial regression models were performed to identify the determinants of sleepiness trajectories post-stroke. RESULTS: Baseline ESS was comparable between stroke/TIA and matched individuals (median [Q1; Q3] ESS = 7 [4;10] versus 6 [4;10], p = 0.86). The range of improvement in ESS was higher in stroke patients compared to controls (∆ESS = -2 [-4;1] vs -1 [-3;2], p = 0.03). In multivariable analysis, comorbid SA and CPAP treatment did not influence trajectories of sleepiness post-stroke. DISCUSSION AND CONCLUSION: Sleepiness improvement was unexpectedly higher in stroke patients compared to matched individuals, with no significant influence of comorbid SA and CPAP on its trajectory. Sleepiness may not be primarily indicative of SA in stroke or TIA patients.

FACE study: 2-year follow-up of adaptive servo-ventilation for sleep-disordered breathing in a chronic heart failure cohort.

BACKGROUND: Sleep-disordered breathing (SDB) is a common comorbidity in patients with heart failure (HF) and is associated with worse prognosis. OBJECTIVES: This study evaluated the effects of adaptive servo-ventilation (ASV) on morbidity and mortality in a large heterogeneous population of HF patients with different etiologies/phenotypes. METHODS: Consecutive HF patients with predominant central sleep apnea (± obstructive sleep apnea) indicated for ASV were included; the control group included patients who refused or stopped ASV before three months follow-up. Six homogenous clusters were determined using the latent class analysis (LCA) method. The primary endpoint was time to composite first event (all-cause death, lifesaving cardiovascular intervention, or unplanned hospitalization for worsening of chronic HF). RESULTS: Of 503 patients at baseline, 324 underwent 2-year follow-up. Compared to control group, 2-year primary endpoint event-free survival was significantly greater in patients in ASV group only in univariable analysis (1.67, 95% [1.12-2.49]; p = 0.01). Secondary endpoints, event-free of cardiovascular death or heart failure-related hospitalization and all-cause death or all-cause hospitalization were positively impacted by ASV (univariate and multivariable analysis). LCA identified two groups, with preserved and mid-range left ventricular ejection fraction (LVEF) and severe hypoxia, in whom ASV increase prognosis benefit. CONCLUSIONS: Patients with HF and SDB are a highly heterogeneous group identified using LCA. Systematic deep phenotyping is essential to ensure that ASV is prescribed to those benefit from therapy, as ASV use in patients with severe hypoxic burden and those with HFpEF was associated with a significant reduction in cardiovascular events and mortality. CLINICAL TRIAL REGISTRATION: https://clinicaltrials.gov/ct2/show/NCT01831128.

Functional recovery after ischemic stroke: Impact of different sleep health parameters.

Sleep disturbances after ischaemic stroke include alterations of sleep architecture, obstructive sleep apnea, restless legs syndrome, daytime sleepiness and insomnia. Our aim was to explore their impacts on functional outcomes at month 3 after stroke, and to assess the benefit of continuous positive airway pressure in patients with severe obstructive sleep apnea. Ninety patients with supra-tentorial ischaemic stroke underwent clinical screening for sleep disorders and polysomnography at day 15 ± 4 after stroke in a multisite study. Patients with severe obstructive apnea (apnea-hypopnea index ≥ 30 per hr) were randomized into two groups: continuous positive airway pressure-treated and sham (1:1 ratio). Functional independence was assessed with the Barthel Index at month 3 after stroke in function of apnea-hypopnea index severity and treatment group. Secondary objectives were disability (modified Rankin score) and National Institute of Health Stroke Scale according to apnea-hypopnea index. Sixty-one patients (71.8 years, 42.6% men) completed the study: 51 (83.6%) had obstructive apnea (21.3% severe apnea), 10 (16.7%) daytime sleepiness, 13 (24.1%) insomnia, 3 (5.7%) depression, and 20 (34.5%) restless legs syndrome. Barthel Index, modified Rankin score and Stroke Scale were similar at baseline and 3 months post-stroke in the different obstructive sleep apnea groups. Changes at 3 months in those three scores were similar in continuous positive airway pressure versus sham-continuous positive airway pressure patients. In patients with worse clinical outcomes at month 3, mean nocturnal oxygen saturation was lower whereas there was no association with apnea-hypopnea index. Poorer outcomes at 3 months were also associated with insomnia, restless legs syndrome, depressive symptoms, and decreased total sleep time and rapid eye movement sleep.

