Paediatric sleep apnea event prediction using nasal air pressure and machine learning.

Sleep-disordered breathing is an important health issue for children. The objective of this study was to develop a machine learning classifier model for the identification of sleep apnea events taken exclusively from nasal air pressure measurements acquired during overnight polysomnography for paediatric patients. A secondary objective of this study was to differentiate site of obstruction exclusively from hypopnea event data using the model. Computer vision classifiers were developed via transfer learning to either normal breathing while asleep, obstructive hypopnea, obstructive apnea or central apnea. A separate model was trained to identify site of obstruction as either adeno-tonsillar or tongue base. In addition, a survey of board-certified and board-eligible sleep physicians was completed to compare clinician versus model classification performance of sleep events, and indicated very good performance of our model relative to human raters. The nasal air pressure sample database available for modelling comprised 417 normal, 266 obstructive hypopnea, 122 obstructive apnea and 131 central apnea events derived from 28 paediatric patients. The four-way classifier achieved a mean prediction accuracy of 70.0% (95% confidence interval [67.1-72.9]). Clinician raters correctly identified sleep events from nasal air pressure tracings 53.8% of the time, whereas the local model was 77.5% accurate. The site of obstruction classifier achieved a mean prediction accuracy of 75.0% (95% confidence interval [68.7-81.3]). Machine learning applied to nasal air pressure tracings is feasible and may exceed the diagnostic performance of expert clinicians. Nasal air pressure tracings of obstructive hypopneas may "encode" information regarding the site of obstruction, which may only be discernable by machine learning.

Evaluation of Upper Airway Stimulation for Adolescents With Down Syndrome and Obstructive Sleep Apnea.

Importance: Patients with Down syndrome have a high incidence of persistent obstructive sleep apnea (OSA) and limited treatment options. Upper airway hypoglossal stimulation has been shown to be effective for adults with OSA but has not yet been evaluated for pediatric populations. Objective: To evaluate the safety and effectiveness of upper airway stimulation for adolescent patients with Down syndrome and severe OSA. Design, Setting, and Participants: This prospective single-group multicenter cohort study with 1-year follow-up was conducted between April 1, 2015, and July 31, 2021, among a referred sample of 42 consecutive adolescent patients with Down syndrome and persistent severe OSA after adenotonsillectomy. Intervention: Upper airway stimulation. Main Outcomes and Measures: The prespecified primary outcomes were safety and the change in apnea-hypopnea index (AHI) from baseline to 12 months postoperatively. Polysomnographic and quality of life outcomes were assessed at 1, 2, 6, and 12 months postoperatively. Results: Among the 42 patients (28 male patients [66.7%]; mean [SD] age, 15.1 [3.0] years), there was a mean (SD) decrease in AHI of 12.9 (13.2) events/h (95% CI, -17.0 to -8.7 events/h). With the use of a therapy response definition of a 50% decrease in AHI, the 12-month response rate was 65.9% (27 of 41), and 73.2% of patients (30 of 41) had a 12-month AHI of less than 10 events/h. The most common complication was temporary tongue or oral discomfort, which occurred in 5 patients (11.9%). The reoperation rate was 4.8% (n = 2). The mean (SD) improvement in the OSA-18 total score was 34.8 (20.3) (95% CI, -42.1 to -27.5), and the mean (SD) improvement in the Epworth Sleepiness Scale score was 5.1 (6.9) (95% CI, -7.4 to -2.8). The mean (SD) duration of nightly therapy was 9.0 (1.8) hours, with 40 patients (95.2%) using the device at least 4 hours a night. Conclusions and Relevance: Upper airway stimulation was able to be safely performed for 42 adolescents who had Down syndrome and persistent severe OSA after adenotonsillectomy with positive airway pressure intolerance. There was an acceptable adverse event profile with high rates of therapy response and quality of life improvement. Trial Registration: ClinicalTrials.gov Identifier: NCT02344108.

Otoendoscopes to Enhance Telemedicine During the COVID-19 Pandemic.

