TY - JOUR

T1 - Artificial intelligence and allergic rhinitis

T2 - does ChatGPT increase or impair the knowledge?

AU - Høj, Simon

AU - Thomsen, Simon F.

AU - Meteran, Hanieh

AU - Sigsgaard, Torben

AU - Meteran, Howraman

N1 - Publisher Copyright: © The Author(s) 2023. Published by Oxford University Press on behalf of Faculty of Public Health.

PY - 2024

Y1 - 2024

N2 - Background Optimal management of allergic rhinitis requires patient education with easy access to accurate information. However, previous online platforms have provided misleading information. The demand for online medical information continues to grow, especially with the introduction of advanced chatbots like ChatGPT. Methods This study aimed to evaluate the quality of information provided by ChatGPT regarding allergic rhinitis. A Likert scale was used to assess the accuracy of responses, ranging from 1 to 5. Four authors independently rated the responses from a healthcare professional’s perspective. Results A total of 20 questions covering various aspects of allergic rhinitis were asked. Among the answers, eight received a score of 5 (no inaccuracies), five received a score of 4 (minor non-harmful inaccuracies), six received a score of 3 (potentially misinterpretable inaccuracies) and one answer had a score of 2 (minor potentially harmful inaccuracies). Conclusions The variability in accuracy scores highlights the need for caution when relying solely on chatbots like ChatGPT for medical advice. Patients should consult qualified healthcare professionals and use online sources as a supplement. While ChatGPT has advantages in medical information delivery, its use should be approached with caution. ChatGPT can be useful for patient education but cannot replace healthcare professionals.

AB - Background Optimal management of allergic rhinitis requires patient education with easy access to accurate information. However, previous online platforms have provided misleading information. The demand for online medical information continues to grow, especially with the introduction of advanced chatbots like ChatGPT. Methods This study aimed to evaluate the quality of information provided by ChatGPT regarding allergic rhinitis. A Likert scale was used to assess the accuracy of responses, ranging from 1 to 5. Four authors independently rated the responses from a healthcare professional’s perspective. Results A total of 20 questions covering various aspects of allergic rhinitis were asked. Among the answers, eight received a score of 5 (no inaccuracies), five received a score of 4 (minor non-harmful inaccuracies), six received a score of 3 (potentially misinterpretable inaccuracies) and one answer had a score of 2 (minor potentially harmful inaccuracies). Conclusions The variability in accuracy scores highlights the need for caution when relying solely on chatbots like ChatGPT for medical advice. Patients should consult qualified healthcare professionals and use online sources as a supplement. While ChatGPT has advantages in medical information delivery, its use should be approached with caution. ChatGPT can be useful for patient education but cannot replace healthcare professionals.

KW - allergy

KW - Artificial intelligence

KW - ChatGPT

KW - digital health

KW - rhinitis

UR - http://www.scopus.com/inward/record.url?scp=85186453644&partnerID=8YFLogxK

U2 - 10.1093/pubmed/fdad219

DO - 10.1093/pubmed/fdad219

M3 - Journal article

C2 - 37968109

AN - SCOPUS:85186453644

VL - 46

SP - 123

EP - 126

JO - Journal of Public Health

JF - Journal of Public Health

SN - 1741-3842

IS - 1

ER -