Objective: To evaluate the clinical applications and limitations of chat generative pretrained transformer (ChatGPT) in otolaryngology.Study Design: Cross‐sectional survey.Setting: Tertiary academic center.Methods: ChatGPT 4.0 was queried for diagnoses and management plans for 20 physician‐written clinical vignettes in otolaryngology. Attending physicians were then asked to rate the difficulty of the clinical vignettes and agreement with the differential diagnoses and management plans of ChatGPT responses on a 5‐point Likert scale. Summary statistics were calculated. Univariate ordinal regression was then performed between vignette difficulty and quality of the diagnoses and management plans.Results: Eleven attending physicians completed the survey (61% response rate). Overall, vignettes were rated as very easy to neutral difficulty (range of median score: 1.00‐4.00; overall median 2.00). There was a high agreement with the differential diagnosis provided by ChatGPT (range of median score: 3.00‐5.00; overall median: 5.00). There was also high agreement with treatment plans (range of median score: 3.00‐5.00; overall median: 5.00). There was no association between vignette difficulty and agreement with differential diagnosis or treatment. Lower diagnosis scores had greater odds of having lower treatment scores.Conclusion: Generative artificial intelligence models like ChatGPT are being rapidly adopted in medicine. Performance with curated, easy‐to‐moderate difficulty otolaryngology scenarios indicate high agreement with physicians for diagnosis and management. However, a decreased quality in diagnosis is associated with decreased quality in management. Further research is necessary on ChatGPT's ability to handle unstructured clinical information.

Objective: Laser-assisted uvulopalatoplasty (LAUP) has been used as a treatment option for snoring and obstructive sleep apnea for almost three decades. It has been previously reported that some patient’s sleep-disordered breathing worsened following surgery. The aim of this paper is to further elucidate the specific complications of LAUP. Data sources: A systematic search of the electronic databases MEDLINE/PubMed, Google Scholar, and Embase. Review methods: The PRISMA statement was followed. Databases were searched from inception through September 2, 2018. The following search was applied to MEDLINE/PubMed ((laser AND uvul*) OR (LAUP) OR (LAVP) OR (laser AND (apnea OR apnoea OR sleep))). Results: Forty-two studies with a mean follow-up of 16.1 months reported complications on 3,093 total patients who underwent LAUP. The percentages and associated complications of LAUP are as follows: bleeding (2.6%), candidiasis (0.3%), dryness (7.2%), dysgeusia (0.3%), dysosmia (0.2%), globus sensation (8.2%), surgical site infection (1.3%), velopharyngeal (VP) insufficiency (3.9%), and VP stenosis (1.6%). The mean duration of patient-reported pain in studies that reported pain was 11.65 days. Only globus and VP insufficiency had a significant incidence compared with either the general population or the post-oropharyngeal surgery population with relative risks of 1.48 and 2.25, respectively. Overall, there were approximately 26 complications per 100 patients who underwent LAUP. Conclusion: LAUP is associated with a statistically significant rate of VP insufficiency and globus sensation; however, studies lack details of surgical approaches, suggesting that in a population identified as good candidates, a tissue-sparing approach may result in fewer complications.

Military Medicine is AMSUS’ monthly peer-reviewed journal, with articles including scientific papers, case reports, and editorials. Its objective is to promote awareness of federal medicine by providing a forum for responsible discussion of common ideas and problems relevant to federal healthcare.