Hess-Erga, Jeanette

Objective To examine the quality of information provided by artificial intelligence platforms ChatGPT-4 and Claude 2 surrounding the management of vestibular schwannomas. Study design Cross-sectional. Setting Skull base surgeons were involved from different centers and countries. Intervention Thirty-six questions regarding vestibular schwannoma management were tested. Artificial intelligence responses were subsequently evaluated by 19 lateral skull base surgeons using the Quality Assessment of Medical Artificial Intelligence (QAMAI) questionnaire, assessing “Accuracy,” “Clarity,” “Relevance,” “Completeness,” “Sources,” and “Usefulness.” Main Outcome Measure The scores of the answers from both chatbots were collected and analyzed using the Student t test. Analysis of responses grouped by stakeholders was performed with McNemar test. Stuart-Maxwell test was used to compare reading level among chatbots. Intraclass correlation coefficient was calculated. Results ChatGPT-4 demonstrated significantly improved quality over Claude 2 in 14 of 36 (38.9%) questions, whereas higher-quality scores for Claude 2 were only observed in 2 (5.6%) answers. Chatbots exhibited variation across the dimensions of “Accuracy,” “Clarity,” “Completeness,” “Relevance,” and “Usefulness,” with ChatGPT-4 demonstrating a statistically significant superior performance. However, no statistically significant difference was found in the assessment of “Sources.” Additionally, ChatGPT-4 provided information at a significant lower reading grade level. Conclusions Artificial intelligence platforms failed to consistently provide accurate information surrounding the management of vestibular schwannoma, although ChatGPT-4 achieved significantly higher scores in most analyzed parameters. These findings demonstrate the potential for significant misinformation for patients seeking information through these platforms.

ABSTRACT Over the past two decades, there has been increasing interest in the diagnosis and management of schwannomas of the inner ear including hearing rehabilitation with cochlear implants. However, tumor nomenclature and classification within the literature have been variable and oftentimes cumbersome. The term “intralabyrinthine schwannoma” is in common use when describing these tumors but is a potential source of confusion given that people often use the term “labyrinth” or “labyrinthine” to refer to the vestibular component of the inner ear only (i.e., labyrinthectomy or the translabyrinthine approach). During the Ninth Quadrennial Conference on Vestibular Schwannoma and Other Cerebellopontine Angle Lesions in Bergen, Norway, in May 2023, a multidisciplinary group of conference participants met and discussed issues pertaining to current terminology and classifications to enhance clarity and to reflect recent advances in tumor management and hearing rehabilitation. Although a variety of terms have been previously used to describe inner ear schwannomas, consensus was achieved on the term “inner ear schwannoma (IES)” to describe eighth nerve schwannomas of the cochlea, vestibule, or semicircular canals. Subgroups under this term comprise intravestibular, intracochlear, or intravestibulocochlear inner ear schwannomas (low complexity tumors), inner ear schwannomas with transfundal extension into the internal auditory canal but without modiolar involvement (intermediate complexity tumors), and inner ear schwannomas with transfundal extension with modiolar involvement (high complexity tumors). The details of the recommendations for an updated and simplified tumor nomenclature centered around tumor control and hearing rehabilitation with cochlear implantation are presented.