Identifying obstructive sleep apnea in patients presenting for laser-assisted uvulopalatoplasty

Helping early obstructive sleep apnea diagnosis with machine learning: A systematic review (Preprint)

Background

American Academy of Sleep Medicine guidelines suggest that clinical prediction algorithms can be used to screen patients with obstructive sleep apnea (OSA) without replacing polysomnography, the gold standard.

Objective

We aimed to identify, gather, and analyze existing machine learning approaches that are being used for disease screening in adult patients with suspected OSA.

Methods

We searched the MEDLINE, Scopus, and ISI Web of Knowledge databases to evaluate the validity of different machine learning techniques, with polysomnography as the gold standard outcome measure and used the Prediction Model Risk of Bias Assessment Tool (Kleijnen Systematic Reviews Ltd) to assess risk of bias and applicability of each included study.

Results

Our search retrieved 5479 articles, of which 63 (1.15%) articles were included. We found 23 studies performing diagnostic model development alone, 26 with added internal validation, and 14 applying the clinical prediction algorithm to an independent sample (although not all reporting the most common discrimination metrics, sensitivity or specificity). Logistic regression was applied in 35 studies, linear regression in 16, support vector machine in 9, neural networks in 8, decision trees in 6, and Bayesian networks in 4. Random forest, discriminant analysis, classification and regression tree, and nomogram were each performed in 2 studies, whereas Pearson correlation, adaptive neuro-fuzzy inference system, artificial immune recognition system, genetic algorithm, supersparse linear integer models, and k-nearest neighbors algorithm were each performed in 1 study. The best area under the receiver operating curve was 0.98 (0.96-0.99) for age, waist circumference, Epworth Somnolence Scale score, and oxygen saturation as predictors in a logistic regression.

Conclusions

Although high values were obtained, they still lacked external validation results in large cohorts and a standard OSA criteria definition.

Trial Registration

PROSPERO CRD42021221339; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=221339

Obstructive sleep apnea syndrome: natural history, diagnosis, and emerging treatment options

Sleep apnea is an entity characterized by repetitive upper airway obstruction resulting in nocturnal hypoxia and sleep fragmentation. It is estimated that 2%-4% of the middle-aged population has sleep apnea with a predilection in men relative to women. Risk factors of sleep apnea include obesity, gender, age, menopause, familial factors, craniofacial abnormalities, and alcohol. Sleep apnea has been increasingly recognized as a major health burden associated with hypertension and increased risk of cardiovascular disease and death. Increased airway collapsibility and derangement in ventilatory control responses are the major pathological features of this disorder. Polysomnography (PSG) is the gold-standard method for diagnosis of sleep apnea and assessment of sleep apnea severity; however, portable sleep monitoring has a diagnostic role in the setting of high pretest probability sleep apnea in the absence of significant comorbidity. Positive pressure therapy is the mainstay therapy of sleep apnea. Other treatment modalities, such as upper airway surgery or oral appliances, may be used for the treatment of sleep apnea in select cases. In this review, we focus on describing the sleep apnea definition, risk factor profile, underlying pathophysiologic mechanisms, associated adverse consequences, diagnostic modalities, and treatment strategies.

Severity of obstructive sleep apnea: correlation with clinical examination and patient perception

OBJECTIVE

To correlate clinical history, patient self-perception of obstructive sleep apnea, and physical examination with the severity of OSA.

METHODS

One hundred and two consecutive patients were prospectively enrolled over a 6-month period. All patients underwent a comprehensive history and clinical examination, nasopharyngoscopy, and an overnight-attended polysomnogram.

RESULTS

There were 65 males and 37 females with a mean age of 50.2 +/- 11.3 years (range, 24 to 76 years). The mean apnea-hypopnea index (AHI) was 37.9 +/- 27.7 (range, 0.7 to 111.2). There was a strong correlation between patient self-perception of OSA severity and AHI (r = 0.499, P < 0.0001), and the correlation with AI was 0.577 (P < 0.0001). OSA severity strongly correlated with Friedman Tongue Position grade, (r = 0.389, P < 0.0001), Friedman clinical staging, (r = 0.331, P = 0.0007). Of significance, only 6.9% of patients with mild OSA had a >50% collapse of the base of tongue region, as compared to 65.9% of patients with severe OSA.

CONCLUSION

There is good correlation between clinical examination parameters and the severity of OSA. An algorithm for surgical treatment of OSA should acknowledge both the site of obstruction and the severity of disease.

