AI health advice isn’t always right

Image credit: zulfugarkarimov via Unsplash

AI chatbots like ChatGPT and Google Gemini are increasingly used for health questions, but recent studies raise serious concerns about their reliability. In one analysis, these tools answered medical questions incorrectly nearly half the time, highlighting risks of misinformation, missed diagnoses, and unsafe recommendations. While they can be helpful for general education, they should never replace professional medical evaluation, especially when symptoms are serious or decisions carry real consequences.

Source

Rao AS, Esmail KP, Lee RS, et al. Large Language Model Performance and Clinical Reasoning Tasks. JAMA Netw Open. 2026;9(4):e264003. doi:10.1001/jamanetworkopen.2026.4003

Additional Reading

https://www.washingtonpost.com/health/2026/04/21/chatbot-medical-advice-accurate/

https://medschool.duke.edu/stories/hidden-risks-asking-ai-health-advice

https://www.bbc.com/news/articles/clyepyy82kxo

Previous
Previous

Walk faster, live longer

Next
Next

Milk phospholipids and early brain development