Search

Objective(s): To evaluate the impact of consistent surgical teams on procedure duration in head and neck free tissue transfer, and to evaluate the length of stay and readmission rates with consistent teams. Methods: A retrospective chart review of head and neck microvascular reconstruction by a single surgeon between August 2017 and November 2021 was performed. Procedure duration, wound complications, length of stay, and 30‐day readmissions were analyzed. One circulating nurse (CN) and surgical technologist (ST) were considered "consistent" due to their prior work with the primary surgeon. All others were considered "ad hoc." Teams were "Consistent CN + ST," "Consistent ST," "Consistent CN," or "Ad hoc." Procedure duration between groups was compared via analysis of variance. Multivariate linear regression was performed to predict procedure duration. Results: A total of 135 patients were included. Age, sex, and American Society of Anesthesiologists status did not significantly differ across groups (p = 0.963; p = 0.467; p = 0.908, respectively). The mean procedure duration was 339.3 min and differed significantly across all groups (p = 0.006, Cohen d = 0.32). Compared to the Ad hoc group, consistent teams demonstrated significant reductions in mean procedure duration (Consistent CN + ST: 58.4 min, p = 0.001, Cohen d = 0.67; Consistent ST: 51.6 min, p = 0.013, Cohen d = 0.61; Consistent CN: 44.5 min, p = 0.031, Cohen d = 0.52). Controlling for other factors, the ad hoc team predicted increased procedure duration on multivariate analysis (β 57.38, 19.92–94.85, p < 0.003). Wound complications, length of stay, and readmission rates did not differ significantly across groups (p = 0.940; p = 0.174; p = 0.935, respectively). Conclusion: Consistent CN and ST improve operative efficiency in head and neck‐free tissue transfer. Future studies may evaluate the impact of team consistency on complications, physician burnout, and health systems costs. Level of Evidence: 3 Laryngoscope, 133:2154–2159, 2023 [ABSTRACT FROM AUTHOR]

Objective(s): Maneuvers during drug‐induced sleep endoscopy (DISE), for patients with obstructive sleep apnea (OSA), have been used as predictors for success with oral appliances. Hypoglossal nerve stimulation (HGNS) promotes opening at the velum through palatoglossus coupling. In this study, we evaluate maneuvers during DISE as predictors for HGNS treatment efficacy. Methods: We evaluated patients undergoing HGNS between November, 2014 and February, 2021. We assessed maneuvers including jaw thrust and chin lift during preoperative DISE. The impact of tongue base and palatal opening during these maneuvers were rated from 1 to 4 (1: no improvement, 2: mild improvement, 3: moderate improvement, 4: significant improvement). Patients were grouped by a score of 1–2 (weak response) or 3–4 (strong response). Apnea hypopnea index (AHI) change was calculated from the difference between preoperative and postoperative sleep study. Results: One hundred and seventy one patients were included. With jaw thrust, there was no significant difference in AHI change between patients with weak or strong response at the palate (n = 68 vs. 94, 9.5 vs. 13.6, p = 0.21) or tongue base (n = 24 vs. 138, 16.6 vs. 11.3, p = 0.24). On chin lift, there was no significant difference at the palate (n = 82 vs. 18, 13.9 vs. 11.4, p = 0.63) or tongue base (n = 92 vs. 72, 10.8 vs. 14.6, p = 0.24). On multiple linear regression analysis, lower body mass index, higher preoperative AHI, and higher preoperative oxygen nadir were associated with a larger AHI change. Conclusion: Palatal coupling maneuvers during DISE are not predictive of AHI change with HGNS. Findings using these maneuvers should not preclude HGNS candidacy. Level of Evidence: 3 Laryngoscope, 133:431–436, 2023 [ABSTRACT FROM AUTHOR]

A review of current literature on the surgical management of nasal obstruction for eustacian tube dysfunction suggests potential benefit. However, due to the lack of prospective studies with control groups definitive benefit cannot be determined. Further studies are necessary to evaluate the role of nasal surgery in this patient population. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to assess reporting quality of machine learning (ML) algorithms in the head and neck oncology literature using the TRIPOD-AI criteria., Data Sources: A comprehensive search was conducted using PubMed, Scopus, Embase, and Cochrane Database of Systematic Reviews, incorporating search terms related to "artificial intelligence," "machine learning," "deep learning," "neural network," and various head and neck neoplasms., Review Methods: Two independent reviewers analyzed each published study for adherence to the 65-point TRIPOD-AI criteria. Items were classified as "Yes," "No," or "NA" for each publication. The proportion of studies satisfying each TRIPOD-AI criterion was calculated. Additionally, the evidence level for each study was evaluated independently by two reviewers using the Oxford Centre for Evidence-Based Medicine (OCEBM) Levels of Evidence. Discrepancies were reconciled through discussion until consensus was reached., Results: The study highlights the need for improvements in ML algorithm reporting in head and neck oncology. This includes more comprehensive descriptions of datasets, standardization of model performance reporting, and increased sharing of ML models, data, and code with the research community. Adoption of TRIPOD-AI is necessary for achieving standardized ML research reporting in head and neck oncology., Conclusion: Current reporting of ML algorithms hinders clinical application, reproducibility, and understanding of the data used for model training. To overcome these limitations and improve patient and clinician trust, ML developers should provide open access to models, code, and source data, fostering iterative progress through community critique, thus enhancing model accuracy and mitigating biases., Level of Evidence: NA Laryngoscope, 2024., (© 2024 The American Laryngological, Rhinological and Otological Society, Inc.)

Objectives: To develop and validate machine learning (ML) and deep learning (DL) models using drug-induced sleep endoscopy (DISE) images to predict the therapeutic efficacy of hypoglossal nerve stimulator (HGNS) implantation., Methods: Patients who underwent DISE and subsequent HGNS implantation at a tertiary care referral center were included. Six DL models and five ML algorithms were trained on images from the base of tongue (BOT) and velopharynx (VP) from patients classified as responders or non-responders as defined by Sher's criteria (50% reduction in apnea-hypopnea index (AHI) and AHI < 15 events/h). Precision, recall, F1 score, and overall accuracy were evaluated as measures of performance., Results: In total, 25,040 images from 127 patients were included, of which 16,515 (69.3%) were from responders and 8,262 (30.7%) from non-responders. Models trained on the VP dataset had greater overall accuracy when compared to BOT alone and combined VP and BOT image sets, suggesting that VP images contain discriminative features for identifying therapeutic efficacy. The VCG-16 DL model had the best overall performance on the VP image set with high training accuracy (0.833), F1 score (0.78), and recall (0.883). Among ML models, the logistic regression model had the greatest accuracy (0.685) and F1 score (0.813)., Conclusion: Deep neural networks have potential to predict HGNS therapeutic efficacy using images from DISE, facilitating better patient selection for implantation. Development of multi-institutional data and image sets will allow for development of generalizable predictive models., Level of Evidence: N/A Laryngoscope, 2024., (© 2024 The American Laryngological, Rhinological and Otological Society, Inc.)