Long-Term Efficacy and Safety of Pitolisant for Residual Sleepiness Due to OSA.

BACKGROUND: In people with OSA, excessive daytime sleepiness is a prominent symptom and can persist despite adherence to CPAP, the first-line therapy for OSA. Pitolisant was effective in reducing daytime sleepiness in two 12-week randomized controlled trials (RCTs), one in patients adherent to CPAP (BF2.649 in Patients With OSA and Treated by CPAP But Still Complaining of EDS [HAROSA 1]) and the other in patients refusing or not tolerating CPAP (BF2.649 in Patients With OSA, Still Complaining of EDS and Refusing to be Treated by CPAP [HAROSA 2]). RESEARCH QUESTION: Does the efficacy and safety of pitolisant persist when these patients take it long-term? STUDY DESIGN AND METHODS: All adults included in the HAROSA 1 and HAROSA 2 RCTs (both pitolisant and placebo arms) were offered pitolisant (up to 20 mg/d) after completion of the short-term double-anonymized phase (ie, from week 13) in an open-label cohort study. The primary efficacy outcome was the change in Epworth Sleepiness Scale score between baseline and week 52. Safety outcomes were treatment-emergent adverse event(s) (TEAE[s]), serious TEAEs, and special interest TEAEs. RESULTS: Out of 512 adults included in the two RCTs, 376 completed the 1-year follow-up. The pooled mean difference in Epworth Sleepiness Scale score from baseline to 1 year for the intention-to-treat sample was -8.0 (95% CI, -8.3 to -7.5). The overall proportions of TEAEs, serious TEAEs, and TEAEs of special interest were 35.1%, 2.0%, and 11.1%, respectively, without any significant difference between patients in the initial pitolisant and placebo arms. No cardiovascular safety issues were reported. INTERPRETATION: Pitolisant is effective in reducing daytime sleepiness over 1 year in adults with OSA, with or without CPAP treatment. Taken for 1 year, it has a good safety profile (including cardiovascular). TRIAL REGISTRATION: ClinicalTrials.gov; Nos.: NCT01071876 and NCT01072968; URL: www. CLINICALTRIALS: gov.

CPAP resumption after a first termination and impact on all-cause mortality in France.

BACKGROUND: Continuation of continuous positive airway pressure (CPAP) therapy after initial prescription has been shown to reduce all-cause mortality versus therapy termination. However, there is a lack of data on the rates and impact of resuming CPAP in patients with obstructive sleep apnoea (OSA). This analysis determined the prevalence of CPAP resumption in the year after termination, characterised determinants of CPAP resumption, and examined the impact of CPAP resumption on all-cause mortality. METHODS: French national health insurance reimbursement system data for adults aged ≥18 years were used. CPAP prescription was identified by specific treatment codes. Patients who resumed CPAP after first therapy termination and continued to use CPAP for 1 year were matched with those who resumed CPAP then terminated therapy for a second time. RESULTS: Out of 103 091 individuals with a first CPAP termination, 26% resumed CPAP over the next 12 months, and 65% of these were still using CPAP 1 year later. Significant predictors of CPAP continuation after resumption included male sex, hypertension and CPAP prescription by a pulmonologist. In the matched population, the risk of all-cause death was 38% lower in individuals who continued using CPAP after therapy resumption versus those who had a second therapy discontinuation (hazard ratio 0.62, 95% CI 0.48-0.79; p=0.0001). CONCLUSION: These data suggest that individuals with OSA who fail initial therapy with CPAP should be offered a second trial with the device to ensure that effective therapy is not withheld from those who might benefit.

Obstructive sleep apnea: a major risk factor for COVID-19 encephalopathy?

