We hypothesize that the control of tongue position using a newly developed tongue position retainer, where the tongue is held in a protruded position (i.e., intervention A) or in its resting position (i.e., intervention B), is effective for maintaining upper airway patency in obstructive sleep apnea (OSA) compared with no control of tongue position. This is a randomized, controlled, non-blinded, crossover, and two-armed trial (i.e., sequence AB/BA) in 26 male participants (i.e., sample size) who are scheduled to undergo a dental operation under intravenous sedation with OSA (10 ≤ respiratory event index < 30/h). Participants will be randomly allocated into either sequence by a permuted block method, stratified by body mass index. Under intravenous sedation, participants will undergo two interventions, separated by a washout period after receiving intervention A or intervention B using a tongue position retainer after baseline evaluation, before each intervention is provided. The primary outcome is the abnormal breathing index of apnea as determined by the frequency of apnea per hour. We expect that, compared with no control of tongue position, both intervention A and intervention B will improve the abnormal breathing events with superior effects achieved by the former, offering a therapeutic option for OSA.

Obstructive sleep apnea (OSA) is a chronic disorder associated with serious health consequences, yet many cases remain undiagnosed due to limited access to standard diagnostic tools such as polysomnography. Recent advances in artificial intelligence (AI) have enabled the development of deep convolutional neural networks that analyze craniofacial radiographs, particularly lateral cephalograms, to detect anatomical risk factors for OSA. The goal of this approach is not to replace polysomnography but to identify individuals with a high suspicion of OSA at the primary care or dental level and to guide them toward timely and appropriate diagnostic evaluation. Current studies have demonstrated that AI can recognize patterns of oropharyngeal crowding and anatomical imbalance of the upper airway with high accuracy, often exceeding manual assessment. Furthermore, interpretability analyses suggest that AI focuses on clinically meaningful regions, including the tongue, mandible, and upper airway. Unexpected findings such as predictive signals from outside the airway also suggest AI may detect subtle features associated with age or obesity. Ultimately, integrating AI with cephalometric imaging may support early screening and referral for polysomnography, improving care pathways and reducing delays in OSA treatment.