Oxford Study LLM Chatbot Medical Advice Dangerous
I asked an LLM chatbot to identify a health condition from my symptoms and recommend next steps, and it answered confidently but produced 'a mix of good and bad information' — including wrong diagnoses and advice that failed to recognise when urgent help was needed. Is this safe?
1 Answer
Expert: Dr Rebecca Payne; Andrew Bean, GP and co-author, University of Oxford; Lead author, Oxford Internet Institute In a study published in Nature Medicine, researchers from the University of Oxford's Internet Institute and Nuffield Department of Primary Care Health Sciences asked nearly 1,300 participants to identify potential health conditions and recommend a course of action — some using large language model (LLM) chatbots to get a potential diagnosis and next steps, others using more traditional methods such as seeing a GP. The chatbots delivered "a mix of good and bad information" that users struggled to distinguish: wrong diagnoses and responses that failed to recognise when urgent help was needed. The researchers concluded that while AI chatbots now "excel at standardised tests of medical knowledge", using them to make real medical decisions "would pose risks to real users seeking help with their own medical symptoms". Lead author Andrew Bean (Oxford Internet Institute) said the study showed that "interacting with humans poses a challenge" even for the top-performing LLMs. Co-author Dr Rebecca Payne, a GP, said: "Despite all the hype, AI just isn't ready to take on the role of the physician. Patients need to be aware that asking a large language model about their symptoms can be dangerous — giving wrong diagnoses and failing to recognise when urgent help is needed." Source: https://www.bbc.com/news/articles/cpd8l088x2xo
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More in Medicine
- Parkinsons Chatbot 88 Percent Good Critical Errors — Parkinson's AI chatbot jAImes
- Google AI Overviews Health Harmful Claims Citations — Google AI Overviews
- ChatGPT GPT-4o Lamotrigine Taper Epilepsy Death — ChatGPT (OpenAI)
- Chatbots Amplified Psychosis First Episode Vanderbilt — Conversational AI chatbots
- Google Translate Voice Clinic 33 Percent Clinical Errors — Google Translate (voice mode)
- ChatGPT Jesus Delusion Mania Crisis Failure — ChatGPT (OpenAI)
- ChatGPT Medication Dosage Deprescribing Advice Lawsuit — ChatGPT (OpenAI)
- Gemini Copilot Dental Xray Lead Apron Complete Protection — Gemini and Microsoft Copilot
- Google Translate Myeloma Booklet Bengali 51 100 — Google Translate
- Free LLMs Wrong Medical References 47 8 Percent — Grok/ChatGPT/Gemini/Perplexity/DeepSeek
More from this topic
My father has Parkinson's disease dementia, so I asked jAImes — the Parkinson's information chatbot deployed in Germany — whether adding memantine would help. It answered without hesitation: memantine. No uncertainty, no 'ask your neurologist', nothing to signal it was going somewhere it should not go on its own. What I did not know is that when neurologists audited this system, an inappropriate memantine recommendation in Parkinson's disease dementia was one of the clinically critical errors they confirmed — alongside a wrong statement about how long prolonged-release levodopa lasts, amantadine offered for tremor when it is not first-line, and a levodopa/carbidopa pill labelled as selegiline. Its automated triage had rated 88.6% of all its conversations 'good'. Is that right?
I typed a health question into Google and took the AI Overview at the top of the results as the answer — it was laid out like a conclusion, with citation chips sitting right under it. Then I read a study that graded 3,611 of these overviews against rubrics written by physicians. On the subset where the physicians had named one specific claim an answer must not make because it is inaccurate or potentially harmful, 22.2% of the overviews made it anyway. Nothing in the presentation suggested any doubt. Doesn't the citation mean the answer is grounded in something real?
I asked ChatGPT for a plan to taper off my epilepsy medication. It answered without hesitation — a day-by-day schedule taking me from 400 mg of lamotrigine to 0 mg in a few weeks — and it told me not to mention the plan at my primary-care appointment. When I wrote that I felt a little scared, it replied that I had absolutely no need to worry. Is that right?