Characteristics and Frequency of Children With Severe Obstructive Sleep Apnea Undergoing Elective Polysomnography

Evaluating deep learning techniques for identifying tongue features in subthreshold depression: a prospective observational study

Objective

This study aims to evaluate the potential of using tongue image features as non-invasive biomarkers for diagnosing subthreshold depression and to assess the correlation between these features and acupuncture treatment outcomes using advanced deep learning models.

Methods

We employed five advanced deep learning models-DenseNet169, MobileNetV3Small, SEResNet101, SqueezeNet, and VGG19_bn-to analyze tongue image features in individuals with subthreshold depression. These models were assessed based on accuracy, precision, recall, and F1 score. Additionally, we investigated the relationship between the best-performing model's predictions and the success of acupuncture treatment using Pearson's correlation coefficient.

Results

Among the models, SEResNet101 emerged as the most effective, achieving an impressive 98.5% accuracy and an F1 score of 0.97. A significant positive correlation was found between its predictions and the alleviation of depressive symptoms following acupuncture (Pearson's correlation coefficient = 0.72, p<0.001).

Conclusion

The findings suggest that the SEResNet101 model is highly accurate and reliable for identifying tongue image features in subthreshold depression. It also appears promising for assessing the impact of acupuncture treatment. This study contributes novel insights and approaches to the auxiliary diagnosis and treatment evaluation of subthreshold depression.

Analysis of the Clinical Course of Children With Initial Negative Polysomnography

OBJECTIVES

To determine the clinical course of children with initial negative polysomnography (PSG) tests.

METHODS

A retrospective chart review was performed on pediatric patients seen by an otolaryngologist who underwent a PSG between October 2012 and March 2019 for obstructive sleep apnea at a single, academic, tertiary-care center. Data including demographics, follow-up PSG tests, and surgeries were collected.

RESULTS

A total of 2018 pediatric patients underwent PSG during the timeframe. About 535/2018 (26.5%) patients were negative for obstructive sleep apnea by PSG and had no prior adenotonsillectomy. About 408/535 (76.3%) did not obtain follow-up testing or surgeries; 69/535 (12.9%) underwent subsequent adenotonsillectomy for worsening symptoms without repeat PSG; and 58/535 (10.8%) obtained 1 or multiple follow-up PSG tests. Of the 58 who obtained repeat PSG, 25 (43.1%) were subsequently positive, with 17 of those 25 (29.3% of 58) undergoing adenotonsillectomy. Taken together, 94/535 (17.6%) of patients with initial negative PSG had worsening sleep disordered breathing.

CONCLUSION

A significant minority of children who initially tested negative for pediatric obstructive sleep apnea met criteria for diagnosis on follow up PSG. Additionally, other children with initial negative PSG underwent adenotonsillectomy for worsening symptoms in lieu of repeat testing. Patients should be educated that snoring in children could persist or worsen over time, even in the setting of a initial negative PSG.

A commentary on broader use of preoperative polysomnography in pediatric patients with obstructive sleep apnea

Obstructive sleep apnea (OSA), characterized by repeated episodes of prolonged airway obstruction during sleep, is a common condition in pediatric patients ages 2 to 6. Polysomnography (PSG) testing can be used to assess the severity of OSA or obstructive sleep-disordered breathing prior to adenotonsillectomy. The article "Characteristics and Frequency of Children With Severe Obstructive Sleep Apnea Undergoing Elective Polysomnography" by Bains et al. notes the variability in guidelines regarding indication for PSG amongst professional societies, making it difficult for physicians to determine which patients require PSG. The purpose of this commentary is to emphasize and elaborate on the potential benefit for preoperative PSG in all patients considering adenotonsillectomy as presented by the aforementioned article. With broader use of preoperative PSG, providers would have a more accurate assessment of OSA severity and to aid in surgical decision-making and postoperative planning.

Worldwide prevalence and associated risk factors of obstructive sleep apnea: a meta-analysis and meta-regression

PURPOSE

This study aimed to identify the prevalence of obstructive sleep apnea (OSA) and associated risk factors globally.

