Background: Questionnaires have been used in the past 2 decades to predict the diagnosis of vertigo and assist clinical decision-making. A questionnaire-based machine learning model is expected to improve the efficiency of diagnosis of vestibular disorders. Objective: This study aims to develop and validate a questionnaire-based machine learning model that predicts the diagnosis of vertigo. Methods: In this multicenter prospective study, patients presenting with vertigo entered a consecutive cohort at their first visit to the ENT and vertigo clinics of 7 tertiary referral centers from August 2019 to March 2021, with a follow-up period of 2 months. All participants completed a diagnostic questionnaire after eligibility screening. Patients who received only 1 final diagnosis by their treating specialists for their primary complaint were included in model development and validation. The data of patients enrolled before February 1, 2021 were used for modeling and cross-validation, while patients enrolled afterward entered external validation. Results: A total of 1693 patients were enrolled, with a response rate of 96.2% (1693/1760). The median age was 51 (IQR 38-61) years, with 991 (58.5%) females; 1041 (61.5%) patients received the final diagnosis during the study period. Among them, 928 (54.8%) patients were included in model development and validation, and 113 (6.7%) patients who enrolled later were used as a test set for external validation. They were classified into 5 diagnostic categories. We compared 9 candidate machine learning methods, and the recalibrated model of light gradient boosting machine achieved the best performance, with an area under the curve of 0.937 (95% CI 0.917-0.962) in cross-validation and 0.954 (95% CI 0.944-0.967) in external validation. Conclusions: The questionnaire-based light gradient boosting machine was able to predict common vestibular disorders and assist decision-making in ENT and vertigo clinics. Further studies with a larger sample size and the participation of neurologists will help assess the generalization and robustness of this machine learning method.

Objective: To evaluate whether children with rapid eye movement (REM)–predominant obstructive sleep apnea (OSA) are less likely to achieve disease resolution following different management strategies compared with those with non–REM‐predominant OSA. Methods: We performed a secondary analysis of the Childhood Adenotonsillectomy Trial. Children aged 5.0–9.9 years with OSA were randomized to adenotonsillectomy (AT) or watchful waiting. REM‐predominant OSA was defined as a REM‐AHI to NREM‐AHI ratio of ≥ 2. The primary outcome was OSA resolution at 7‐month follow‐up. Results: Among 382 children (48.2% male; median age 6.75 years), 55.8% had REM‐predominant OSA. Black race and obesity were associated with a higher prevalence of this subtype. REM‐predominant OSA group exhibited increased daytime sleepiness (difference, 10%; 95% CI, 1%–17%), higher AHI (difference, 1.37; 95% CI, 0.67–2.22), and lower oxygen saturation nadirs (difference, −2.00; 95% CI, −3.00 to −2.00) compared with the non–REM‐predominant OSA group. However, PSQ‐defined symptom burden (difference, −1%; 95% CI, −9% to 7%) and OSA‐18‐defined quality‐of‐life impairment (difference, 3%; 95% CI, −6% to 12%) did not differ significantly between groups. At the 7‐month follow‐up, children in the REM‐predominant OSA group who underwent watchful waiting were significantly less likely to experience spontaneous resolution than those in the non–REM‐predominant OSA group (aOR, 0.52; 95% CI, 0.28–0.97). However, no significant difference was observed in the OSA resolution rate between the two groups who underwent AT (aOR, 0.75; 95% CI, 0.34–1.66). Conclusions: REM‐predominant OSA was associated with greater daytime sleepiness and PSG severity but was not associated with significantly greater parent‐reported symptom burden or worse disease‐specific quality of life. Children with REM‐predominant OSA were less likely to experience spontaneous resolution after watchful waiting, underscoring the prioritization of AT. Level of Evidence: 3. Trial Registration: ClinicalTrials.gov Identifier: NCT00560859

Background: To optimize the oto-endoscopic treatment of patients with adhesive otitis media (AdOM). Methods: In this observational retrospective cohort study, a total of 73 patients (81 ears) diagnosed with AdOM were included. Surgical interventions included insertion of the tympanotomy tube, tympanoplasty, or a combination of both. Follow-up evaluations were carried out at 2 weeks and at 1, 3, 6, and 12 months. Pure tone audiometry was administered between 1 and 3 months post-surgery, and imaging examinations were carried out at 6 months. Results: Tympanotomy tube insertion was performed in 11.1% (9 out of 81) of the cases, while tympanoplasty was performed in 79% (64 out of 81) of the cases, and both procedures were performed in 9.9% (8 out of 81). The rate of tympanoplasty increased with the Sade grade. Postoperatively, air conduction hearing and air-bone gap (ABG) in patients classified as Sade grades III to V showed a significant improvement. Conclusions: The individualized oto-endoscopic surgery significantly improves hearing outcomes in advanced AdOM (Sade grades III-V), as evidenced by reduced ABG. Patients with varying degrees of AdOM require customized treatment approaches. Level of Evidence: 4.

Achieving adequate coupling between the internal and external components of a cochlear implant is essential for optimal device performance and depends in part on scalp thickness. Suboptimal cochlear implant coupling may occur in patients with increased scalp thickness, leading to impaired magnetic retention and signal transmission. This study describes a modified hook-assisted transmuscular technique designed to address this issue while preserving soft tissue integrity. This retrospective single-centre case series included adult patients undergoing cochlear implantation with scalp thickness >7 mm. The technique involves two parallel muscle incisions and the use of a custom-designed hook to elevate the temporalis muscle under direct visualisation, allowing controlled implant placement without the need for skin flap thinning. The method was applied in 15 adult patients with a follow-up period of 1 to 6 months. Mean scalp thickness was reduced from 10.7 mm to 4.3 mm. No cases of flap necrosis or infection were observed. Operative time was comparable to conventional procedures, and no patients required revision surgery or high-strength magnets during follow-up. This technique appears to be a feasible and practical option for improving cochlear implant coupling in patients with thick scalp flaps. Further studies are required to assess long-term outcomes.