OBJECTIVES: As telemedicine has become increasingly utilized during the COVID-19 pandemic, portable otoendoscopy offers a method to perform an ear examination at home. The objective of this pilot study was to assess the quality of otoendoscopic images obtained by non-medical individuals and to determine the effect of a simple training protocol on image quality. METHODS: Non-medical participants were recruited and asked to capture images of the tympanic membrane before and after completion of a training module, as well as complete a survey about their experience using the otoendoscope. Images were de-identified, randomized, and evaluated by 6 otolaryngologists who were blinded as to whether training had been performed prior to the image capture. Images were rated using a 5-point Likert scale. RESULTS: Completion of a training module resulted in a significantly higher percentage of tympanic membrane visible on otoendoscopic images, as well as increased physician confidence in identifying middle ear effusion/infection, cholesteatoma, and deferring an in-person otoscopy (P < .0001). However, even with improved image quality, in most cases, physicians reported that they would not feel comfortable using the images to for diagnosis or to defer an in-person examination. Most participants reported that the otoendoscope was simple to use and that they would feel comfortable paying for the device. CONCLUSIONS: At-home otoendoscopes can offer a sufficient view of the tympanic membrane in select cases. The use of a simple training tool can significantly improve image quality, though often not enough to replace an in-person otoscopic exam.

Redefining Success by Focusing on Failures After Pediatric Hypoglossal Stimulation in Down Syndrome.

OBJECTIVES/HYPOTHESIS: Patients with Down syndrome have a high incidence of obstructive sleep apnea (OSA) and limited treatment options. Hypoglossal stimulation has shown efficacy but has not yet been approved for pediatric populations. Our objective is to characterize the therapy response of adolescent patients with down syndrome and severe OSA who underwent hypoglossal stimulation. STUDY DESIGN: Prospective longitudinal trial. METHODS: We are conducting a multicenter single-arm trial of hypoglossal stimulation for adolescent patients with Down syndrome and severe OSA. Interim analysis was performed to compare objective sleep and quality of life outcomes at 12 months postoperatively for the first 20 patients. RESULTS: The mean age was 15.5 and baseline AHI 24.2. Of the 20 patients, two patients (10.0%) had an AHI under 1.5 at 12 months; nine patients of 20 (45.0%) under five; and 15 patients of 20 (75.0%) under 10. The mean decrease in AHI was 15.1 (P < .001). Patients with postoperative AHI over five had an average baseline OSA-18 survey score of 3.5 with an average improvement of 1.7 (P = .002); in addition, six of these patients had a relative decrease of apneas compared to hypopneas and seven had an improvement in percentage of time with oxygen saturation below 90%. CONCLUSIONS: Patients with persistently elevated AHI 12 months after hypoglossal implantation experienced improvement in polysomnographic and quality of life outcomes. These results suggest the need for a closer look at physiologic markers for success beyond reporting AHI as the gold standard. LEVEL OF EVIDENCE: 4 Laryngoscope, 131:1663-1669, 2021.

Pediatric, Family-Centered, "At-Home" Otologic Physical Examination in the COVID-19 Era.

SARS-CoV-2, the novel coronavirus resulting in the present COVID-19 pandemic, has increased the otolaryngologist's reliance on telemedicine to manage outpatient pathology. The nature of telemedicine, however, limits a provider's ability to obtain a comprehensive physical examination, specifically of the tympanic membrane. Various smartphone-based otoscopic attachments are now available that facilitate patient-obtained otoscopic image capture of the tympanic membrane. Here, we present 3 cases in which a patient-purchased, over-the-counter otoscope was utilized to alter otologic management during the time of social distancing. Further research is necessary to improve our understanding the safety and efficacy of patient-based "at-home" otoscopic examination and to optimize the use of these devices.

Predictors of complications following adenotonsillectomy in children with severe obstructive sleep apnea.

OBJECTIVE: To identify pre-operative risk factors predicting complications following adenotonsillectomy in children with severe OSA. METHODS: Retrospective chart review in an academic tertiary care center. Children with symptoms of OSA with overnight polysomnography (PSG) revealing apnea-hypopnea index (AHI) >10, who underwent adenotonsillectomy with overnight postoperative observation between 2008 and 2012. Univariate logistic regression was used to assess odds ratio (OR) of individual risk factors versus postoperative complications such as overnight desaturations <90%, length of stay (LOS)>24 h, supplemental oxygen requirement, and transfer to a higher level of care. RESULTS: All patients (n=157) with severe OSA were observed overnight. Mean age was 5.3±3.7 years. Twenty-five (15.9%) patients had LOS>24 h. Forty-two (26.8%) had overnight desaturations <90%. AHI ≥15 and O2 saturation nadir <80% on preop polysomnography (PSG) were independent predictors of post-op O2 saturation <90% and LOS>24 h. (p<0.05). PSG minimum saturation <80% was the strongest predictor of all variables examined with an OR of 6.98 (3.15-15.48, 95% CI) for desaturation <90% and 5.19 (2.11-12.75, 95% CI) for LOS>24 h. Preop PSG O2 saturation<90% predicted overnight post op oxygen requirement with an OR of 3.38 (1.39-8.25, 95%CI). CONCLUSIONS: Preoperative polysomnography yields significant independent predictors of post-op complications in children with OSA. While AHI is a significant independent predictor, minimum O2 saturation on preop PSG appeared the strongest predictor when <80%. Patients with these risk factors, especially low O2 on PSG, warrant overnight observation with continuous pulse oximetry.