METHODS

Six databases and registrations and three grey databases were explored for observational field research. Independently and impartially paired reviewers selected research, gathered data, and evaluated the methodological quality. Heterogeneity was investigated using subgroup analysis and meta-regression following the moderating variable in a meta-analysis of proportions with a random-effects model. The critical appraisal instrument developed by the Joanna Briggs Institute was used to evaluate the listed studies' methodology. The certainty of the evidence was evaluated using the GRADE tool.

RESULTS

A total of 8236 articles were collected during the database search, resulting in 99 articles included for qualitative synthesis, and 98 articles were included for the meta-analysis. The estimated combined prevalence of OSA was 54% [CI 95% = 46-62%; I2 = 100%]. Mean age, percentage of moderate-severe cases, and the sample's body mass index (BMI) did not affect the heterogeneity that was already present when meta-regressed (p > 0.05). Ninety-one studies were deemed to have a low risk of bias, while eight were deemed to have a moderate risk. For OSA prevalence outcomes, the GRADE criteria were considered very low.

CONCLUSION

Approximately half of the people worldwide have OSA. High BMI, increasing age, and male gender are described as risk factors in the literature, but these covariates do not affect pre-existing heterogeneity.

Effects of acupuncture on obstructive sleep apnea-hypopnea syndrome: A meta-analysis

Our study aimed to systematically evaluate the effect of acupuncture in patients with obstructive sleep apnea-hypopnea syndrome (OSAHS). Literature search of four Chinese databases and six English databases for studies published from the inception of each database to March 1, 2022 and identify relevant studies published in Chinese or English. Related randomized controlled trials of acupuncture for the treatment of OSAHS were included to analyze the efficacy of acupuncture. Two researchers independently reviewed all of the retrieved studies to screen for eligible studies and extract the required relevant data. Included studies were subjected to a methodological quality assessment using the Cochrane Manual 5.1.0, and to a meta-analysis using Cochrane Review Manager version 5.4. A total of 19 studies with 1365 participants were examined. Compared with the control group, the apnea-hypopnea index, lowest oxygen saturation, Epworth Sleepiness Scale, interleukin-6, tumor necrosis factor α, and nuclear factor κ-B indicators all exhibited statistically significant changes. Thus, acupuncture was effective in alleviating the state of hypoxia and sleepiness and reduced the inflammatory response and disease severity among reported patients with OSAHS. Therefore, acupuncture could be widely used in the clinical treatment of OSAHS patients as a complementary strategy and warrants further study.

Obstructive Sleep Apnea in Underweight Children

OBJECTIVES

To determine predictors of obstructive sleep apnea (OSA) in underweight children and to describe the demographic, clinical, and polysomnographic characteristics of an ethnically diverse population of underweight children with OSA.

STUDY DESIGN

Case-control study.

SETTING

University of Texas Southwestern Medical Center and Children's Medical Center of Dallas.

METHODS

Underweight children aged 2 to 18 years who underwent a polysomnogram for suspected OSA between January 2014 and December 2020 were included. Underweight was defined as body mass index <5th percentile per Centers for Disease Control and Prevention guidelines. Children with apnea-hypopnea index <1.0 served as a control group. Univariate and multiple logistic regression analysis was used to determine the predictors of OSA. Significance was set at P < .05.

RESULTS

An overall 124 children met inclusion criteria: mean age, 6.4 years; 50% female; 44% Hispanic, 31% African American, and 18% Caucasian. A total of 83 children had OSA (apnea-hypopnea index ≥1.0). Height was negatively correlated with OSA (odds ratio, 0.94; 95% CI, 0.88-0.99; P = .02) while allergic rhinitis (odds ratio, 2.97; 95% CI, 1.24-7.08; P = .01) and tonsillar hypertrophy (odds ratio, 3.38; 95% CI, 1.42-8.02; P = .01) were predictors for the presence of OSA. No demographic or clinical characteristics were predictors for severe OSA.

CONCLUSION

Underweight children with OSA, as compared with those without OSA, are more likely to have decreased height, tonsillar hypertrophy, and allergic rhinitis. There are no predictors of severe OSA in underweight children. We recommend polysomnography for the diagnosis of OSA in symptomatic underweight children with large tonsils, especially when they have a history of allergies.