Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns.

Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.

A mathematical model to serve as a clinical tool for assessing obstructive sleep apnea severity.

Obstructive sleep apnea (OSA) is a sleep disorder caused by periodic airway obstructions and has been associated with numerous health consequences, which are thought to result from tissue hypoxia. However, challenges in the direct measurement of tissue-level oxygenation make it difficult to analyze the hypoxia exposure pattern in patients. Furthermore, current clinical practice relies on the apnea-hypopnea index (AHI) and pulse oximetry to assess OSA severity, both of which have limitations. To overcome this, we developed a clinically deployable mathematical model, which outputs tissue-level oxygenation. The model incorporates spatial pulmonary oxygen uptake, considers dissolved oxygen, and can use time-dependent patient inputs. It was applied to explore a series of breathing patterns that are clinically differentiated. Supporting previous studies, the result of this analysis indicated that the AHI is an unreliable indicator of hypoxia burden. As a proof of principle, polysomnography data from two patients was analyzed with this model. The model showed greater sensitivity to breathing in comparison with pulse oximetry and provided systemic venous oxygenation, which is absent from clinical measurements. In addition, the dissolved oxygen output was used to calculate hypoxia burden scores for each patient and compared to the clinical assessment, highlighting the importance of event length and cumulative impact of obstructions. Furthermore, an intra-patient statistical analysis was used to underscore the significance of closely occurring obstructive events and to highlight the utility of the model for quantitative data processing. Looking ahead, our model can be used with polysomnography data to predict hypoxic burden on the tissues and help guide patient treatment decisions.

Clinical and financial impact of sleep disordered breathing on heart failure admissions.

BACKGROUND: The impact of sleep disordered breathing (SDB) on heart failure (HF) is increasingly recognized. However, limited data exist in support of quantification of the clinical and financial impact of SDB on HF hospitalizations. METHODS: A sleep-heart registry included all patients who underwent inpatient sleep testing during hospitalization for HF at a single cardiac center. Readmission data and actual costs of readmissions were obtained from the institutional honest broker. Patients were classified based on the inpatient sleep study as having no SDB, obstructive sleep apnea (OSA), or central sleep apnea (CSA). Cumulative cardiac readmission rates and costs through 3 and 6 months post-discharge were calculated. Unadjusted and adjusted (age, sex, body mass index, and left ventricular ejection fraction) modeling of cost was performed. RESULTS: The cohort consisted of 1547 patients, 393 (25%) had no SDB, 438 (28%) had CSA, and 716 (46%) had OSA. Within 6 months of discharge, 195 CSA patients (45%), 264 OSA patients (37%), and 109 no SDB patients (28%) required cardiovascular readmissions. Similarly, 3- and 6-month mortality rates were higher in both SDB groups than those with no SDB. Both unadjusted and adjusted readmission costs were higher in the OSA and CSA groups compared to no SDB group at 3 and 6 months post-discharge with the CSA and OSA group costs nearly double (~ $16,000) the no SDB group (~ $9000) through 6 months. INTERPRETATION: Previously undiagnosed OSA and CSA are common in patients hospitalized with HF and are associated with increased readmissions rate and mortality.

Pathways of Microcirculatory Endothelial Dysfunction in Obstructive Sleep Apnea: A Comprehensive Ex Vivo Evaluation in Human Tissue.

