Background: Obstructive sleep apnea (OSA) is a prevalent yet underdiagnosed condition associated with a major healthcare burden. Current diagnostic tools, such as full-night polysomnography (PSG), pose a limited accessibility to diagnosis due to their elevated costs. Recent advances in Artificial Intelligence (AI), including Machine Learning (ML) and deep learning (DL) algorithms, offer novel potential tools for an accurate OSA screening and diagnosis. This systematic review evaluates articles employing AI-powered models for OSA screening and diagnosis in the last decade. Methods: A comprehensive electronic search was performed on PubMed/MEDLINE, Google Scholar, and SCOPUS databases. The included studies were original articles written in English, reporting the use of ML algorithms to diagnose and predict OSA in suspected patients. The last search was performed in June 2024. This systematic review is registered in PROSPERO (Registration ID: CRD42024563059). Results: Sixty-five articles, involving data from 109,046 patients, met the inclusion criteria. Due to the heterogeneity of the algorithms, outcomes were analyzed into six sections (anthropometric indexes, imaging, electrocardiographic signals, respiratory signals, and oximetry and miscellaneous signals). AI algorithms demonstrated significant improvements in OSA detection, with accuracy, sensitivity, and specificity often exceeding traditional tools. In particular, anthropometric indexes were most widely used, especially in logistic regression-powered algorithms. Conclusions: The application of AI algorithms to OSA diagnosis and screening has great potential to improve patient outcomes, increase early detection, and lessen the load on healthcare systems. However, rigorous validation and standardization efforts must be made to standardize datasets.

Objective: The aim of this study is to show our experience with the correct management of patients suffering from odontogenic sinusitis with oroantral communication and fistula. Methods: According to the inclusion criteria, 41 patients were enrolled in this retrospective study with a diagnosis of odontogenic sinusitis with oroantral communication and fistula; 1 patient with pre-implantological complication, 14 with implantological complications, and 26 with classical complications. Results: Two patients were treated with a fractioned combined approach, 13 patients were treated with an oral approach only, and 26 patients were treated with a combination. There was a complete resolution of the symptoms and closure of the fistula in all the patients enrolled. Conclusions: In our study, in all 41 patients, there was a surgical success. The best option is to use a multidisciplinary approach for patients suffering from odontogenic sinusitis.

Odontogenic sinusitis (ODS) refers to the maxillary sinus infection, which is secondary to either adjacent infectious dental pathologies or procedures. The aim of this retrospective study is to report the experiences of the department of integrated therapies in otolaryngology (Campus Bio-Medico Foundation, Rome, Italy) in classifying and treating patients that are affected by odontogenic sinusitis derived from “classic complications”. A total of 68 patients responding to the criteria and to the definition as a classical odontogenic complication were included. The surgical therapy consisted of a combined oral and nasal simultaneous approach for 28 patients (43%), a combined non-simultaneous approach for 4 patients (6%), a nasal only approach for 14 patients (21%), and an oral only approach for 20 patients (30%). All the patients presented a complete resolution of the symptoms. The choice of performing a nasal, oral, or combined approach is based on the presence of anatomical elements that facilitate sinusitis and reinfection occurrence, such as deviated nasal septum, concha bullosa, or obstructed osteo-meatal complex. The correct use of validated classification, the pre-operative CT scan, a multidisciplinary approach, and an appropriate presurgical examination are the necessary elements to obtain a good success rate.

(1) Background: Drug-Induced Sleep Endoscopy (DISE) enables the three-dimensional and dynamic visualization of the upper airway (UA) during sleep, which is useful in selecting the best treatment option for obstructive sleep apnea (OSA) patients, particularly for surgical procedures. Despite international consensus statements or position papers, a universally accepted DISE methodology and classification system remain a controversial open question. (2) Methods: A review of the English scientific literature on DISE related to endoscopic classification systems and surgical outcome predictors (3) Results: Of the 105 articles, 47 were included in the analysis based on their content’s relevance to the searched keywords. (4) Conclusions: A final report and scoring classification system is not universally accepted; the most internationally applied endoscopic classification system during DISE does not cover all patterns of events that occur simultaneously during the endoscopic examination, highlighting that several configurations of collapse and obstruction at different UA levels could be observed during DISE, which should be described in detail if DISE has to be considered in the decision-making process for the UA surgical treatment in OSA patients and if DISE has to have a role as a predictive factor for surgical outcomes analysis.

Ankyloglossia (tongue-tie) is a condition of the oral cavity in which an abnormally short lingual frenulum affects the tongue’s mobility. Literature on the correlation between ankyloglossia and obstructive sleep apnea (OSA) is scarce. The main objective of this study was to report our preliminary experience in adult OSA patients before and after ankyloglossia treatment, using drug-induced sleep endoscopy (DISE) to evaluate the upper airway modifications resulting after treatment, and to present a systematic review of the impact of ankyloglossia and its treatment on OSA adults. We found that, after frenotomy, regarding the DISE findings, and according to the VOTE classification, two of the three patients showed an improvement in tongue level, from 2A-P (complete anteroposterior collapse) to 1ap (partial anteroposterior collapse). The third patient showed no changes in his UA after frenotomy, neither worsening nor showing improvement. Thus, the results of this study suggest that frenotomy in OSA patients with ankyloglossia could reduce tongue collapse, probably by allowing the tongue to take into the physiological position in the oral cavity. These patients should undergo speech therapy and oropharyngeal exercises prior to any surgical procedure, in order to avoid glossoptosis and to improve the quality of life and sleep apnea results.

Obstructive Sleep Apnea (OSA) is characterized by repetitive collapse of the upper airway during sleep. Drug-Induced Sleep endoscopy (DISE) is used to identify the collapse site. Among the possible sites of collapse, the epiglottis occurs more frequently than previously described. In this study, we reviewed DISE findings and classified different epiglottic collapse patterns. We found 104 patients (16.4%) with epiglottis collapse (primary 12.5% and secondary 3.9%). We described the following patterns of epiglottis collapse: Anterior–Posterior (AP) collapse with rigid component “trapdoor type” (48%); AP collapse with lax component “floppy type” (13.5%); Lateral– Lateral (LL) collapse with omega shape component “book type” (14.5%); and secondary due to lateral pharyngeal wall or tongue base collapse (24%). The identification of the epiglottic collapse pattern is crucial in decision-making when attempting to ameliorate OSA. These findings in OSA phenotyping could influence the type of treatment chosen.