Perioperative dexamethasone administration and risk of bleeding following tonsillectomy in children: a randomized controlled trial.

CONTEXT: Corticosteroids are commonly given to children undergoing tonsillectomy to reduce postoperative nausea and vomiting; however, they might increase the risk of perioperative and postoperative hemorrhage. OBJECTIVE: To determine the effect of dexamethasone on bleeding following tonsillectomy in children. DESIGN, SETTING, AND PATIENTS: A multicenter, prospective, randomized, double-blind, placebo-controlled study at 2 tertiary medical centers of 314 children aged 3 to 18 years undergoing tonsillectomy without a history of bleeding disorder or recent corticosteroid medication use and conducted between July 15, 2010, and December 20, 2011, with 14-day follow-up. We tested the hypothesis that dexamethasone would not result in 5% more bleeding events than placebo using a noninferiority statistical design. INTERVENTION: A single perioperative dose of dexamethasone (0.5 mg/kg; maximum dose, 20 mg), with an equivalent volume of 0.9% saline administered to the placebo group. MAIN OUTCOME MEASURES: Rate and severity of posttonsillectomy hemorrhage in the 14-day postoperative period using a bleeding severity scale (level I, self-reported or parent-reported postoperative bleeding; level II, required inpatient admission for postoperative bleeding; or level III, required reoperation to control postoperative bleeding). RESULTS: One hundred fifty-seven children (median [interquartile range] age, 6 [4-8] years) were randomized into each study group, with 17 patients (10.8%) in the dexamethasone group and 13 patients (8.2%) in the placebo group reporting bleeding events. In an intention-to-treat analysis, the rates of level I bleeding were 7.0% (n = 11) in the dexamethasone group and 4.5% (n = 7) in the placebo group (difference, 2.6%; upper limit 97.5% CI, 7.7%; P for noninferiority = .17); rates of level II bleeding were 1.9% (n = 3) and 3.2% (n = 5), respectively (difference, -1.3%; upper limit 97.5% CI, 2.2%; P for noninferiority < .001); and rates of level III bleeding were 1.9% (n = 3) and 0.6% (n = 1), respectively (difference, 1.3%; upper limit 97.5% CI, 3.8%; P for noninferiority = .002). CONCLUSIONS: Perioperative dexamethasone administered during pediatric tonsillectomy was not associated with excessive, clinically significant level II or III bleeding events based on not having crossed the noninferior threshold of 5%. Increased subjective (level I) bleeding events caused by dexamethasone could not be excluded because the noninferiority threshold was crossed. TRIAL REGISTRATION: clinicaltrials.gov Identifier: NCT01415583.

A pilot study to identify pre- and peri-operative risk factors for airway complications following adenotonsillectomy for treatment of severe pediatric OSA.

OBJECTIVE: A pilot study to identify risk factors predicting post-operative complications in children with severe OSA undergoing adenotonsillectomy. METHODS: Retrospective review in a tertiary care academic institution. Two-stage least squares regression analysis and instrumental variable analysis to allow for modeling of pre- and peri-operative risk factors as having significance in predicting post-operative morbidity. RESULTS: Eighty-three children (mean age 4.88 ± 3.09 years) with apnea-hypopnea index (AHI) ≥ 10 who were observed overnight following adenotonsillectomy were evaluated for rates of major (increased level of care, CPAP/BiPAP use, pulmonary edema and reintubation) and minor (oxygen saturation <90%) airway complications as well as total observation costs. Major and minor complications occurred in 4.8% and 19.3% of children, respectively. Age <2 years (p<0.01), AHI >24 (p<0.05), intra-operative laryngospasm requiring treatment (p<0.05), oxygen saturations <90% on room air in PACU (p<0.05) and PACU stay >100 min (p<0.01) independently predicted post-operative complications. Children with any one of these factors experienced a 38% complication rate versus 4% in all others. CONCLUSIONS: This pilot study identified pre- and peri-operative risk factors that collectively can be investigated as predictors of post-operative airway complications in a prospective study. By identifying preliminary results comparing the complication rates between those children with and without these risk factors, we will be able to calculate the sample size for a future prospective validation study. Such a study is necessary to understand the safety and potential significant cost savings of observing children without risk factors on the pediatric floor and not in an ICU setting. A best practice algorithm can be created for children with severe OSA only after completing this prospective study.

