Lauran K. Evans

Objective: To evaluate the accuracy, completeness, clarity, source transparency, and readability of leading AI chatbot responses to patient questions about tracheostomy and to determine whether AI tools can reliably support patient education where high‐quality guidance is critical for safety. Study Design: Cross‐sectional content analysis. Setting: Virtual study environment using publicly accessible AI platforms, with expert evaluation conducted via Qualtrics‐based distribution. Methods: Twelve frequently asked questions about tracheostomy care were identified using search‐listening tools and clinician input, then submitted to 5 AI chatbots — ChatGPT4, Google Gemini 2.0, Microsoft Copilot, DeepSeek V3, and Grok 3 — and to a senior laryngologist. Three blinded laryngologists independently evaluated each response using the Quality Analysis of Medical Artificial Intelligence instrument. Readability was assessed using nine metrics. Results: Gemini 2.0 achieved significantly higher completeness scores than physician responses ( P < .001), with DeepSeek and Grok 3 ( P < .05) also outperforming ( P < .05). Accuracy did not differ significantly between AI‐ and expert‐generated responses. On average, the AI models outperformed physician in clarity, completeness, and usefulness based on QAMAI scoring ( P < .05). All AI and expert responses exceeded the NIH‐recommended 6th‐grade reading level, ranging from 10th−13th grade ( P < .001). Inter‐rater reliability was 78%. Conclusion: AI chatbots can generate accurate and comprehensive responses to common tracheostomy care questions, demonstrating potential to support patient education. However, they continue to lack guaranteed, verifiable sourcing, and this study did not assess actual patient comprehension of the AI‐generated responses. Future efforts should focus on adapting AI‐generated education materials to meet health literacy standards and evaluating their direct impact on patient understanding and outcomes.

SignificanceThyroid cancer is the most common endocrine malignancy, and diagnosis is often challenging due to overlapping features between benign and malignant nodules. Fine-needle aspiration, the clinical gold standard, frequently yields indeterminate results and lacks spatial context, leading to unnecessary surgeries. Real-time margin assessment also remains limited. There is a need for accurate, label-free, spatially resolved imaging. Dynamic optical contrast imaging (DOCI), which measures autofluorescence lifetimes of endogenous fluorophores, offers a promising platform for intraoperative cancer detection.AimWe develop and evaluate a machine learning integrated DOCI framework to classify thyroid tissue subtypes and segment cancerous regions from ex vivo hyperspectral sections, with potential for real-time surgical use.ApproachFresh ex vivo thyroid specimens were imaged using a 23-channel DOCI acquisition. A pixel-level principal component analysis (PCA) and logistic regression classifier produced tissue probabilities, aggregated by a regional majority-vote gate to categorize specimens as normal, follicular, or papillary. Tumor-specific squeeze-and-excitation U-Net models were trained on voxel-only inputs for semantic segmentation. PCA-guided channel ablation identified a reduced spectral subset, and the pipeline was retrained using a compact 12-channel input.ResultsThe first two PCA components explained over 70% of spectral variance and yielded well-separated tissue clusters. The regional PCA classifier achieved 92.3% validation accuracy and 100% accuracy on the test set. Full 23-channel U-Net models delivered strong segmentation (papillary: Dice nonempty 0.829, balanced Dice 0.914; follicular: Dice nonempty 0.618, balanced Dice 0.809). Reduced-channel models preserved most performance and improved follicular segmentation (Dice nonempty 0.762), confirming spectral redundancy.ConclusionsIntegrating DOCI with interpretable machine learning enables accurate, label-free differentiation and segmentation of thyroid tissues. Channel reduction demonstrates that high performance is achievable with a compact spectral subset, supporting faster, more cost-efficient DOCI systems and future real-time intraoperative deployment.

Objective: Patient frailty negatively impacts postsurgical outcomes across multiple specialties. Commonly used frailty scoring systems include the Modified 5‐Item Frailty Index (MFI‐5) and the Clinical Risk Analysis Index (RAI‐C). We compared these frailty indices in predicting postsurgical outcomes in otolaryngology, a comparison that has never been completed to date. Methods: Retrospective chart review of patients undergoing otolaryngologic surgery at a quaternary care medical center (2022–2024) with an RAI‐C score available for analysis. Chi‐square analysis and ROC curves were utilized to determine associations and predictive ability of each scoring system. Results: Among 1209 patients, 21% met MFI‐5 frailty criteria (MFI‐5 score > 1), and 23% met RAI‐C frailty criteria (RAI‐C score > 30). The Pearson correlation coefficient between MFI‐5 and RAI‐C was 0.481 (95% CI [0.43, 0.53]), indicating a moderate correlation between the two metrics. Patients deemed frail by RAI‐C had 5.7 times higher odds of experiencing a postoperative complication than non‐frail counterparts (95% CI [3.51, 9.28], p < 0.0001), but MFI‐5 frailty status was not associated with postoperative complications. Both RAI‐C and MFI‐5 demonstrated significant predictive ability for 30‐day readmission (AUC 0.77, 95% CI [0.64, 0.89] vs. AUC 0.76, 95% CI [0.61, 0.88]), respectively. When compared to MFI‐5, RAI‐C had greater predictive performance for all other postoperative outcomes in this study. Conclusion: RAI‐C outperformed MFI‐5 in predicting postoperative outcomes in patients undergoing otolaryngologic surgeries. RAI‐C assessment should be considered in frailty research, multidisciplinary treatment planning, and managing patient expectations and outcomes.

