ChatGPT vs. multidisciplinary team decisions in auditory implantation: a concordance analysis of implant type and side selection
- 19 July 2026
- journal article
- research article
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 283 (10) , 6357-6364
Abstract
Introduction Auditory implantation is a standard rehabilitation strategy for patients with severe hearing loss, and candidacy determination requires a multidisciplinary, multidimensional evaluation. With the increasing clinical use of artificial intelligence–based large language models, ChatGPT has emerged as a potential decision-support tool. This study aimed to evaluate the agreement between multidisciplinary team (MDT) decisions and ChatGPT recommendations in pediatric and adult implant candidates. Methods This retrospective cross-sectional study included 100 consecutive auditory implant candidates (50 pediatric, 50 adult) evaluated at a tertiary referral center. Each case was independently presented to ChatGPT (OpenAI, accessed March 2025) using standardized English prompts. ChatGPT was asked whether implantation was recommended and, if so, which side should be implanted. MDT decisions were used as the reference standard, and agreement between MDT and ChatGPT was analyzed using Cohen’s kappa (κ) coefficient. Results High agreement was observed between MDT and ChatGPT for both implant type (κ = 0.714; p < 0.001) and side of implantation (κ = 0.701; p < 0.001). Subgroup analysis demonstrated higher agreement in pediatric patients (implant type κ = 0.773; side κ = 0.784; p < 0.001) compared to adults (implant type κ = 0.589; side κ = 0.601; p < 0.001). Concordance was also higher in simple cases than in clinically complex cases. Conclusion ChatGPT demonstrated substantial agreement with MDT decisions regarding implant type and side of implantation, with higher concordance in pediatric and simple cases. These findings suggest that ChatGPT may serve as a supportive decision-making tool in structured clinical scenarios; however, multidisciplinary evaluation remains essential in individualized and complex cases.Keywords
This publication has 18 references indexed in Scilit:
- The utility of large language models in oncological multidisciplinary team meetings: A systematic reviewEuropean Journal of Surgical Oncology, 2026
- ChatGPT-4 vs. multi-disciplinary tumor board decisions for the therapeutic management of primary laryngeal cancerActa Oto-Laryngologica, 2025
- Concordance of ChatGPT artificial intelligence decision-making in colorectal cancer multidisciplinary meetings: retrospective studyBJS Open, 2025
- Performance of artificial intelligence in answering cardiovascular textual questionsEuropean Heart Journal - Digital Health, 2023
- Large language model (ChatGPT) as a support tool for breast tumor boardnpj Breast Cancer, 2023
- Determining Cochlear Implant Candidacy in Adults: Limitations, Expansions, and Opportunities for ImprovementSeminars in Hearing, 2021
- What Influences Decision-Making for Cochlear Implantation in Adults? Exploring Barriers and Drivers From a Multistakeholder PerspectiveEar & Hearing, 2020
- Long-term Communication Outcomes for Children Receiving Cochlear Implants Younger Than 12 MonthsOtology & Neurotology, 2016
- Auditory brainstem implantationAuris Nasus Larynx, 2012
- Cochlear Implants in Children--A ReviewActa Oto-Laryngologica, 2002