Treatment options for obstructive sleep apnea

Screening for Obstructive Sleep Apnea Risk by Using Machine Learning Approaches and Anthropometric Features

Obstructive sleep apnea (OSA) is a global health concern and is typically diagnosed using in-laboratory polysomnography (PSG). However, PSG is highly time-consuming and labor-intensive. We, therefore, developed machine learning models based on easily accessed anthropometric features to screen for the risk of moderate to severe and severe OSA. We enrolled 3503 patients from Taiwan and determined their PSG parameters and anthropometric features. Subsequently, we compared the mean values among patients with different OSA severity and considered correlations among all participants. We developed models based on the following machine learning approaches: logistic regression, k-nearest neighbors, naïve Bayes, random forest (RF), support vector machine, and XGBoost. Collected data were first independently split into two data sets (training and validation: 80%; testing: 20%). Thereafter, we adopted the model with the highest accuracy in the training and validation stage to predict the testing set. We explored the importance of each feature in the OSA risk screening by calculating the Shapley values of each input variable. The RF model achieved the highest accuracy for moderate to severe (84.74%) and severe (72.61%) OSA. The level of visceral fat was found to be a predominant feature in the risk screening models of OSA with the aforementioned levels of severity. Our machine learning models can be employed to screen for OSA risk in the populations in Taiwan and in those with similar craniofacial structures.

Machine learning approaches for screening the risk of obstructive sleep apnea in the Taiwan population based on body profile

(a) Objective: Obstructive sleep apnea syndrome (OSAS) is typically diagnosed through polysomnography (PSG). However, PSG incurs high medical costs. This study developed new models for screening the risk of moderate-to-severe OSAS (apnea-hypopnea index, AHI ≥15) and severe OSAS (AHI ≥30) in various age groups and sexes by using anthropometric features in the Taiwan population.(b) Participants: Data were derived from 10,391 northern Taiwan patients who underwent PSG.(c) Methods: Patients' characteristics - namely age, sex, body mass index (BMI), neck circumference, and waist circumference - was obtained. To develop an age- and sex-independent model, various approaches - namely logistic regression, k-nearest neighbor, naive Bayes, random forest (RF), and support vector machine - were trained for four groups based on sex and age (men or women; aged <50 or ≥50 years). Dataset was separated independently (training:70%; validation: 10%; testing: 20%) and Cross-validated grid search was applied for model optimization. Models demonstrating the highest overall accuracy in validation outcomes for the four groups were used to predict the testing dataset.(d) Results: The RF models showed the highest overall accuracy. BMI was the most influential parameter in both types of OSAS severity screening models.(e) Conclusion: The established models can be applied to screen OSAS risk in the Taiwan population and those with similar craniofacial features.

Tratamiento quirúrgico por otorrinolaringología en el síndrome de apnea-hipopnea obstructiva del sueño (SAHOS)

El síndrome de apnea-hipopnea obstructiva del sueño (SAHOS) se caracteriza por la obstrucción parcial o el colapso total de la vía aérea superior, de manera intermitente y repetitiva, por lo que, en un principio, se vio el manejo quirúrgico como una alternativa curativa para esta patología. Sin embargo, en la actualidad se reconoce que la cirugía, aun sin lograr tasas de efectividad muy altas de manera consistente, sí mejora la tolerancia y adaptación a la terapia de presión positiva, la cual sigue siendo la primera línea de manejo.Así, el primer paso antes de pensar en cualquier procedimiento quirúrgico es un adecuado diagnóstico topográfico, de modo que siempre se debe realizar una nasofibrolaringoscopia para identificar el o los sitios de obstrucción. Además, se sabe que el 75% de los pacientes presentan obstrucciones en múltiples niveles y que, cuando el abordaje se hace multinivel, se logra corregir el SAHOS hasta en un 95%. Entre los procedimientos vigentes se encuentran cirugías de nariz, paladar blando, amígdalas, base de lengua, estimulación del nervio hipogloso y procedimientos del esqueleto facial, así como procedimientos coadyuvantes, entre los que están radiofrecuencia e implantes de paladar.

