Obstructive Sleep Apnea in Women: Study of Speech and Craniofacial Characteristics

Obstructive sleep apnea detection during wakefulness: a comprehensive methodological review

Obstructive sleep apnea (OSA) is a chronic condition affecting up to 1 billion people, globally. Despite this spread, OSA is still thought to be underdiagnosed. Lack of diagnosis is largely attributed to the high cost, resource-intensive, and time-consuming nature of existing diagnostic technologies during sleep. As individuals with OSA do not show many symptoms other than daytime sleepiness, predicting OSA while the individual is awake (wakefulness) is quite challenging. However, research especially in the last decade has shown promising results for quick and accurate methodologies to predict OSA during wakefulness. Furthermore, advances in machine learning algorithms offer new ways to analyze the measured data with more precision. With a widening research outlook, the present review compares methodologies for OSA screening during wakefulness, and recommendations are made for avenues of future research and study designs.

Automatic detection of obstructive sleep apnea based on speech or snoring sounds: a narrative review

Background and Objective

Obstructive sleep apnea (OSA) is a common chronic disorder characterized by repeated breathing pauses during sleep caused by upper airway narrowing or collapse. The gold standard for OSA diagnosis is the polysomnography test, which is time consuming, expensive, and invasive. In recent years, more cost-effective approaches for OSA detection based in predictive value of speech and snoring has emerged. In this paper, we offer a comprehensive summary of current research progress on the applications of speech or snoring sounds for the automatic detection of OSA and discuss the key challenges that need to be overcome for future research into this novel approach.

Methods

PubMed, IEEE Xplore, and Web of Science databases were searched with related keywords. Literature published between 1989 and 2022 examining the potential of using speech or snoring sounds for automated OSA detection was reviewed.

Key Content and Findings

Speech and snoring sounds contain a large amount of information about OSA, and they have been extensively studied in the automatic screening of OSA. By importing features extracted from speech and snoring sounds into artificial intelligence models, clinicians can automatically screen for OSA. Features such as formant, linear prediction cepstral coefficients, mel-frequency cepstral coefficients, and artificial intelligence algorithms including support vector machines, Gaussian mixture model, and hidden Markov models have been extensively studied for the detection of OSA.

Conclusions

Due to the significant advantages of noninvasive, low-cost, and contactless data collection, an automatic approach based on speech or snoring sounds seems to be a promising tool for the detection of OSA.

Assessment of cephalometric parameters and correlation with the severity of the obstructive sleep apnea syndrome

BACKGROUND

In individuals diagnosed with obstructive sleep apnea syndrome (OSAS), variations in craniofacial structure have been inconsistently documented, showing differing degrees of alteration between obese and nonobese patients. In addition, sleep disturbance has also been shown to induce disequilibrium in this population of patients. This pilot observational study aimed to assess craniofacial values in obese and nonobese subpopulations of patients with OSAS and their correlation and association with the severity of OSAS. We also assessed whether OSAS patients are characterized by an impaired equilibrium in relation to and associated with the severity of OSAS.

METHODS

We included all consecutive adult patients with OSAS. Through cephalometry, we assessed the upper (UPa-UPp) and lower (LPa-LPp) pharynx diameters, superior anterior facial height (Sor-ANS), anterior facial height (ANS-Me), anterior vertical dimension (Sor-Me), posterior facial height (S-Go) and craniovertebral angle (CVA). Furthermore, we analyzed postural equilibrium through a stabilometric examination.

RESULTS

Forty consecutive OSAS patients (45% female with a mean age of 56 ± 8.2 years) were included. The subgroup of nonobese patients had a reduced UPa-UPp (p = 0.02). Cephalometric measurements were correlated with the severity of OSAS in nonobese patients, whereas only Sor-ANS was correlated with the severity of OSAS in the obese subpopulation. In the overall population, altered craniofacial values are associated with severe OSAS. Although there are differences in equilibrium between obese and nonobese OSAS patients, the stabilometric measurements were not correlated or associated with OSAS severity.

CONCLUSION

Altered craniofacial values and compromised equilibrium in OSAS patients are linked to OSAS severity. Therefore, the management of OSAS should be tailored not only to weight management but also to craniofacial and postural rehabilitation to enhance patient outcomes.

Is Bipolar Radiofrequency-Assisted Liposuction Equivalent to Open Anterior Platysmaplasty in Facelift Surgery?

BACKGROUND

During facelift surgery, anterior platysmaplasty (AP) has been used for decades, but it limits lateral advancement and can induce contour irregularities. Radiofrequency (RF)-assisted-liposuction in the anterior neck can avoid these disadvantages by tightening skin without open surgery.

PURPOSE

The purpose of the study was to compare the esthetic outcomes of facelift surgery with those of AP and RF.