BACKGROUND: The mechanism and markers of cardiovascular disease (CVD) in obstructive sleep apnea (OSA) remain unknown. The microcirculation is the site of early changes in OSA patients who are free of CVD risk. METHODS: Patients with newly diagnosed moderate to severe OSA (n = 7) were studied before and 12 weeks after intensive treatment with continuous positive airway pressure (CPAP), along with weight and age matched controls (n = 7). Microcirculatory vessels were isolated from gluteal biopsies and changes in critical functional genes were measured. RESULTS: The following genes changed after 12 weeks of intensive CPAP therapy in the microcirculatory vessels: angiotensin receptor type 1 (AGTR-1) (11.6 (3.4) to 6 (0.8); P = 0.019); NADPH oxidase (NOX4) (0.85 (0.02) to 0.79 (0.11); P = 0.016); and dimethylarginine dimethylaminohydrolase (DDAH 1) (1 (0.31) to 0.55 (0.1); P = 0.028). Despite decreased nitric oxide (NO) availability as measured indirectly through brachial artery flow-mediated dilation, endothelial NO synthase (NOS3) did not change with CPAP. Other disease markers of OSA that changed with treatment in the microcirculation were endothelin, hypoxia inducible factor 1a, nuclear factor kappa B, interleukin-8, and interleukin-6. CONCLUSIONS: In this ex vivo evaluation of the microcirculation of patients with OSA and no CVD risk, several pathways of CVD were activated supporting that OSA independently induces microcirculatory endothelial dysfunction and serving as disease-specific markers for future pharmacological targeting of OSA-related CVD risk. The findings support the role of renin-angiotensin activation and endothelial oxidative stress in the decreased microcirculatory NO availability in OSA.

Central sleep apnea treatment in patients with heart failure with reduced ejection fraction: a network meta-analysis.

PURPOSE: Adaptive servo-ventilation (ASV) is contraindicated for the treatment of central sleep apnea (CSA) in patients with heart failure with reduced ejection fraction (HFrEF), limiting treatment options. Though continuous positive airway pressure (CPAP), bi-level PAP with back-up rate (BPAP-BUR), and transvenous phrenic nerve stimulation (TPNS) are alternatives, not much is known about their comparative efficacies, which formed the basis of conducting this network meta-analysis. We sought to analyze their comparative effectiveness in reducing apnea hypopnea index (AHI). Additionally, we also studied their comparative effectiveness on subjective daytime sleepiness as assessed by Epworth sleepiness score (ESS). METHODS: Randomized controlled trials (RCTs) from PubMed were analyzed in a network meta-analysis and relative superiority was computed based on P-score ranking and Hasse diagrams. RESULTS: Network meta-analysis based on 8 RCTs showed that when compared to guideline-directed medical therapy (GDMT-used as a common comparator across trials), reduction in AHI by ASV (- 26.05 [- 38.80; - 13.31]), TPNS (- 24.90 [- 42.88; - 6.92]), BPAP-BUR (- 20.36 [- 36.47; - 4.25]), and CPAP (- 16.01 [- 25.42; - 6.60]) were statistically significant but not between the interventions. Based on 6 RCTs of all the interventions, only TPNS showed a statistically significant decrease in ESS (- 3.70 (- 5.58; - 1.82)) when compared to GDMT, while also showing significant differences when compared with ASV (- 3.20 (- 5.86; - 0.54)), BPAP-BUR (- 4.00 (- 7.33; - 0.68)), and CPAP (- 4.45 (- 7.75; - 1.14)). Ranking of treatments based on Hasse diagram, accounting for both AHI and ESS as outcomes for relative hierarchy showed relative superiority of both ASV and TPNS over BPAP-BUR and CPAP. CONCLUSIONS: Results indicated relative superiority of TPNS and ASV to BPAP-BUR and CPAP in their effects on AHI and ESS.

Transvenous Phrenic Nerve Stimulation for Central Sleep Apnea: Clinical and Billing Review.

Central sleep apnea (CSA) frequently coexists with heart failure and atrial fibrillation and contributes to cardiovascular disease progression and mortality. A transvenous phrenic nerve stimulation (TPNS) system has been approved for the first time by the Food and Drug Administration for the treatment of CSA. This system, remede System (Zoll Medical, Inc.), is implanted during a minimally invasive outpatient procedure and has shown a favorable safety and efficacy profile. Currently, patient access to this therapy remains limited by the small number of specialized centers in the United States and the absence of a standard coverage process by insurers. Although a period of evaluation by insurers is expected for new therapies in their early stages, the impact on patients is particularly severe given the already limited treatment options for CSA. Implantation and management of this novel therapy require the establishment of a specialized multidisciplinary program as part of a sleep medicine practice and support from health care systems and hospitals. Several centers in the United States have been successful in building sustainable TPNS programs offering this novel therapy to their patients by navigating the current reimbursement environment. In this article, we review the background and efficacy data of TPNS and briefly address relevant aspects of the clinical activities involved in a TPNS program. The article presents the status of coverage and reimbursement for this novel therapy. We also discuss the current approach to obtaining reimbursement from third-party payors during this transitional period of evaluation by Medicare and other insurers.

