Enhancing paranasal sinus disease detection with AutoML: efficient AI development and evaluation via magnetic resonance imaging.

PURPOSE: Artificial intelligence (AI) in the form of automated machine learning (AutoML) offers a new potential breakthrough to overcome the barrier of entry for non-technically trained physicians. A Clinical Decision Support System (CDSS) for screening purposes using AutoML could be beneficial to ease the clinical burden in the radiological workflow for paranasal sinus diseases. METHODS: The main target of this work was the usage of automated evaluation of model performance and the feasibility of the Vertex AI image classification model on the Google Cloud AutoML platform to be trained to automatically classify the presence or absence of sinonasal disease. The dataset is a consensus labelled Open Access Series of Imaging Studies (OASIS-3) MRI head dataset by three specialised head and neck consultant radiologists. A total of 1313 unique non-TSE T2w MRI head sessions were used from the OASIS-3 repository. RESULTS: The best-performing image classification model achieved a precision of 0.928. Demonstrating the feasibility and high performance of the Vertex AI image classification model to automatically detect the presence or absence of sinonasal disease on MRI. CONCLUSION: AutoML allows for potential deployment to optimise diagnostic radiology workflows and lay the foundation for further AI research in radiology and otolaryngology. The usage of AutoML could serve as a formal requirement for a feasibility study.

Artificial intelligence chatbots as sources of patient education material for obstructive sleep apnoea: ChatGPT versus Google Bard.

PURPOSE: To perform the first head-to-head comparative evaluation of patient education material for obstructive sleep apnoea generated by two artificial intelligence chatbots, ChatGPT and its primary rival Google Bard. METHODS: Fifty frequently asked questions on obstructive sleep apnoea in English were extracted from the patient information webpages of four major sleep organizations and categorized as input prompts. ChatGPT and Google Bard responses were selected and independently rated using the Patient Education Materials Assessment Tool-Printable (PEMAT-P) Auto-Scoring Form by two otolaryngologists, with a Fellowship of the Royal College of Surgeons (FRCS) and a special interest in sleep medicine and surgery. Responses were subjectively screened for any incorrect or dangerous information as a secondary outcome. The Flesch-Kincaid Calculator was used to evaluate the readability of responses for both ChatGPT and Google Bard. RESULTS: A total of 46 questions were curated and categorized into three domains: condition (n = 14), investigation (n = 9) and treatment (n = 23). Understandability scores for ChatGPT versus Google Bard on the various domains were as follows: condition 90.86% vs.76.32% (p < 0.001); investigation 89.94% vs. 71.67% (p < 0.001); treatment 90.78% vs.73.74% (p < 0.001). Actionability scores for ChatGPT versus Google Bard on the various domains were as follows: condition 77.14% vs. 51.43% (p < 0.001); investigation 72.22% vs. 54.44% (p = 0.05); treatment 73.04% vs. 54.78% (p = 0.002). The mean Flesch-Kincaid Grade Level for ChatGPT was 9.0 and Google Bard was 5.9. No incorrect or dangerous information was identified in any of the generated responses from both ChatGPT and Google Bard. CONCLUSION: Evaluation of ChatGPT and Google Bard patient education material for OSA indicates the former to offer superior information across several domains.

Performance of artificial intelligence chatbots in sleep medicine certification board exams: ChatGPT versus Google Bard.

PURPOSE: To conduct a comparative performance evaluation of GPT-3.5, GPT-4 and Google Bard in self-assessment questions at the level of the American Sleep Medicine Certification Board Exam. METHODS: A total of 301 text-based single-best-answer multiple choice questions with four answer options each, across 10 categories, were included in the study and transcribed as inputs for GPT-3.5, GPT-4 and Google Bard. The first output responses generated were selected and matched for answer accuracy against the gold-standard answer provided by the American Academy of Sleep Medicine for each question. A global score of 80% and above is required by human sleep medicine specialists to pass each exam category. RESULTS: GPT-4 successfully achieved the pass mark of 80% or above in five of the 10 exam categories, including the Normal Sleep and Variants Self-Assessment Exam (2021), Circadian Rhythm Sleep-Wake Disorders Self-Assessment Exam (2021), Insomnia Self-Assessment Exam (2022), Parasomnias Self-Assessment Exam (2022) and the Sleep-Related Movements Self-Assessment Exam (2023). GPT-4 demonstrated superior performance in all exam categories and achieved a higher overall score of 68.1% when compared against both GPT-3.5 (46.8%) and Google Bard (45.5%), which was statistically significant (p value < 0.001). There was no significant difference in the overall score performance between GPT-3.5 and Google Bard. CONCLUSIONS: Otolaryngologists and sleep medicine physicians have a crucial role through agile and robust research to ensure the next generation AI chatbots are built safely and responsibly.