Investigating the association between obstructive sleep apnea and periodontitis

BACKGROUND

Obstructive sleep apnea (OSA) is a sleep disorder characterized by disruptions of normal sleep architecture. Chronic periodontitis is a chronic disease of the periodontium that elicits a general inflammatory response to local dental plaque. It has been suggested that periodontal disease may increase in severity with increasingly severe OSA because both disease entities share common inflammatory pathways, acting synergistically to alter the host response. The aim of this study is to analyze the association between severity of OSA and the prevalence/severity of periodontitis.

METHODS

One hundred patients from a large veterans administration sleep study center (n = 26 normal, n = 21 mild, n = 19 moderate, n = 34 severe) diagnosed with an overnight polysomnogram underwent a comprehensive periodontal examination. Periodontal parameters measured included the following: 1) mean periodontal probing depth (PD); 2) clinical attachment level (CAL); 3) gingival recession; and 4) percentage of sites with bleeding on probing, plaque, PD ≥5 mm, and CAL ≥3 mm.

RESULTS

Seventy-three percent of the sampled population had moderate/severe periodontal disease. χ(2) analyses revealed no significant differences in the prevalence of periodontal disease between the apnea-hypopnea index (AHI) groups, with a negligible Spearman correlation coefficient of 0.246 between AHI severity and periodontal disease severity categories. Analysis of covariance indicated a significant association between AHI severity categories and percentage of sites with plaque, after adjusting for age. Multivariable logistic regression analysis predicting moderate/severe periodontitis with AHI score, age, and smoking status indicated a significant association with age (P = 0.028) but no significant association with the other two predictors.

CONCLUSION

OSA was not significantly associated with the prevalence of moderate/severe periodontitis and the periodontal parameters examined, except percentage plaque.

Evaluation and validation of a method for determining platelet catecholamine in patients with obstructive sleep apnea and arterial hypertension

Background

Measurements of plasma and urinary catecholamine are susceptible to confounding factors that influence the results, complicating the interpretation of sympathetic nervous system (SNS) activity in the Obstructive sleep apnea (OSA) and arterial hypertension (HYP) conditions.

Objective

In this study, we validated a test for platelet catecholamine and compared the catecholamine levels (adrenaline and noradrenaline) in urine, plasma and platelets in patients with OSA and HYP compared with controls.

Methods

In the validation, 30 healthy, nonsmoking volunteers who were not currently undergoing treatment or medication were selected as the control group. One hundred fifty-four individuals (114 OSA, 40 non-OSA) were consecutively selected from the outpatient clinic of the Sleep Institute and underwent clinical, polysomnographic and laboratory evaluation, including the urinary, plasma and platelet levels of adrenaline (AD) and noradrenaline (NA). Patients were then allocated to groups according to the presence of OSA and/or hypertension.

Results

A logistic regression model, controlled for age and BMI, showed that urinary AD and urinary NA were risk factors in the OSA+HYP group and the HYP group; however, the model showed higher levels of platelet NA for OSA without HYP. After 1 year of CPAP (continuous upper airway pressure) treatment, patients (n = 9) presented lower levels of urinary NA (p = 0.04) and platelet NA (p = 0.05).

Conclusion

Urinary NA and AD levels were significantly associated with the condition of hypertension with and without OSA, whereas platelet NA with OSA without comorbidity. These findings suggest that platelet catecholamine levels might reflect nocturnal sympathetic activation in OSA patients without hypertension.

Craniofacial morphology in pediatric patients with persistent obstructive sleep apnea with or without positive airway pressure therapy: a cross-sectional cephalometric comparison with controls

INTRODUCTION

Compression on the midface with nasal mask-delivered positive airway pressure (PAP) therapy in growing patients might contribute to midface retrusion. The objective of this study was to investigate the association between long-term PAP use and craniofacial morphologic pattern in children with persistent obstructive sleep apnea.

METHODS

Images generated with cone-beam volumetric imaging were used to complete lateral cephalometric analyses of anteroposterior projection of the midface region. The study group included 12 subjects (10 boys, 2 girls; mean age, 9.0 years) who used PAP therapy for at least 6 months and at least 6 hours per night. Measurements from this group were compared with those of a control group of 11 subjects (5 boys, 6 girls; mean age, 9.6 years) with obstructive sleep apnea who did not have PAP. Measurements were taken at 1 time point.