BACKGROUND: This study evaluates the impact of high risk of obstructive sleep apnea (OSA) on coronavirus disease 2019 (COVID-19) acute encephalopathy (AE). METHODS: Between 3/1/2020 and 11/1/2021, 97 consecutive patients were evaluated at the Geneva University Hospitals with a neurological diagnosis of COVID-19 AE. They were divided in two groups depending on the presence or absence of high risk for OSA based on the modified NOSAS score (mNOSAS, respectively ≥ 8 and < 8). We compared patients' characteristics (clinical, biological, brain MRI, EEG, pulmonary CT). The severity of COVID-19 AE relied on the RASS and CAM scores. RESULTS: Most COVID-19 AE patients presented with a high mNOSAS, suggesting high risk of OSA (> 80%). Patients with a high mNOSAS had a more severe form of COVID-19 AE (84.8% versus 27.8%), longer mean duration of COVID-19 AE (27.9 versus 16.9 days), higher mRS at discharge (≥ 3 in 58.2% versus 16.7%), and increased prevalence of brain vessels enhancement (98.1% versus 20.0%). High risk of OSA was associated with a 14 fold increased risk of developing a severe COVID-19 AE (OR = 14.52). DISCUSSION: These observations suggest an association between high risk of OSA and COVID-19 AE severity. High risk of OSA could be a predisposing factor leading to severe COVID-19 AE and consecutive long-term sequalae.

Determinants of apnea-hypopnea index variability during home sleep testing.

BACKGROUND: A single-night attended in-laboratory polysomnography or home sleep testing are common approaches for obstructive sleep apnea (OSA) diagnosis. However, internight variability in apnea-hypopnea index value is common, and may result in misclassification of OSA severity and inapropriate treatment decisions. OBJECTIVE: To investigate factors determining short-term apnea-hypopnea index variability using multi-night automated home sleep testing, and to determine how this variability impacts clinical decisions. PATIENTS/METHODS: Adults with suspected OSA who successfully performed three home sleep tests using measurements of mandibular jaw movements (Sunrise, Namur, Belgium) combined with automated machine learning analysis were enrolled. Data analysis included principal component analysis, generalized estimating equation regression and qualitative agreement analysis. RESULTS: 160 individuals who performed three sleep tests over a mean of 8.78 ± 8.48 days were included. The apnea-hypopnea index varied by -0.88 events/h (5th-95th percentile range: -14.33 to 9.72 events/h). Based on a single-night recording, rates of overtreatment and undertreatment would have been of 13.5% and 6.0%, respectively. Regression analysis adjusted for age, sex, body mass index, total sleep time, and time between home sleep tests showed that time spent in deep non-rapid eye movement sleep and with head in supine position were independent significant predictors of the apnea-hypopnea index variability. CONCLUSIONS: At the individual level, short-term internight variability in the apnea-hypopnea index was significantly associated with time spent in deep non-rapid eye movement sleep and head in supine position. Clinical decisions based on a single-night testing may lead to errors in OSA severity classification and incorrect therapeutic decisions.

Auto-adjusted versus fixed positive airway pressure in patients with severe OSA: A large randomized controlled trial.

BACKGROUND AND OBJECTIVE: Continuous positive airway pressure (CPAP) in the treatment of severe obstructive sleep apnoea (OSA) can be used in fixed CPAP or auto-adjusted (APAP) mode. The aim of this prospective randomized controlled clinical study was to evaluate the 3 month-efficacy of CPAP used either in fixed CPAP or APAP mode. METHODS: Eight hundred one patients with severe OSA were included in twenty-two French centres. After 7 days during which all patients were treated with APAP to determine the effective pressure level and its variability, 353 and 351 patients were respectively randomized in the fixed CPAP group and APAP group. After 3 months of treatment, 308 patients in each group were analysed. RESULTS: There was no difference between the two groups in terms of efficacy whatever the level of efficient pressure and pressure variability (p = 0.41). Exactly, 219 of 308 patients (71.1%) in the fixed CPAP group and 212 of 308 (68.8%) in the APAP group (p = 0.49) demonstrated residual apnoea hypopnoea index (AHI) <10/h and Epworth Score <11. Tolerance and adherence were also identical with a similar effect on quality of life and blood pressure evaluation. CONCLUSION: The two CPAP modes, fixed CPAP and APAP, were equally effective and tolerated in severe OSA patients.

