By Rebecca Payne
Publication Date: 2026-03-31 14:53:00
Millions of people turn to artificial intelligence (AI) chatbots for advice on everything from cooking to filing taxes. Chatbots are increasingly asking them about their health.
But as the UK’s top medical official recently warned, this may not be wise when it comes to medical decisions. In a recent study, colleagues and I tested how well large language model (LLM) chatbots help the public deal with common health problems. The results were striking.
The chatbots we tested were not ready to act as doctors. A common reaction to studies like this is that AI is evolving faster than scientific publishing. By the time an article appears, the models tested may already be updated. However, studies using newer versions of these patient triage systems suggest that the same problems remain.
We gave participants brief descriptions of common medical situations. They were randomly assigned to either use one of three widely used chatbots or rely on any sources…
