Objective: To prospectively assess the rate and timing of recovery of olfactory (OD) and gustatory (GD) dysfunction in patients affected by COVID‐19.Study Design: Cohort study.Setting: Population‐based evaluation in a COVID‐19 high‐prevalence region.Subjects and Methods: We analyzed the clinical course of OD and GD in a cohort of home‐quarantined SARS‐CoV‐2–positive patients from Northern Italy. Physicians administered a survey‐based questionnaire at recruitment (T0). During follow‐up, patients responded to online dedicated surveys modulated according to symptoms at T0.Results: A total of 151 patients completed the follow‐up survey. OD and/or GD were observed in 83% and 89% of subjects, respectively. Resolution rates of OD and GD at 30 days from onset were 87% and 82%, respectively. Risk factors for late resolution were grade of dysfunction at onset (total vs partial), gender, and presence of nasal congestion. Three (2%) patients previously reporting complete resolution of symptoms complained of subsequent recurrence of OD and/or GD after a mean of 19 days from resolution of the previous episode.Conclusion: COVID‐19–related OD and GD had high rate of resolution in the first month from onset of symptoms. However, in 10% to 15% of patients, these symptoms showed only partial improvement after this period.

Introduction: Fully convoluted neural networks (FCNN) applied to video-analysis are of particular interest in the field of head and neck oncology, given that endoscopic examination is a crucial step in diagnosis, staging, and follow-up of patients affected by upper aero-digestive tract cancers. The aim of this study was to test FCNN-based methods for semantic segmentation of squamous cell carcinoma (SCC) of the oral cavity (OC) and oropharynx (OP). Materials and Methods: Two datasets were retrieved from the institutional registry of a tertiary academic hospital analyzing 34 and 45 NBI endoscopic videos of OC and OP lesions, respectively. The dataset referring to the OC was composed of 110 frames, while 116 frames composed the OP dataset. Three FCNNs (U-Net, U-Net 3, and ResNet) were investigated to segment the neoplastic images. FCNNs performance was evaluated for each tested network and compared to the gold standard, represented by the manual annotation performed by expert clinicians. Results: For FCNN-based segmentation of the OC dataset, the best results in terms of Dice Similarity Coefficient (Dsc) were achieved by ResNet with 5(×2) blocks and 16 filters, with a median value of 0.6559. In FCNN-based segmentation for the OP dataset, the best results in terms of Dsc were achieved by ResNet with 4(×2) blocks and 16 filters, with a median value of 0.7603. All tested FCNNs presented very high values of variance, leading to very low values of minima for all metrics evaluated. Conclusions: FCNNs have promising potential in the analysis and segmentation of OC and OP video-endoscopic images. All tested FCNN architectures demonstrated satisfying outcomes in terms of diagnostic accuracy. The inference time of the processing networks were particularly short, ranging between 14 and 115 ms, thus showing the possibility for real-time application.

Open partial horizontal laryngectomies (OPHLs) are well-established and oncologically safe procedures for intermediate–advanced laryngeal cancers (LC). T–N categories are well-known prognosticators: herein we tested if “anterior” vs. “posterior” tumor location (as defined in respect to the paraglottic space divided according to a plane passing through the arytenoid vocal process, perpendicular to the ipsilateral thyroid lamina) may represent an additional prognostic factor. We analyzed a retrospective cohort of 85 T3–4a glottic LCs, treated by Type II or III OPHL (according to the European Laryngological Society classification) from 2005 to 2017 at two academic institutions. Five-year overall survival (OS), disease-specific survivals (DSS), and recurrence-free survivals (RFS) were compared according to tumor location and pT category. Anterior and posterior tumors were 43.5% and 56.5%, respectively, 78.8% of lesions were T3 and 21.2% were T4a. Five-year OS, DSS, and RFS for T3 were 74.1%, 80.5%, and 63.4%, respectively, and for T4a 71.8%, 71.8%, and 43%, respectively (p not significant). In relation to tumor location, the survival outcomes were 91%, 94.1%, and 72.6%, respectively, for anterior tumors, and 60.3%, 66.3%, and 49.1%, respectively, for posterior lesions (statistically significant differences). These data provide evidence that laryngeal compartmentalization is a valid prognosticator, even more powerful than the pT category.

The long-term problems of head and neck cancer survivors (HNCS) are not well known. In a cross-sectional international study aimed at exploring the long-term quality of life in this population, 1114 HNCS were asked to state their two most serious long-term effects. A clinician recorded the responses during face-to-face appointments. A list of 15 example problems was provided, but a free text field was also available. A total of 1033 survivors responded to the question. The most frequent problems were ‘dry mouth’ (DM) (n = 476; 46%), ‘difficulty swallowing/eating’ (DSE) (n = 408; 40%), ‘hoarseness/difficulty speaking’ (HDS) (n = 169; 16%), and ‘pain in the head and neck’ (PHN) (n = 142; 14%). A total of 5% reported no problems. Logistic regression adjusted for age, gender, treatment, and tumor stage and site showed increased odds of reporting DM and DSE for chemo-radiotherapy (CRT) alone compared to surgery alone (odds ratio (OR): 4.7, 95% confidence interval (CI): 2.5–9.0; OR: 2.1, CI: 1.1–3.9), but decreased odds for HDS and PHN (OR: 0.3, CI: 0.1–0.6; OR: 0.2, CI: 0.1–0.5). Survivors with UICC stage IV at diagnosis compared to stage I had increased odds of reporting HDS (OR: 1.9, CI: 1.2–3.0). Laryngeal cancer survivors had reduced odds compared to oropharynx cancer survivors of reporting DM (OR: 0.4, CI: 0.3–0.6) but increased odds of HDS (OR: 7.2, CI: 4.3–12.3). This study provides evidence of the serious long-term problems among HNCS.

Purpose: This study aimed to evaluate the utility of large language model (LLM) artificial intelligence tools, Chat Generative Pre-Trained Transformer (ChatGPT) versions 3.5 and 4, in managing complex otolaryngological clinical scenarios, specifically for the multidisciplinary management of odontogenic sinusitis (ODS). Methods: A prospective, structured multidisciplinary specialist evaluation was conducted using five ad hoc designed ODS-related clinical scenarios. LLM responses to these scenarios were critically reviewed by a multidisciplinary panel of eight specialist evaluators (2 ODS experts, 2 rhinologists, 2 general otolaryngologists, and 2 maxillofacial surgeons). Based on the level of disagreement from panel members, a Total Disagreement Score (TDS) was calculated for each LLM response, and TDS comparisons were made between ChatGPT3.5 and ChatGPT4, as well as between different evaluators. Results: While disagreement to some degree was demonstrated in 73/80 evaluator reviews of LLMs’ responses, TDSs were significantly lower for ChatGPT4 compared to ChatGPT3.5. Highest TDSs were found in the case of complicated ODS with orbital abscess, presumably due to increased case complexity with dental, rhinologic, and orbital factors affecting diagnostic and therapeutic options. There were no statistically significant differences in TDSs between evaluators’ specialties, though ODS experts and maxillofacial surgeons tended to assign higher TDSs. Conclusions: LLMs like ChatGPT, especially newer versions, showed potential for complimenting evidence-based clinical decision-making, but substantial disagreement was still demonstrated between LLMs and clinical specialists across most case examples, suggesting they are not yet optimal in aiding clinical management decisions. Future studies will be important to analyze LLMs’ performance as they evolve over time.