RESULTS

No significant differences were identified between the groups for any cephalometric variable. Multivariate linear regression analysis also did not identify a significant association between the number of months of PAP therapy and the cephalometric variables. Cephalometric data for both groups were pooled for comparison with appropriate published normative values for age and sex. Anterior cranial base length, overall anteroposterior length of the maxillary base, and mandibular body length were significantly shorter than normal in the subjects compared with published normative values.

CONCLUSIONS

No association was demonstrated between midface projection and PAP use in growing patients. When compared with normative data for anterior cranial base, children with obstructive sleep apnea had shorter maxillary and mandibular lengths.

The effect of geniglossal advancement on airway flow using a computational flow dynamics model

OBJECTIVES/HYPOTHESIS

Obstructive sleep apnea (OSA) is a sleep disorder caused by partial or complete collapse of the pharyngeal airway. Genioglossal advancement (GGA) is a well-tolerated surgical procedure intended to address hypopharyngeal collapse, yet there are few studies that monitor changes in airflow dynamics at this site. Computation fluid dynamics (CFD) utilizes airflow simulation to predict changes in airflow after anatomic manipulation.

STUDY DESIGN

We investigated the change in volume and airflow dynamics of the pharyngeal airway after GGA in a cadaveric model.

METHODS

We performed serial GGA from 1 mm (control) to 3, 7, and 9 mm on a lightly preserved cadaver. After each intervention, we performed high-resolution computed tomography scans, reconstructed the pharyngeal airway, and quantified airspace volume and CFD analysis with both laminar and large eddy simulation models.

RESULTS

Airway volume increased with linear GGA. In both CFD simulation models, velocity increased and pressure decreased after 9-mm advancement secondary to increased airway diameter and less abrupt changes in airway geometry.

CONCLUSIONS

These results suggest that GGA may be effective in increasing airway volume and flow to address hypopharyngeal obstruction in OSA.

Obstructive sleep apnea hypopnea syndrome and metabolic syndrome: a synergistic cardiovascular risk factor

PURPOSE

Cardiovascular disease (CVD) is the leading cause of morbidity and mortality for adults in the United States. One risk factor for CVD is metabolic syndrome, which encompasses obesity, hypertension, insulin resistance, proinflammatory state, and prothrombotic state. A lesser-understood risk factor is obstructive sleep apnea hypopnea syndrome (OSAHS). This article explores the physiological consequences of the interaction between OSAHS and metabolic syndrome on the cardiovascular system.

DATA SOURCES

Search terms "metabolic syndrome,""obstructive sleep apnea,""cardiovascular disease,""diabetes,""obesity," and "atherosclerosis," were used. Studies involving children were excluded.

CONCLUSIONS

Both metabolic syndrome and OSAHS have significant impact on the cardiovascular system; however, when both conditions are present together, the impact is synergistic and CVD risk is multiplied. Treatment with continuous positive airway pressure (CPAP) reduces the global burden of CVD risk.

IMPLICATIONS FOR PRACTICE

Providers need to screen patients routinely for both metabolic syndrome and OSAHS. Treatment should include CPAP, weight reduction, oral appliances, and/or upper airway surgeries with concurrent management for metabolic syndrome. Future research should further elucidate the mechanisms of action by which OSAHA and metabolic syndrome contribute to CVD. This understanding can lead to more stringent guidelines on the management of metabolic syndrome and OSAHS.

Comparison of adjustable and fixed oral appliances for the treatment of obstructive sleep apnea

STUDY OBJECTIVES

To compare the efficacy of adjustable and fixed oral appliances for the treatment of OSA.

METHODS

Retrospective review of consecutive patients with OSA treated with either adjustable or fixed oral appliances. Polysomnography was conducted before and during therapy. Effective treatment was defined as an apnea-hypopnea index (AHI) < 5 events/h or < 10 events/h with resolution of sleepiness (Epworth < 10). We compared efficacy rates between fixed and adjustable appliances and sought to identify factors associated with greater success.

