How Easily Can AI Chatbots Spread Misinformation in Audiology and Otolaryngology?
OTO Open · 2026-01 · 10 (1)
DOI: 10.1002/oto2.70204 ↗Kurz gefasst
Fachartikel in der Zeitschrift OTO Open, online erschienen am 03.03.2026. Verfasst von W Wiktor Jedrzejczak und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Experimental Audiology World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objective
Chatbots powered by large language models (LLMs) have recently emerged as prominent sources of information. However, their ability to propagate misinformation as well as information, particularly in specialized fields like audiology and otolaryngology, remains underexplored. This study aimed to evaluate the accuracy of 6 popular chatbots—ChatGPT, Gemini, Claude, DeepSeek, Grok, and Mistral—in response to questions framed around a range of unproven methods in audiological and otolaryngological care. Study Design Cross‐sectional study.
Setting
A set of 50 questions was developed based on common conversations between patients and clinicians. We then posed these questions to the chatbots.
Methods
We tested each chatbot 10 times to account for variable responses, producing a total of 3000 responses. The responses were compared with correct answers based on the general opinion of 11 professionals. The consistency of the responses was evaluated by Cohen's Kappa.
Results
Most chatbot responses to the majority of questions were deemed accurate. Grok consistently performed best, where its answers aligned perfectly with the opinions of the experts. Deepseek exhibited the lowest accuracy, scoring 95.8%. Mistral exhibited the lowest consistency, scoring 0.96.
Conclusions
Although all the chatbots generally avoided endorsing unproven methods, some responses deviated from the expert consensus and could therefore be said to contribute to the spread of misinformation. The best performer among the group was Grok, which provided consistently accurate responses, showing it has the potential for clinical and educational use within audiology and otolaryngology.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Experimental Audiology World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland.
- Audiology and Phoniatrics Clinic World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland.
- Tinnitus Department World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland.
- Rehabilitation Clinic World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland.
- Otorhinolaryngosurgery Clinic World Hearing Center, Institute of Physiology and Pathology of Hearing Warsaw Poland.
ORCID-Profile: W Wiktor Jedrzejczak, Agata Szkiełkowska, Danuta Raj-Koziak, Elżbieta Włodarczyk, Henryk Skarżyński, Krzysztof Kochanek
Zitieren
APA
Jedrzejczak, W. W., Szkiełkowska, A., Raj-Koziak, D., Włodarczyk, E., Skarżyński, H., & Kochanek, K. (2026). How Easily Can AI Chatbots Spread Misinformation in Audiology and Otolaryngology?. OTO Open, 10(1). https://doi.org/10.1002/oto2.70204
Vancouver
Jedrzejczak WW, Szkiełkowska A, Raj-Koziak D, Włodarczyk E, Skarżyński H, Kochanek K. How Easily Can AI Chatbots Spread Misinformation in Audiology and Otolaryngology?. OTO Open. 2026;10(1). doi:10.1002/oto2.70204
BibTeX
@article{Jedrzejczak2026,
author = {Jedrzejczak, W Wiktor and Szkiełkowska, Agata and Raj-Koziak, Danuta and Włodarczyk, Elżbieta and Skarżyński, Henryk and Kochanek, Krzysztof},
title = {How Easily Can AI Chatbots Spread Misinformation in Audiology and Otolaryngology?},
journal = {OTO Open},
year = {2026},
volume = {10},
number = {1},
doi = {10.1002/oto2.70204}
}
EUVIMED