Studying sleep: towards the identification of hypnogram features that drive expert interpretation.

STUDY OBJECTIVES: Hypnograms contain a wealth of information and play an important role in sleep medicine. However, interpretation of the hypnogram is a difficult task and requires domain knowledge and "clinical intuition." This study aimed to uncover which features of the hypnogram drive interpretation by physicians. In other words, make explicit which features physicians implicitly look for in hypnograms. METHODS: Three sleep experts evaluated up to 612 hypnograms, indicating normal or abnormal sleep structure and suspicion of disorders. ElasticNet and convolutional neural network classification models were trained to predict the collected expert evaluations using hypnogram features and stages as input. The models were evaluated using several measures, including accuracy, Cohen's kappa, Matthew's correlation coefficient, and confusion matrices. Finally, model coefficients and visual analytics techniques were used to interpret the models to associate hypnogram features with expert evaluation. RESULTS: Agreement between models and experts (Kappa between 0.47 and 0.52) is similar to agreement between experts (Kappa between 0.38 and 0.50). Sleep fragmentation, measured by transitions between sleep stages per hour, and sleep stage distribution were identified as important predictors for expert interpretation. CONCLUSIONS: By comparing hypnograms not solely on an epoch-by-epoch basis, but also on these more specific features that are relevant for the evaluation of experts, performance assessment of (automatic) sleep-staging and surrogate sleep trackers may be improved. In particular, sleep fragmentation is a feature that deserves more attention as it is often not included in the PSG report, and existing (wearable) sleep trackers have shown relatively poor performance in this aspect.

Sleep Apnea is Associated With Accelerated Vascular Aging: Results From 2 European Community-Based Cohort Studies.

Background The mechanisms underlying the association between obstructive sleep apnea (OSA) and cardiovascular disease may include accelerated vascular aging. The aim was to compare the magnitude of vascular aging in patients with high versus low risk of OSA. Methods and Results In 2 community-based studies, the PPS3 (Paris Prospective Study 3) and the Maastricht Study, high risk of OSA was determined with the Berlin questionnaire (a screening questionnaire for OSA). We assessed carotid artery properties (carotid intima-media thickness, Young's elastic modulus, carotid-femoral pulse wave velocity, carotid pulse wave velocity, carotid diameter using high precision ultrasound echography), and carotid-femoral pulse wave velocity (in the Maastricht Study only). Regression coefficients were estimated on pooled data using multivariate linear regression. A total of 8615 participants without prior cardiovascular disease were included (6840 from PPS3, 62% men, mean age 59.5±6.2 years, and 1775 from the Maastricht Study, 51% men, 58.9±8.1 years). Overall, high risk of OSA prevalence was 16.8% (n=1150) in PPS3 and 23.8% (n=423) in the Maastricht Study. A high risk of OSA was associated with greater carotid intima-media thickness (ß=0.21; 0.17-0.26), Young's elastic modulus (ß=0.21; 0.17-0.25), carotid-femoral pulse wave velocity (ß=0.24; 0.14-0.34), carotid pulse wave velocity (ß=0.31; 0.26-0.35), and carotid diameter (ß=0.43; 0.38-0.48), after adjustment for age, sex, total cholesterol, smoking, education level, diabetes mellitus, heart rate, and study site. Consistent associations were observed after additional adjustments for mean blood pressure, body mass index, or antihypertensive medications. Conclusions These data lend support for accelerated vascular aging in individuals with high risk of OSA. This may, at least in part, underlie the association between OSA and cardiovascular disease.

Chronic obstructive pulmonary disease and atrial fibrillation: an interdisciplinary perspective.

Chronic obstructive pulmonary disease (COPD) is highly prevalent among patients with atrial fibrillation (AF), shares common risk factors, and adds to the overall morbidity and mortality in this population. Additionally, it may promote AF and impair treatment efficacy. The prevalence of COPD in AF patients is high and is estimated to be ∼25%. Diagnosis and treatment of COPD in AF patients requires a close interdisciplinary collaboration between the electrophysiologist/cardiologist and pulmonologist. Differential diagnosis may be challenging, especially in elderly and smoking patients complaining of unspecific symptoms such as dyspnoea and fatigue. Routine evaluation of lung function and determination of natriuretic peptides and echocardiography may be reasonable to detect COPD and heart failure as contributing causes of dyspnoea. Acute exacerbation of COPD transiently increases AF risk due to hypoxia-mediated mechanisms, inflammation, increased use of beta-2 agonists, and autonomic changes. Observational data suggest that COPD promotes AF progression, increases AF recurrence after cardioversion, and reduces the efficacy of catheter-based antiarrhythmic therapy. However, it remains unclear whether treatment of COPD improves AF outcomes and which metric should be used to determine COPD severity and guide treatment in AF patients. Data from non-randomized studies suggest that COPD is associated with increased AF recurrence after electrical cardioversion and catheter ablation. Future prospective cohort studies in AF patients are needed to confirm the relationship between COPD and AF, the benefits of treatment of either COPD or AF in this population, and to clarify the need and cost-effectiveness of routine COPD screening.