Ancient schwannoma of the cervical sympathetic chain.

Ancient schwannomas exhibit characteristic histological features. Fine-needle aspiration cytology (FNAC) is of limited use. Radiological evidence demonstrating displacement of blood vessels may aid diagnosis of schwannoma. Malignant transformation of ancient schwannoma has been reported. Surgical excision carries a high risk of postoperative Horner's syndrome.

Septic Arthritis of the Temporomandibular Joint Secondary to Acute Otitis Media in an Adult: A Rare Case with Achromobacter xylosoxidans.

Septic arthritis of the temporomandibular joint (SATMJ) is a rare complication of acute otitis media (AOM) with only four reported cases in the English and Japanese literature. Based on the unusual nature of this clinical condition, we discuss the first documented case due to Achromobacter xylosoxidans and the utility of myringotomy with long-term intravenous antibiotics via a peripherally inserted central catheter (PICC). We describe the case of a 76-year-old male patient that was brought in by ambulance to the accident and emergency (A&E) department due to severe right-sided otalgia with increased hearing impairment. A clinical diagnosis of acute otitis media with sepsis was made and the patient was commenced on the sepsis protocol. He then developed symptoms of septic arthritis of the TMJ which was confirmed on radiological imaging. After a multidisciplinary team discussion, the patient was treated with a myringotomy and intravenous ceftriaxone for 8 weeks in the community via a PICC rather than TMJ arthrocentesis with positive outcomes at 3 months' follow-up.

Peri-operative management of high-risk paediatric adenotonsillectomy patients: A survey of 35 UK tertiary referral centres.

INTRODUCTION: Peri-operative management of high-risk paediatric patients undergoing adenotonsillectomy for treatment of obstructive sleep apnoea varies between tertiary referral hospitals. 'Day of surgery cancellation' (DoSC) rates of up to 11% have been reported due to pre-booked critical care being unavailable on the day of surgery as a result of competing needs from other hospital departments. We report the results of a survey of peri-operative management in UK tertiary care centres of high-risk paediatric patients undergoing adenotonsillectomy for obstructive sleep apnoea (OSA). METHODS: An 8-point questionnaire was developed using a cloud-based software platform (www.surveymonkey.com). A web-link to the survey was embedded in a customised e-mail which was sent via secure server to the Clinical Leads for Paediatric Otolaryngology at 35 United Kingdom (UK) Tertiary referral centres. RESULTS: The survey response rate was 60% (n = 21). Almost all (94.1%) of centres considered paediatric critical care facilities to be limited, with 70.6% (n = 12) stating that DoSC often occurred due to unavailable paediatric critical care capacity. There was variation between tertiary referral units in the practice applied for pre-booking critical care beds (our survey identifies 6 variations) (Table 1). The most frequent selection method reported (47.1%) was at the discretion of the booking clinician at the time of listing the patient for surgery. CONCLUSION: In the context of limited critical care resources, variation in practice and difficulty in accurately predicting which patients will require post-operative critical care beds, a review and consensus on best practice in the peri-operative management of high risk paediatric adenotonsillectomy patients may offer a safe means of reducing cancellations and improving patient care, resource allocation and hospital efficiency.

Congenital Temporomandibular Joint Ankylosis: Case Report and Literature Review.

Congenital temporomandibular joint (TMJ) ankylosis is an uncommon condition that presents itself at or soon after birth in the absence of acquired factors that could have contributed to the ankylosis such as infection and trauma. The experience of managing one such case is reported in light of a review of the literature on this condition. Key management principles include adequate removal of the ankylotic mass, costochondral grafting, and post-op physiotherapy. Most patients reported in the literature with the condition experienced relapse. This echoes our own experience where there was recurrence of the ankylosis. However, after removal of the ankylotic mass, the patient maintains a satisfactory maximal incisal opening (MIO) till the present day. The additional challenges faced in the congenital form in addition to the already complex management of acquired paediatric temporomandibular joint ankylosis are (1) much earlier insult to the TMJ, (2) reduced opportunity for neuromuscular development of the muscles of mastication, and (3) reduced compliance with postoperative physiotherapy programmes due to the younger age of these patients.