STUDY DESIGN, SETTING, SAMPLE

A 5-year retrospective cohort study was performed on facelift patients treated by a single surgeon. Exclusions were single-side surgery, previous facelift, chin/lip augmentation/reduction, and inadequate data.

PREDICTOR VARIABLE

The predictor variable was neck management technique (AP vs RF).

MAIN OUTCOME VARIABLES

The primary outcome variable was the change in cervicomental angle (CMA) following surgery as measured on facial photographs. Secondary outcomes included distance changes from the central CMA point in vertical and horizontal planes to repeatable reference planes.

COVARIATES

Covariates were age, body mass index, American Society of Anesthesiologists classification, smoking, and simultaneous procedures.

ANALYSES

The statistical analysis was performed using Wilcoxon rank-sum, Fisher's exact, Kruskal-Wallis tests, Pearson's correlation, and linear regressions. The level of statistical significance was P < .05.

RESULTS

There were 132 patients included in the study; 67 received AP and 65 received RF. AP trended toward better performance in CMA change in the unadjusted analysis (-18.7° ± 13.8° vs -22.3° ± 13.7°, respectively, P = .08). AP and RF performed similarly in the adjusted analysis (P = .29). Techniques were similar in horizontal distance change to the CMA (P = .31). RF was associated with less change in the vertical distance to the CMA in the unadjusted analysis (-11.9 mm ± 11.0 mm vs -6.7 mm ± 8.7 mm, respectively, P = .01) and adjusted analysis (β = 4.3 mm, 95% confidence interval .8 to 7.9 mm, P = .02).

CONCLUSION AND RELEVANCE

Utilization of the RF technique for management of the anterior neck in facelift surgery is associated with similar outcomes to the AP technique in horizontal distance to the CMA, but AP performed better in CMA change and vertical distance to the CMA.

Self-helped detection of obstructive sleep apnea based on automated facial recognition and machine learning

PURPOSE

The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay diagnosis. With the widespread use of artificial intelligence, we presumed that the combination of simple clinical information and imaging recognition based on facial photos may be a useful tool to screen for OSA.

METHODS

We recruited consecutive subjects suspected of OSA who had received sleep examination and photographing. Sixty-eight points from 2-dimensional facial photos were labelled by automated identification. An optimized model with facial features and basic clinical information was established and tenfold cross-validation was performed. Area under the receiver operating characteristic curve (AUC) indicated the model's performance using sleep monitoring as the reference standard.

RESULTS

A total of 653 subjects (77.2% males, 55.3% OSA) were analyzed. CATBOOST was the most suitable algorithm for OSA classification with a sensitivity, specificity, accuracy, and AUC of 0.75, 0.66, 0.71, and 0.76 respectively (P < 0.05), which was better than STOP-Bang questionnaire, NoSAS scores, and Epworth scale. Witnessed apnea by sleep partner was the most powerful variable, followed by body mass index, neck circumference, facial parameters, and hypertension. The model's performance became more robust with a sensitivity of 0.94, for patients with frequent supine sleep apnea.

CONCLUSION

The findings suggest that craniofacial features extracted from 2-dimensional frontal photos, especially in the mandibular segment, have the potential to become predictors of OSA in the Chinese population. Machine learning-derived automatic recognition may facilitate the self-help screening for OSA in a quick, radiation-free, and repeatable manner.

Craniofacial morphology in patients with obstructive sleep apnea: cephalometric evaluation

Introduction

Obstructive sleep apnea is characterized by a reduced airflow through the upper airways during sleep. Two forms of obstructive sleep apnea are described: the central form and the obstructive form. The obstructive form is related to many factors, such as the craniofacial morphology.

Objective

To evaluate the correlation between the morphology of the cranial base, of the mandible and the maxilla, and obstructive sleep apnea severity.

Methods

Eighty-four patients, mean age of 50.4 years old; 73 males and 11 females with obstructive sleep apnea were enrolled in the present study. Patients with high body mass index and comorbidities were excluded. Lateral cephalograms and polysomnography were collected for each patient to evaluate the correlation between craniofacial morphology and obstructive sleep apnea severity. A Spearman’s rho correlation test between cephalometric measurements and obstructive sleep apnea indexes was computed. Statistical significance was set at p < 0.05.

Results

Patients with a severe obstructive sleep apnea presented a reduction of sagittal growth of both effective mandibular length and cranio-basal length. The mandibular length was the only variable with a statistical correlation with apnea-hypopnea index. Vertical dimension showed a weak correlation with the severity of obstructive sleep apnea. No correlation with maxillary sagittal dimension was shown.

Conclusion

Obstructive sleep apnea severity may be correlated to mandibular and cranial base growth. Facial vertical dimension had no correlation with obstructive sleep apnea severity.