Validity, reliability, and readability of Artificial Intelligence chatbots as public sources of information on hearing loss: a comparative evaluation of ChatGPT, Bing, Gemini, and Perplexity
AI chatbots deliver generally accurate hearing-health content, but high-threshold accuracy, domain-specific reliability and readability remain suboptimal. They should supplement, not replace the professional counselling. Continued optimisation and external validation are needed before routine clinical recommendation.
Authors
- Sara Rafiee (ORCID: https://orcid.org/0009-0008-5180-7388)
- Derek J. Hoare (ORCID: https://orcid.org/0000-0002-8768-1392)
- Mohamad Amin Pourhoseingholi (ORCID: https://orcid.org/0000-0002-0121-8031)
- Catherine F. Killan (ORCID: https://orcid.org/0000-0002-8092-6238)
- Paul K. Bateman (ORCID: https://orcid.org/0000-0002-2584-7641)
- Nicola Wray
Institutions
- University of Nottingham (GB)
- NIHR Nottingham Hearing Biomedical Research Unit (GB)
- Nottingham Biomedical Research Centre (GB)
- Shahid Beheshti University of Medical Sciences (IR)
Publication Details
- Journal
- International Journal of Audiology
- Published
- 2025-10-23
- DOI
- https://doi.org/10.1080/14992027.2025.2569927
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31