[Sleep-related breathing disorders. Sleep anamnesis questionnaire and determination of clinical results within the framework of staged diagnostics]

Sleep-related breathing disorders (SBAS) affect approximately 8% of the population of middle aged adults. At the age of 20 years, approximately 10% of the population snore, while at the age of 60 about 50% of men snore. Some 9% of middle aged women and 24% of middle aged men have an apnea hypopnea index (AHI) of >5 (number of nocturnal apnea and hypopnea per hour of sleep). Sleep apnea hypopnea syndrome is found in 2% of the women and 4% of the men, i.e. they have an AHI>5 associated with daytime sleepiness. Forms, check lists, summaries and patient-readable questionnaires have proved helpful in the evaluation of SBAS.

Screening for obstructive sleep apnea: an evidence-based analysis

Sleep disordered breathing is a spectrum of diseases that includes snoring, upper airway resistance syndrome, and obstructive sleep apnea (OSA). Obstructive sleep apnea is a common sleep disorder and is estimated to have an incidence of 24% in men and 9% in women. However, many authors believe that up to 93% of women and 82% of men with moderate to severe OSA remain undiagnosed. There is a strong link between sleep disordered breathing and hypertension, believed to be due to sleep fragmentation, intermittent hypoxemia, and increased sympathetic tone, which results in a higher mortality and morbidity rate among these patients. It is therefore desirable to attempt to diagnose all patients with OSA, to institute early treatment intervention, and to prevent development of cardiovascular complications. The gold standard for diagnosing OSA remains the attended overnight level I polysomnogram. However, in view of the limited resources, including limited number of recording beds, high cost, long waiting lists, and labor requirements, many authors have explored the use of clinical predictors or questionnaires that may help to identify higher-risk patients. Screening devices in the form of single or multiple channel monitoring systems have also been introduced and may represent an alternative method to diagnose OSA. The ideal screening device should be cheap, readily accessible, easily used with minimal instructions, have no risk or side effects to the patient, and be safe and accurate. We review a variety of clinical predictive formulae and several screening devices available for the diagnosis of OSA.

Obstructive sleep apnea syndrome in ambulatory surgical patients

Obstructive sleep apnea in the ambulatory surgery setting has become a more significant concern in recent years because its Identification and recognition are a critical part of preoperative patients' risk assessment. The types of surgeries that can be performed on an outpatient basis have increased and include many specialty procedures that previously were performed on an inpatient basis only. Ambulatory surgery has proven to be a cost-effective alternative for patients and physicians; however, patients in this setting often have complex surgical histories. Perioperative nurses must provide a more integrated approach to patient assessment to recognize, identify, plan, and implement a course of safe care for patients with obstructive sleep apnea. Reviewing patients' histories can help nurses identify symptoms of obstructive sleep apnea, allowing them to alert the surgical team of special requirements. Ambulatory patients with identified obstructive sleep apnea will require a planned course of care. Ambulatory care facilities should have a policy in place to ensure that safe care will be provided to patients for the entire perioperative course.

Lung volume dependence of pharyngeal cross-sectional area by acoustic pharyngometry

Pharyngeal size and the dynamic behavior of the pharynx may be important factors in the modulation of pharyngeal airflow. There are two measures of pharyngeal function: changes in pharyngeal area with lung volume and changes in pharyngeal area in response to externally applied positive pressure. Both measurements have been used for the assessment of pharyngeal function, and both reflect pharyngeal "floppiness." The aim of the present study was to examine the relationship between pharyngeal cross-sectional area, using acoustic reflection technique, and different lung volumes (tidal volume, inspiratory reserve volume, and expiratory reserve volume), to determine whether there are differences in mechanical properties of the pharynx of normal volunteers in response to changes in intrapharyngeal pressure. The acoustic technique was used to assess the pharyngeal cross-sectional area of 40 healthy volunteers (29 men and 11 women) at tidal volume, inspiratory reserve volume, and expiratory reserve volume. In men, the mean pharyngeal area at tidal volume was 3.191 cm2, the mean pharyngeal area at inspiratory reserve volume was 2.976 cm2, and the mean pharyngeal area at expiratory reserve volume was 2.975 cm2. In women, the corresponding pharyngeal area measurements were 2.832, 2.484, and 2.492 cm2. Statistical analysis of results showed that men have a larger pharyngeal cross-sectional area and the pharyngeal airways of men and women act in a similar manner in response to changes in intrapharyngeal pressure, with men having a greater change. Examination of the pharyngeal compliance by acoustic pharyngometry adds to the potential of this technique as a tool for the evaluation of the pharyngeal airway in terms of area and dynamic behavior assessment. This may be of relevance in promotion of the development of upper airway assessment in patients with obstructive sleep apnea.