Obstructive sleep apnea and the risk of gout: a population-based case-control study.

BACKGROUND: Patients with obstructive sleep apnea (OSA) might be at risk of gout because of pathophysiological mechanisms that can lead to hyperuricemia and eventually gout or because of shared risk factors between both diseases. The objective of the present study was to investigate the risk of gout in patients with OSA. METHODS: A population-based case-control study using the UK Clinical Practice Research Datalink GOLD including all patients aged 40 years and older with a first diagnosis of gout between 1987 and 2014. Gout cases were matched by year of birth, sex, and practice to non-gout controls. Conditional logistic regression estimated the risk of gout with an earlier diagnosis of OSA. Analyses were adjusted for lifestyle factors, comorbidities, and recent drug use. RESULTS: One hundred eleven thousand five hundred nine cases were matched with 210,241 controls. Patients with OSA were at increased risk of gout (OR 1.86; 95%CI (1.71-2.02). However, this association disappeared (OR 1.05; 95% CI 0.96-1.16) after adjustment for smoking status, body mass index (BMI), alcohol use, a history of heart failure, diabetes mellitus, renal function, and recent use of diuretics and other medications. Among females with OSA and patients with OSA associated with heart failure, renal impairment, or higher BMI, the risk of gout was however still increased when compared to the total control population. CONCLUSION: This study showed that the observed association between OSA and gout disappeared after adjustment.

Pulmonary rehabilitation, physical activity, respiratory failure and palliative respiratory care.

The CIRO Academy in Horn (the Netherlands) organised a 2-day meeting to present and discuss the studies published in 2017 pertaining to key priority areas of respiratory and critical care medicine. This review summarises studies focussing on pulmonary rehabilitation and exercise training, physical activity, chronic respiratory failure and palliative respiratory care published in 2017.

Severity of nocturnal hypoxia and daytime hypercapnia predicts CPAP failure in patients with COPD and obstructive sleep apnea overlap syndrome.

BACKGROUND: Obstructive sleep apnea (OSA) and chronic obstructive pulmonary disease (COPD) are independent risk factors for cardiovascular diseases. In patients with OSA and concurrent COPD, continuous positive airway pressure (CPAP) therapy improves survival. Nevertheless, a significant proportion of such patients do not tolerate CPAP. The aim of the present study was to analyze early predictors of CPAP failure in patients with OSA and concurrent COPD, and to evaluate the effects of bilevel positive airway pressure (BiPAP) in this high-risk group of patients. METHODS: A post hoc analysis from the database of 2100 patients diagnosed with OSA between 2012 and 2014 identified 84 subjects as having concomitant COPD and meeting inclusion criteria. Demographic data, pulmonary function tests, OSA parameters, blood gases, response to CPAP and BiPAP titration, and two months of therapy were collected. A multivariate model was generated to find determinants of CPAP failure. RESULTS: Primary CPAP failure was found in 23% of patients who were more obese (p = 0.018), had worse lung function, lower PO2 (p = 0.023) and higher PCO2 while awake (p < 0.001), and more sleep time with an SpO2 < 90% (CT90%) (p < 0.001) compared to those who responded to CPAP. In multivariate analysis, PCO2 while awake [odds ratio (OR) 29.5, confidence interval (CI) 2.22-391, p = 0.010] and CT90% (OR 1.06, CI 1.01-1.11, p = 0.017) independently predicted CPAP failure after adjustments for covariates. The BiPAP therapy was well tolerated and effectively alleviated hypercapnia in all patients with primary CPAP failure. CONCLUSIONS: Daytime hypercapnia and nocturnal hypoxia are independent predictors of early CPAP failure in patients with the OSA-COPD overlap syndrome.