Thyroid cancer presents significant diagnostic challenges due to its complex anatomy and diverse tissue types. This study leverages Dynamic Optical Contrast Imaging (DOCI), a label-free, real-time imaging technology, with machine learning to enhance tumor detection and segmentation. Using 23 DOCI filters, we applied Principal Component Analysis (PCA) for dimensionality reduction, k-nearest neighbors (k-NN) for classification, and U-Net models for segmentation. The approach achieved high accuracy in distinguishing tissue types, with PCA enabling clear clustering, k-NN classifying normal, follicular, and papillary tissues, and U-Net models achieving 96.34% and 92.02% accuracy for papillary and follicular segmentation, respectively. Filter importance analysis reduced input dimensionality without significantly compromising performance, highlighting the potential for optimized imaging protocols. These findings demonstrate DOCI’s utility in improving diagnostic accuracy and tumor characterization in thyroid cancer and beyond, offering a foundation for personalized treatment planning and surgical precision.

Objective: To investigate the state and trajectory of gender, racial, and academic authorship diversity in the otolaryngology clinical trial literature over the past 2 decades.Study Design: Bibliometric analysis.Setting: Otolaryngology clinical trial literature.Methods: Clinical trials published in the 9 major otolaryngology journals between 2000 and 2020 were included. The gender, race, and academic seniority of the first, senior, and corresponding authors were recorded for each trial. Multivariable regression models assessed the temporal trajectory of authorship diversity over time and the disparity in citations across author characteristics. Models adjusted for relevant confounders pertaining to publication environment and study design.Results: Among 2117 trials, first, senior, and corresponding authors have been predominantly White (60%‐64%), male (76%‐80%), and attending physicians (63%‐69%). Trials led by Black (β 0.8%, 95% CI [0.5%, 1.1%] per year), Asian (1.0% [0.7%, 1.3%] per year), and MD resident (0.4% [0.1%, 0.7%] per year) first authorship increased, but representation of female (0.2% [−0.1%, 0.5%] per year), Black (0% [−0.03%, 0.02%] per year), Hispanic (−0.2% [−0.33%, −0.02%] per year) senior authorship remained persistently low. Asian‐led trials were cited significantly less compared to White‐led trials even after adjusting for study design and publication year (aIRR 0.82 [0.73, 0.92]).Conclusions: Despite promising signs of improving authorship diversity over time, persistent underrepresentation of female, Black, Hispanic senior authorship underscore the need for additional efforts to diversify the otolaryngology clinical science workforce.

Objectives: Anaplastic thyroid cancer (ATC) is the most aggressive and fatal thyroid malignancy. Currently, there still exists a paucity of literature studying the relationship between available ATC‐targeted therapy, immunotherapy, and survival. We aim to investigate how systemic therapies affect survival outcomes in ATC.Methods: A single‐tertiary‐institution chart review of patients diagnosed with advanced‐stage ATC, and who underwent surgery as part of their treatment, was performed between 2000 and 2023, with 41 patients included. Demographics, clinical characteristics, and survival data were collected and analyzed via Kaplan–Meier and Cox proportional hazards analyses.Results: 54% of patients were female, and average age was 67.4 years old. The most common mutations identified were BRAF (15 patients), p53 (9 patients), and p63 (2 patients). A total of 18 patients utilized targeted or immunotherapy, with Trametinib and Dabrafenib (9 patients) as the most common agents used. Two‐year overall survival was 24%, and 5‐year overall survival was 23%, with median survival time of 7.6 months. Kaplan–Meier analysis demonstrated improved survival in patients who received chemotherapy (p = 0.048). Cox proportional hazards analysis demonstrated that patients treated with immunotherapy or targeted therapy had a statistically significant increase in survival compared with patients who did not receive these therapies (p = 0.016). Additionally, females and those with a p63 mutation demonstrated improved survival outcomes (p = 0.010, p = 0.001).Conclusions: Targeted therapy and immunotherapy use should be strongly considered when treating patients with ATC. Further studies into novel drugs targeting immune checkpoints and combination therapy are needed to better optimize treatment of patients with ATC.Level of Evidence: 3 Laryngoscope, 2024

