Exploring the Reliability of Allergic Rhinitis Information Provided by AI: A Critical Analysis (2024 AAAAI abstract)

Curious about the accuracy of medical info provided by AI? 🧠💻 Our recent study delves into the reliability of allergic rhinitis data presented by ChatGPT, a popular AI chatbot, compared to clinical guidelines.

Methodology: We evaluated ChatGPT's responses against the AAAAI/ACAAI guidelines, covering prevalence, symptoms, diagnostic tests, management, and prevention. Using the DISCERN instrument, we assessed the quality of information provided.

Key Findings: While ChatGPT scored decently with a 3.44/5 DISCERN score and 81% agreement with guidelines, there were concerns. Only 52% of ChatGPT's sources were accurate, with fabricated articles and dead webpage links among the inaccuracies.

Conclusion: While ChatGPT reflects established guidelines to an extent, it falls short in reliability due to significant errors in sourcing. As AI continues to evolve in healthcare, critical appraisal remains crucial.

📚 For more details, check out the full study here: 

https://www.jacionline.org/article/S0091-6749(23)02249-2/fulltext

The study was published in JACI, one of the highest ranked allergy/immunology journal and was selected for oral presentation during the 2024 AAAAI meeting. Dr Graneiro will present the research. 

Reliability Of Allergic Rhinitis Information Presented By An Artificial Intelligence Bot Versus Clinical. Dimova M, Lorenz K, Dimov G, Raviv O, Graneiro A, Dimov V, Randhawa S. J Allergy Clin Immunol, Vol 153, Issue 2, Suppl AB236, Feb 2024.

DOI:https://doi.org/10.1016/j.jaci.2023.11.758

Got questions or thoughts on AI in medical information? Drop them below! 👇 #AIHealthcare #AllergicRhinitis #MedicalResearch