Research Priorities for Patients with Heart Failure and Central Sleep Apnea. An Official American Thoracic Society Research Statement.

Background: Central sleep apnea (CSA) is common among patients with heart failure and has been strongly linked to adverse outcomes. However, progress toward improving outcomes for such patients has been limited. The purpose of this official statement from the American Thoracic Society is to identify key areas to prioritize for future research regarding CSA in heart failure.Methods: An international multidisciplinary group with expertise in sleep medicine, pulmonary medicine, heart failure, clinical research, and health outcomes was convened. The group met at the American Thoracic Society 2019 International Conference to determine research priority areas. A statement summarizing the findings of the group was subsequently authored using input from all members.Results: The workgroup identified 11 specific research priorities in several key areas: 1) control of breathing and pathophysiology leading to CSA, 2) variability across individuals and over time, 3) techniques to examine CSA pathogenesis and outcomes, 4) impact of device and pharmacological treatment, and 5) implementing CSA treatment for all individualsConclusions: Advancing care for patients with CSA in the context of heart failure will require progress in the arenas of translational (basic through clinical), epidemiological, and patient-centered outcome research. Given the increasing prevalence of heart failure and its associated substantial burden to individuals, society, and the healthcare system, targeted research to improve knowledge of CSA pathogenesis and treatment is a priority.

A 17-Year-Old With Becker Muscular Dystrophy and Unusual Polysomnography Findings.

CASE PRESENTATION: A 17-year-old male patient who was diagnosed with Becker muscular dystrophy (nonsense mutation [c.3822C>A] within exon 28 of the DMD gene) at 6 years of age was evaluated in the multidisciplinary neuromuscular clinic for loss of ambulation for 1 year. From a pulmonary perspective, there were no acute or chronic respiratory symptoms, and no history of pneumonia or aspiration. Clinical examination revealed a nonambulant teenager, with normal oxygen saturation and end-tidal CO2 when awake, no respiratory distress, and symmetrically diminished aeration due to obesity (BMI 40 kg/m2). Results of pulmonary function testing revealed FVC of 83% predicted with actual volume of 3.5 L and peak cough flow of 445 L/min (all within normal limits).

In-Hospital Management of Sleep Apnea During Heart Failure Hospitalization: A Randomized Controlled Trial.

BACKGROUND: Obstructive sleep apnea (OSA) is associated with increased mortality and readmissions in patients with heart failure (HF). The effect of in-hospital diagnosis and treatment of OSA during decompensated HF episodes remains unknown. METHODS AND RESULTS: A single-site, randomized, controlled trial of hospitalized patients with decompensated HF (n = 150) who were diagnosed with OSA during the hospitalization was undertaken. All participants received guideline-directed therapy for HF decompensation. Participants were randomized to an intervention arm which received positive airway pressure (PAP) therapy during the hospitalization (n = 75) and a control arm (n = 75). The primary outcome was discharge left ventricular ejection fraction (LVEF). The LVEF changed in the PAP arm from 25.5 ± 10.4 at baseline to 27.3 ± 11.9 at discharge. In the control group, LVEF was 27.3 ± 11.7 at baseline and 28.8 ± 10.5 at conclusion. There was no significant effect on LVEF of in-hospital PAP compared with controls (P = .84) in the intention-to-treat analysis. The on-treatment analysis in the intervention arm showed a significant increase in LVEF in participants who used PAP for ≥3 hours per night (n = 36, 48%) compared with those who used it less (P = .01). There was a dose effect with higher hours of use associated with more improvement in LVEF. Follow-up of readmissions at 6 months after discharge revealed a >60% decrease in readmissions for patients who used PAP ≥3 h/night compared with those who used it <3 h/night (P < .02) and compared with controls (P < .04). CONCLUSIONS: In-hospital treatment with PAP was safe but did not significantly improve discharge LVEF in patients with decompensated HF and newly diagnosed OSA. An exploratory analysis showed that adequate use of PAP was associated with higher discharge LVEF and decreased 6 months readmissions.