Objective: The Risk Analysis Index (RAI) score is a screening tool to assess patient frailty. It has been shown to be predictive of postoperative outcomes and mortality in orthopedic, urologic, and neurosurgical patient populations. We sought to evaluate the predictive ability of RAI score for surgical outcomes in an otolaryngology patient population.Study Design: Retrospective study.Setting: Academic tertiary medical center.Methods: A retrospective study was conducted of adult patients undergoing otolaryngology surgery at a tertiary medical care center over 21 months. Patients were sent electronic RAI survey questionnaires via direct messaging, which was completed prior to surgery. Endpoint data were analyzed, including demographics, RAI score, and patient outcome data. Univariate analysis, ROC curves, and predictive modeling were utilized.Results: A total of 517 patients responded to the RAI questionnaire, resulting in a 59.6% response rate. Mean RAI score was 21.38 ± 11.83. Higher RAI scores were associated with increased 30‐day readmissions (P < .0015), postoperative complications (P < .001), hospital length of stay (P < .001), and discharge with home health (P < .001). Predictive models for RAI score and postoperative outcomes were created, and a cutoff score of RAI = 30 was established to identify frail patients.Conclusion: We evaluated if RAI scoring predicted postoperative complications in an otolaryngology patient population. Increased RAI score is significantly associated with poorer surgical outcomes, including increased hospital length of stay, 30‐day readmissions, and postoperative complications. We propose a predictive model with suggested RAI cutoff scoring for use in the otolaryngology surgical population.

Objective: This scoping review seeks to understand the existing research in otolaryngological mucosal emphysematous infections and to elucidate gaps in knowledge in the field. We also present a case of bilateral necrotizing tonsillitis in an immunocompromised patient with the first reported imaging findings of emphysematous abscess of the tonsils.Data Sources: PubMed, Embase, Web of Science.Review Methods: We conducted our review according to the Preferred Reporting Items for Systematic Reviews extension for Scoping Reviews. Patient presentation, management, and outcomes were summarized. We also describe the case of a patient with aplastic anemia found to have emphysematous tonsillitis, managed with intubation, broad spectrum intravenous antibiotics and bilateral tonsillectomy.Results: We identified seven case reports or series, involving nine total patients, who presented with emphysematous epiglottitis, supraglottitis, or tonsillitis. The hallmark imaging characteristic was submucosal “gas bubble” on computed tomography. Presenting symptoms included dysphagia, odynophagia, dysphonia, cough, and fever. Both immunocompetent and immunocompromised patients were affected. All patients were treated with broad spectrum antibiotics, and most with steroids. Patients at risk of airway compromise also underwent intubation and surgical drainage or debridement of the emphysematous infection.Conclusion: Emphysematous pharyngeal infections are rare but potentially life‐threatening infections that can progress rapidly, resulting in airway compromise and sepsis in both immunocompetent and immunocompromised individuals. We highlight the importance of swift intervention, with intubation and surgical intervention often required for severe cases. More research is needed on common pathogens and patient risk factors to guide future medical and surgical management.

Objective: To validate the efficacy of a virtual, interdisciplinary workshop in improving HPV knowledge, and vaccination practices among primary care and dental trainees.Methods: A virtual platform was utilized to hold HPV educational workshops with primary care and dental trainees. Online surveys were distributed before and after the 1‐h interactive workshop, led by otolaryngology residents. Surveys included the workshop's impact on (a) improving knowledge of HPV‐associated oropharyngeal squamous cell carcinoma (OPSCC) and (b) affecting change in HPV vaccination practices. The vaccination rates of trainees were recorded prior to and after workshop attendance.Results: After the workshop, participants demonstrated significantly improved scores related to knowledge of HPV in the head and neck (p = 0.003) and showed an increased comfort level with counseling on HPV vaccination (p = 0.002). Respondents were also more aware that the HPV vaccine is approved to prevent OPSCC (61% vs. 95%, p < 0.05). Ninety‐seven percent of respondents stated that the workshop changed their HPV vaccination practices, and 95% of those not fully vaccinated stated they would now be more likely to receive the vaccine themselves. There was a significant increase in the average number of HPV vaccines administered at the studied trainee clinic, from 16.83 vaccines/month to 37.6 vaccines/month (percent increase = 123%) in 5 months following the workshop (p = 0.002).Conclusion: The present interactive virtual workshop demonstrates efficacy in improving HPV‐related knowledge and vaccination practices among trainees. The virtual nature of the course facilitates knowledge transfer and can be used to foster multi‐institutional partnerships regarding medical education and vaccination efforts.Level of Evidence: 4 Laryngoscope, 134:3096–3101, 2024

Background: Cutaneous angiosarcoma is an aggressive tumor commonly found in the head and neck region. There is no consensus regarding the definitive treatment for angiosarcoma.Methods: This was a retrospective chart review that evaluated 64 patients from 1983 to 2019. Demographic and clinical variables were examined for impact on recurrence using the time to recurrence and the overall survival in Kaplan–Meier curves.Results: Average age at diagnosis was 71 (32–95) years, with a 2.8 male: female ratio. Surgery was utilized in 62% of patients, with mean defect size of 11.4 ± 8.1 cm. Recurrence was found in 70% of patients, and mean time to recurrence was 15.3 ± 12.3 months. Decreased recurrence was associated with use of intraoperative frozen section analysis (p = .036) and negative margins (p = .086). Two‐year overall survival was 80%, and recurrence free survival was 30%.Conclusions: Negative margins are associated with decreased recurrence, and intraoperative frozen section analysis may be considered to obtain preliminary surgical margins.Level of Evidence: 4.