RESULTS

We included 805 patients, 602 (74.8%) treated with an adjustable and 203 (25.2%) a fixed oral appliances. Among the cohort, 86.4% were men; mean age was 41.3 ± 9.2 years. Mean AHI was 30.7 ± 25.6, with 34.1% having mild (AHI 5-14.9), 29.2% moderate (AHI 15-29.9), and 36.8% severe (AHI ≥ 30) OSA. Successful therapy was significantly more common with adjustable appliances. Obstructive events were reduced to < 5/h in 56.8% with adjustable compared to 47.0% with fixed appliances (p = 0.02). Similarly, a reduction of events to < 10 with resolution of sleepiness occurred in 66.4% with adjustable appliances versus 44.9% with fixed appliances (p < 0.001). For both devices, success was more common in younger patients, with lower BMI and less severe disease.

CONCLUSIONS

Adjustable devices produced greater reductions in obstructive events and were more likely to provide successful therapy, especially in moderate-severe OSA. Fixed appliances were effective in mild disease, but were less successful in those with higher AHIs. Given these findings, the baseline AHI should be considered when selecting the type of oral appliance.

Nasal continuous positive airway pressure (nCPAP) treatment for obstructive sleep apnea, road traffic accidents and driving simulator performance: a meta-analysis

We used meta-analysis to synthesize current evidence regarding the effect of nasal continuous positive airway pressure (nCPAP) on road traffic accidents in patients with obstructive sleep apnea (OSA) as well as on their performance in driving simulator. The primary outcomes were real accidents, near miss accidents, and accident-related events in the driving simulator. Pooled odds ratios (ORs), incidence rate ratios (IRRs) and standardized mean differences (SMDs) were appropriately calculated through fixed or random effects models after assessing between-study heterogeneity. Furthermore, risk differences (RDs) and numbers needed to treat (NNTs) were estimated for real and near miss accidents. Meta-regression analysis was performed to examine the effect of moderator variables and publication bias was also evaluated. Ten studies on real accidents (1221 patients), five studies on near miss accidents (769 patients) and six studies on the performance in driving simulator (110 patients) were included. A statistically significant reduction in real accidents (OR=0.21, 95% CI=0.12-0.35, random effects model; IRR=0.45, 95% CI=0.34-0.59, fixed effects model) and near miss accidents (OR=0.09, 95% CI=0.04-0.21, random effects model; IRR=0.23, 95% CI=0.08-0.67, random effects model) was observed. Likewise, a significant reduction in accident-related events was observed in the driving simulator (SMD=-1.20, 95% CI=-1.75 to -0.64, random effects). The RD for real accidents was -0.22 (95% CI=-0.32 to -0.13, random effects), with NNT equal to five patients (95% CI=3-8), whereas for near miss accidents the RD was -0.47 (95% CI=-0.69 to -0.25, random effects), with NNT equal to two patients (95% CI=1-4). For near miss accidents, meta-regression analysis suggested that nCPAP seemed more effective among patients entering the studies with higher baseline accident rates. In conclusion, all three meta-analyses demonstrated a sizeable protective effect of nCPAP on road traffic accidents, both in real life and virtual environment.

Brain-derived neurotrophic factor rescues and prevents chronic intermittent hypoxia-induced impairment of hippocampal long-term synaptic plasticity

Obstructive sleep apnea (OSA) is a common sleep and breathing disorder characterized by repeated episodes of hypoxemia. OSA causes neurocognitive deficits including perception and memory impairment but the underlying mechanisms are unknown. Here we show that in a mouse model of OSA, chronic intermittent hypoxia treatment impairs both early- and late-phase long-term potentiation (LTP) in the hippocampus. In intermittent hypoxia-treated mice the excitability of CA1 neurons was reduced and hippocampal brain-derived neurotrophic factor (BDNF) was down-regulated. We further showed that exogenous application of BDNF restored the magnitude of LTP in hippocampal slices from hypoxia-treated mice. In addition, microinjection of BDNF into the brain of the hypoxic mice prevented the impairment in LTP. These data suggest that intermittent hypoxia impairs hippocampal neuronal excitability and reduces the expression of BDNF leading to deficits in LTP and memory formation. Thus, BDNF level may be a novel therapeutic target for alleviating OSA-induced neurocognitive deficits.