Update on Apneas of Heart Failure With Reduced Ejection Fraction: Emphasis on the Physiology of Treatment: Part 2: Central Sleep Apnea.

Central sleep apnea/Hunter-Cheyne-Stokes breathing (CSA/HCSB) is prevalent in patients with heart failure with reduced ejection fraction (HFrEF). The acute pathobiologic consequences of CSA/HSCB eventually lead to sustained sympathetic overactivity, repeated hospitalization, and premature mortality. A few randomized controlled trials (RCTs) have shown statistically significant and clinically important reduction in sympathetic activity when CSA/HCSB is attenuated by oxygen or PAP therapy. Yet, the two largest PAP RCTs in patients with HFrEF, one with CPAP and the other with adaptive servoventilation (ASV), were negative with respect to their primary outcomes, and both were associated with excess mortality. However, both trials suffered from significant deficiencies, casting doubt on their results. A second RCT evaluating an ASV device with an advanced algorithm is ongoing. A new modality of therapy, unilateral phrenic nerve stimulation, has undergone an RCT that demonstrated an improvement in CSA that was associated with a reduction in arousals, improvement in sleepiness, and improvement in quality of life. However, a long-term mortality trial has not been performed with this modality. Most recently, the National Institutes of Health has funded a long-term, phase 3 RCT of low-flow oxygen vs sham for the treatment of CSA/HCSB in HFrEF. The composite primary outcome includes all-cause mortality and hospitalization for worsening HF. In this article, we focus on various therapeutic options for the treatment of CSA/HCSB and, when appropriate, emphasize the importance of identifying CSA/HCSB phenotypes to tailor treatment.

Phrenic nerve stimulation to treat patients with central sleep apnoea and heart failure.

AIMS: The presence of central sleep apnoea (CSA) is associated with poor prognosis in patients with heart failure (HF). The aim of this analysis was to evaluate if using phrenic nerve stimulation to treat CSA in patients with CSA and HF was associated with changes in HF-specific metrics. METHODS AND RESULTS: All patients randomized in the remede System Pivotal Trial and identified at baseline with HF were included (n = 96). Effectiveness data from treatment and former control groups were pooled based on months since therapy activation. Changes from baseline to 6 and 12 months in sleep metrics, Epworth Sleepiness Scale, patient global assessment health-related quality of life, Minnesota Living with Heart Failure Questionnaire (MLHFQ), and echocardiographic parameters are reported. HF hospitalization, cardiovascular death, and the composite of HF hospitalization or cardiovascular death within 6 months are reported by the original randomized group assignment for safety assessment. Sleep metrics and quality of life improved from baseline to 6 and 12 months. At 12 months, MLHFQ scores changed by -6.8 ± 20.0 (P = 0.005). The 6-month rate of HF hospitalization was 4.7% in treatment patients (standard error = 3.3) and 17.0% in control patients (standard error = 5.5) (P = 0.065). Reported adverse events were as expected for a transvenous implantable system. CONCLUSIONS: Phrenic nerve stimulation reduces CSA severity in patients with HF. In parallel, this CSA treatment was associated with benefits on HF quality of life.

Sustained 12 Month Benefit of Phrenic Nerve Stimulation for Central Sleep Apnea.