Normal standard curve for acoustic pharyngometry

Pharyngeal size, compliance, and the dynamic behavior of the upper airway are important factors in the production of obstructive sleep apnea. Assessment of the upper airway for possible site(s) of obstruction is one of the keys to a successful management of the condition. Acoustic pharyngometry has the potential for localizing such sites, however, standardizing the operating technique and producing a standard normal curve is a prerequisite before exploring the potential of this equipment. A total number of 350 normal volunteers (271 males and 79 females) were examined by acoustic pharyngometry and a coefficient of variance of 5% to 7% was obtained from each of them. Mean and standard deviation of pharyngeal area at each point of X-axis (distance) was obtained and analyzed statistically to produce a general standard curve. Using special techniques during examination, the oropharyngeal junction and glottis were located, and thus a mapped acoustic pharyngogram was produced. Mean pharyngeal area was 3.194 cm(2) in males (SD 0.311) and 2.814 cm(2) in females (SD 0.331). Mean glottic area was 1.06 cm(2) in males (SD 0.119) and 0.936 cm(2) in females (SD 0.108). A minimal pharyngeal area is probably needed as a "golden standard" to evaluate patients with obstructive sleep apnea.

Efficacy of laser-assisted uvulopalatoplasty

BACKGROUND AND OBJECTIVE

Laser-assisted uvulopalatoplasty (LAUP) is being used increasingly as a surgical treatment for snoring and obstructive sleep apnea (OSA). There is limited evidence for the success of LAUP in eliminating OSA. This study assesses the efficacy of LAUP in eliminating snoring and OSA and addresses which patients may be the best candidates for LAUP treatment.

STUDY DESIGN/MATERIALS AND METHODS

From January 1994 to January 1996, 297 patients were evaluated for snoring, with 190 (64%) exhibiting some degree of OSA documented by a PSG: 41/ 190 (22%) mild OSA; 33/190 (17%) moderate OSA; 85/190 (45%) severe OSA; 31/190 (16%) severity unknown. Ninety patients (90/ 297) have undergone LAUP treatment: 58/90 (64%) with OSA and 32/90 (36%) with snoring only.

RESULTS

Our results indicate a significant reduction of snoring in patients without OSA, but diminishing success in patients with increasing degrees of OSA. Additionally, LAUP was not efficacious in treating OSA: pre-op respiratory disturbance index (RDI) of 10.8 vs. post-op RDI of 19.5 for mild OSA (P = 0.14); pre-op RDI of 22.9 vs. post-op RDI of 25.4 for moderate OSA (P = 0.43); pre-op RDI of 56.8 vs. post-op RDI of 46.3 (P < 0.05), which is statistically but not clinically significant (i.e., RDI remained in the severe range).

CONCLUSION

We conclude that LAUP is an effective treatment for nonapneic snoring, but does not provide sufficient resolution of OSA, and based on our results, LAUP should be considered as an adjunctive therapy rather than a sole treatment for OSA in most cases.

Mirror-Focused Handpiece for Laser-Assisted Uvulopalatoplasty for the Treatment of Snoring and Sleep Apnea

We describe how a novel mirror-based laser handpiece device allows for the pinpoint coincidence of aiming and surgical beams during uvulopalatoplasty and other laser ablation procedures.

Preoperative, intraoperative, and postoperative management of patients with obstructive sleep apnea syndrome

The patient with untreated, obstructive sleep apnea may present difficult or potentially life-threatening challenges to the surgical team. This is true even if the anticipated surgery is remote to the upper airway. Preoperative recognition of the obstructive apnea is essential as the first step in preventing potential complications. When recognized, intraoperative and postoperative initiative can result in a satisfactory outcome.

Identification of obstructive sleep apnea in patients who snore

As the field of sleep medicine has evolved, the clinical implications of obstructive sleep apnea (OSA) in snoring patients have become well accepted. Recent advances in surgical therapy for snoring allow otolaryngologists to offer simple outpatient treatment to patients with this problem. However, because the incidence of OSA in snorers seeking medical attention is unknown, the appropriate pretreatment evaluation of these patients is a subject of continued debate. Ninety-four snoring patients were recruited for a study to determine the incidence of OSA in this highly selected population. Subjects answered an extensive sleep questionnaire to determine factors that might suggest a diagnosis of OSA. Level III ambulatory sleep studies were performed on each participant. The incidence of OSA in this group was 72% (42% severe and 30% mild to moderate). Twenty of the subjects with OSA also underwent formal level I sleep studies, and the diagnosis of OSA was confirmed in each instance. Although there was a relationship between body mass index and OSA and certain questions correlated with OSA, the sensitivity and specificity of these data alone or in combination were too low to recommend their use in lieu of a formal sleep study. Given the remarkably high incidence of OSA in this group, which may reflect that seen by otolaryngologists who treat snoring, a sleep study should be performed to diagnose OSA and institute therapy for this condition. Level III ambulatory monitoring devices may be the most cost-effective alternative for evaluating this high-risk population.