Creating an Optimal Approach for Diagnosing Sleep Apnea.

Sleep apnea is nowadays recognized as a treatable chronic disease and awareness of it has increased, leading to an upsurge in demand for diagnostic testing. Conventionally, diagnosis depends on overnight polysomnography in a sleep clinic, which is highly human-resource intensive and ignores the night-to-night variability in classical sleep apnea markers, such as the apnea-hypopnea index. In this review, the authors summarize the main improvements that could be made in the sleep apnea diagnosis strategy; how technological innovations and multi-night home testing could be used to simplify, increase access, and reduce costs of diagnostic testing while avoiding misclassification of severity.

Long-term outcomes of CPAP-treated sleep apnea patients: Impact of blood-pressure responses after CPAP initiation and of treatment adherence.

BACKGROUND AND OBJECTIVE: In randomized controlled trials, continuous positive airway pressure (CPAP) is reported as lowering blood pressure (BP) with a mean systolic blood pressure effect size of 2.5 mmHg. These trials have a median follow-up of less than 6 months. Whether this initial BP response during the first months of CPAP treatment translates into a reduction in long-term cardiovascular events and mortality is unknown. METHODS: This observational study addressed long-term hard cardiovascular outcomes and all-cause mortality in a well-defined population of 241 patients previously included in the AgirSASadom parallel randomized controlled trial (assessing whether fixed-pressure CPAP was superior to auto-adjusted CPAP in reducing BP (baseline evaluations 2010-2012)). Long-term outcomes were analyzed using a Cox survival model, and a logistic regression analysis was performed for long-term CPAP adherence. RESULTS: Sixty-nine cardiovascular events occurred in 61 patients during a median follow-up of 113 months (interquartile range [102 ; 124]) giving an incidence of 26 for 1000 person-years. Twenty-one (8.7%) patients died. BP values at baseline (i.e., office and 24-h BP) was a strong predictor of incident cardiometabolic events and mortality (p < 0.01) whereas initial BP response after the first four months of CPAP was not related to outcomes. Long-term CPAP adherence above 4 h/night was associated with a reduction in all-cause mortality (Log-rank P = 0.02) but not in the occurrence of long-term cardiovascular events. CONCLUSION: Independently of initial blood pressure response, long-term CPAP adherence is one of the prerequisites for reducing mortality.

Respiratory effort during sleep and the rate of prevalent type 2 diabetes in obstructive sleep apnoea.

AIM: To determine the association between total sleep time (TST) spent in increased respiratory effort (RE) and the prevalence of type 2 diabetes in a large cohort of individuals with suspected obstructive sleep apnoea (OSA) referred for in-laboratory polysomnography (PSG). MATERIALS AND METHODS: We conducted a retrospective cross-sectional study using the clinical data of 1128 patients. Non-invasive measurements of RE were derived from the sleep mandibular jaw movements (MJM) bio-signal. An explainable machine-learning model was built to predict prevalent type 2 diabetes from clinical data, standard PSG indices, and MJM-derived parameters (including the proportion of TST spent with increased respiratory effort [REMOV [%TST]). RESULTS: Original data were randomly assigned to training (n = 853) and validation (n = 275) subsets. The classification model based on 18 input features including REMOV showed good performance for predicting prevalent type 2 diabetes (sensitivity = 0.81, specificity = 0.89). Post hoc interpretation using the Shapley additive explanation method found that a high value of REMOV was the most important risk factor associated with type 2 diabetes after traditional clinical variables (age, sex, body mass index), and ahead of standard PSG metrics including the apnoea-hypopnea and oxygen desaturation indices. CONCLUSIONS: These findings show for the first time that the proportion of sleep time spent in increased RE (assessed through MJM measurements) is an important predictor of the association with type 2 diabetes in individuals with OSA.