Transvenous phrenic nerve stimulation improved sleep metrics and quality of life after 6 months versus control in the remede System Pivotal Trial. This analysis explored the effectiveness of phrenic nerve stimulation in patients with central sleep apnea after 12 months of therapy. Reproducibility of treatment effect was assessed in the former control group in whom the implanted device was initially inactive for the sixth month and subsequently activated when the randomized control assessments were complete. Patients with moderate-to-severe central sleep apnea implanted with the remede System were randomized to therapy activation at 1 month (treatment) or after 6 months (control). Sleep indices were assessed from baseline to 12 months in the treatment group and from 6 to 12 months in former controls. In the treatment group, a ≥50% reduction in apnea-hypopnea index occurred in 60% of patients at 6 months (95% confidence interval [CI] 47% to 64%) and 67% (95% CI 53% to 78%) at 12 months. After 6 months of therapy, 55% of former controls (95% CI 43% to 67%) achieved ≥50%reduction in apnea-hypopnea index. Patient Global Assessment was markedly ormoderately improved at 6 and 12 months in 60% of treatment patients.Improvements persisted at 12 months. A serious adverse event within 12 months occurred in 13 patients (9%). Phrenic nerve stimulation produced sustained improvements in sleep indices and quality of life to at least 12 months in patients with central sleep apnea. The similar improvement of former controls after 6 months of active therapy confirms benefits are reproducible and reliable.

Angiotensin Receptor Expression and Vascular Endothelial Dysfunction in Obstructive Sleep Apnea.

BACKGROUND: Obstructive sleep apnea (OSA) is associated with vascular endothelial dysfunction (VED) in otherwise healthy patients. The role of renin-angiotensin system (RAS) in the OSA induced VED is not well understood. METHODS: Recently diagnosed OSA patients with very low cardiovascular disease (CVD) risk (Framingham score <5%) were studied at diagnosis and after 12 weeks of verified continuous positive airway pressure (CPAP) therapy. Participants underwent biopsy of gluteal subcutaneous tissue at baseline and after CPAP. Microcirculatory endothelial expression of angiotensin receptors type-1 (AT-1) and type-2 (AT-2) was measured in the subcutaneous tissue using quantitative confocal microscopy techniques. The ex-vivo effect of AT-1 receptor blockade (ARB) on endothelial superoxide production was also measured before and after CPAP treatment. RESULTS: In OSA patients (n = 11), microcirculatory endothelial AT1 expression decreased from 873 (200) (fluorescence units) at baseline to 393 (59) units after 12 weeks of CPAP (P = 0.02). AT2 expression did not decrease significantly in these patients (479 (75) to 329 (58) post CPAP (P = 0.08)). The ex-vivo addition of the losartan to the microcirculatory endothelium resulted in decreased superoxide expression in the vascular walls from 14.2 (2.2) units to 4.2 (0.8) P < 0.001; while it had no effect on post-CPAP patient tissue (P = 0.64). CONCLUSIONS: In OSA patients with no to minimal CVD risk, VED is associated with upregulation of AT-1 expression that is reversible with CPAP. Endothelial oxidative stress was reversible with ARB. RAS activation may play an important role in the development of early CVD risk in OSA patients.

Role of Dietary Antioxidants in the Preservation of Vascular Function and the Modulation of Health and Disease.

In vascular diseases, including hypertension and atherosclerosis, vascular endothelial dysfunction (VED) occurs secondary to altered function of endothelial nitric oxide synthase (eNOS). A novel redox regulated pathway was identified through which eNOS is uncoupled due to S-glutathionylation of critical cysteine residues, resulting in superoxide free radical formation instead of the vasodilator molecule, nitric oxide. In addition, the redox sensitive cofactor tetrahydrobiopterin, BH4, is also essential for eNOS coupling. Antioxidants, either individually or combined, can modulate eNOS uncoupling by scavenging free radicals or impairing specific radical generating pathways, thus preventing oxidative stress and ameliorating VED. Epidemiological evidence and dietary guidelines suggest that diets high in antioxidants, or antioxidant supplementation, could preserve vascular health and prevent cardiovascular diseases (CVDs). Therefore, the purpose of this review is to highlight the possible role of dietary antioxidants in regulating eNOS function and uncoupling which is critical for maintenance of vascular health with normal blood flow/circulation and prevention of VED. We hypothesize that a conditioned dietary approach with suitable antioxidants may limit systemic oxidation, maintain a beneficial ratio of reduced to oxidized glutathione, and other redox markers, and minimize eNOS uncoupling serving to prevent CVD and possibly other chronic diseases.