Medical and surgical interventions for hearing loss associated with congenital cytomegalovirus: a systematic review.

BACKGROUND: Hearing loss associated with congenital cytomegalovirus (CMV) infection occurs in 0.2 to 0.6 per 1000 neonates. OBJECTIVE: The primary goal of this systemic review was to test the following null hypotheses: (1) antiviral therapy has no impact on congenital CMV-related sensorineural hearing loss and (2) surgical therapy has no impact on congenital CMV-related sensorineural hearing loss. DATA SOURCES: Computerized searches of MEDLINE and EMBASE databases through September 2010 were performed, supplemented with manual searches and inquiries to topic experts. REVIEW METHODS: Studies were included based on review of 387 studies according to criteria developed a priori. Data extraction was performed by independent reviewers and focused on relevant audiologic measurements, study designs, and potential confounders. RESULTS: Criterion-meeting studies (n = 19) included a total of 446 participants. The largest randomized controlled trial (RCT) suggested a significant protective effect of intravenous ganciclovir against deterioration of hearing in neonates with central nervous system manifestations of CMV infection. It also, however, suggested a 3-fold increase in neutropenia. The second RCT suggested that there may be no significant benefit of intravenous ganciclovir for normal-hearing infants with asymptomatic congenital CMV. Additional prospective and retrospective data evaluated the impact of oral therapy and cochlear implantation in affected patients. CONCLUSION: Although results are mixed, the highest level of evidence suggests that antiviral therapy confers a protective benefit on neonates with hearing loss and symptomatic CMV. Cochlear implantation can result in advancement of speech and language skills, but there are mixed results compared with non­CMV-infected patients.

The epidemiology of hearing impairment in the United States: newborns, children, and adolescents.

OBJECTIVE: Hearing loss ranks high among disabilities in the United States. The epidemiologic parameters of hearing impairment in the United States have not been systematically studied and important historic data have not diffused to relevant stakeholders; even otolaryngologists are unfamiliar with epidemiologic data. We wished to compile known studies to establish an epidemiologic baseline beginning with pediatric data. DATA SOURCES: Relevant literature was retrieved from medical databases and Centers for Disease Control and Prevention reports. METHODS: Candidate articles and national data sets encompassing pediatric hearing loss were analyzed and compared. Whenever possible, group analyses were performed. RESULTS: The average incidence of neonatal hearing loss in the United States is 1.1 per 1000 infants, with variation among states (0.22 to 3.61 per 1000). Childhood and adolescent prevalence rates demonstrate variability. The prevalence of mild hearing impairment or worse (>20 dB) is 3.1 percent based on the average of comparable audiometric screening studies; self-reporting prevalence is 1.9 percent. Hispanic Americans demonstrate a higher prevalence of hearing impairment than other children. Low-income households demonstrate a higher prevalence of hearing loss compared to households with higher income levels. Genetic causes were attributed to 23 percent across studies. CONCLUSIONS: Analysis of the data reveals gaps in our knowledge of the epidemiology of hearing loss and stresses the importance of consistent definitions of hearing impairment for systematic assessment of changes over time. Hearing loss in childhood deserves further epidemiologic investigation and elevated awareness among health care professionals and the public. Genetic etiologies are likely underestimated in this review.

Podcasting: contemporary patient education.

Portable video technology is a widely available new tool with potential to be used by pediatric otolaryngology practices for patient and family education. Podcasts are media broadcasts that employ this new technology. They can be accessed via the Internet and viewed either on a personal computer or on a handheld device, such as an iPod or an MP3 player. We wished to examine the feasibility of establishing a podcast-hosting Web site. We digitally recorded pediatric otologic procedures in the operating room and saved the digital files to DVDs. We then edited the DVDs at home with video-editing software on a personal computer. Next, spoken narrative was recorded with audio-recording software and combined with the edited video clips. The final products were converted into the M4V file format, and the final versions were uploaded onto our hospital's Web site. We then downloaded the podcasts onto a high-quality portable media player so that we could evaluate their quality. All of the podcasts are now on the hospital Web site, where they can be downloaded by patients and families at no cost. The site includes instructions on how to download the appropriate free software for viewing the podcasts on a portable media player or on a computer. Using this technology for patient education expands the audience and permits portability of information. We conclude that a home computer can be used to inexpensively create informative surgery demonstrations that can be accessed via a Web site and transferred to portable viewing devices with excellent quality.