A Practical Approach to the Identification and Management of Sleep-Disordered Breathing in Heart Failure Patients.

Sleep-disordered breathing (SDB) is a major health problem affecting much of the general population. Although SDB is responsible for rapid progression of heart failure (HF) and the worsening morbidity and mortality, advanced HF state is associated with accelerated development of SDB. In the face of recent developments in SDB treatment and availability of effective therapeutic options known to improve quality of life, exercise tolerance, and heart function, most HF patients with SDB are left unrecognized and untreated. This article provides an overview of SDB in HF with focus on practical approaches intended to facilitate screening and treatment.

Transvenous neurostimulation for central sleep apnoea: a randomised controlled trial.

BACKGROUND: Central sleep apnoea is a serious breathing disorder associated with poor outcomes. The remedé system (Respicardia Inc, Minnetonka, MN, USA) is an implantable device which transvenously stimulates a nerve causing diaphragmatic contraction similar to normal breathing. We evaluated the safety and effectiveness of unilateral neurostimulation in patients with central sleep apnoea. METHODS: We recruited patients from 31 hospital-based centres in Germany, Poland, and the USA in this prospective, multicentre, randomised trial. Participants had to have been medically stable for at least 30 days and have received appropriate guideline recommended therapy, be aged at least 18 years, be expected to tolerate study procedures, and willing and able to comply with study requirements. Eligible patients with an apnoea-hypopnoea index (AHI) of at least 20 events per h, tested by a polysomnography, underwent device implantation and were randomly assigned (1:1) by a computer-generated method stratified by site to either stimulation (treatment) or no stimulation (control) for 6 months. The primary effectiveness endpoint in the intention-to-treat population was the comparison of the proportions of patients in the treatment versus control groups achieving a 50% or greater AHI reduction from baseline to 6 months, measured by a full-night polysomnography assessed by masked investigators in a core laboratory. The primary safety endpoint of 12-month freedom from serious adverse events related to the procedure, system, or therapy was evaluated in all patients. This trial is active, but not recruiting, and is registered with ClinicalTrials.gov (NCT01816776). FINDINGS: Between April 17, 2013, and May 28, 2015, we randomly assigned 151 eligible patients to the treatment (n=73) or control (n=78) groups. In the analysis of the intention-to-treat population, significantly more patients in the treatment group (35 [51%] of 68) had an AHI reduction from baseline of 50% or greater at 6 months than had those in the control group (eight [11%] of 73; difference between groups 41%, 95% CI 25-54, p<0·0001). 138 (91%) of 151 patients had no serious-related adverse events at 12 months. Seven (9%) cases of related-serious adverse events occurred in the control group and six (8%) cases were reported in the treatment group. Seven patients died (unrelated to implant, system, or therapy), four deaths (two in treatment group and two in control group) during the 6-month randomisation period when neurostimulation was delivered to only the treatment group and was off in the control group, and three deaths between 6 months and 12 months of follow-up when all patients received neurostimulation. 27 (37%) of 73 patients in the treatment group reported non-serious therapy-related discomfort that was resolved with simple system reprogramming in 26 (36%) patients, but was unresolved in one (1%) patient. INTERPRETATION: Transvenous neurostimulation significantly reduced the severity of central sleep apnoea, including improvements in sleep metrics, and was well tolerated. The clinically meaningful effects of the therapy are supported by the concordant improvements in oxygenation and quality of life, making transvenous neurostimulation a promising therapeutic approach for central sleep apnoea. FUNDING: Respicardia Inc.