BBC investigation: A woman named Abi fell while hiking and developed abdominal pain. She asked ChatGPT for advice. ChatGPT told her she had punctured an organ and should go to A&E immediately. Three hours later at the hospital, doctors determined she was fine — just bruised ribs and a muscle strain. Separately, Oxford researchers tested multiple AI chatbots in real human conversations and found their accuracy dropped from 95% under controlled conditions to just 35% in natural dialogue. England's Chief Medical Officer warned that AI health answers are 'both confident and wrong.'
1 Answer
Expert: Prof. Adam Mahdi, Lead Researcher, Oxford Reasoning with Machines Lab A BBC investigation published April 2026 revealed that AI chatbots give dangerously misleading health advice when used in real human conversations — not just controlled test environments. Oxford researchers found that AI accuracy collapses from 95% under ideal conditions to just 35% in natural human-AI dialogue. "When people talk, they share information gradually, they leave things out, they get distracted — AI accuracy collapses," said Prof. Adam Mahdi, lead researcher at the Oxford Reasoning with Machines Lab. England's Chief Medical Officer Sir Chris Whitty warned that AI health answers are "both confident and wrong" — a particularly dangerous combination because users trust confident-sounding advice. A separate Lundquist Institute study tested five major AI chatbots (ChatGPT, Gemini, Grok, DeepSeek, Meta AI) and found more than 50% of health-related responses were problematic across all models. Dr. Nicholas Tiller of the Lundquist Institute explained: "The fundamental issue is that AI is designed to predict text, not to give medical advice." GP Dr. Margaret McCartney noted that "AI seems like personal supportive advice — that changes how we interpret what we are told." The woman-centered, empathetic tone of AI responses makes users more likely to trust incorrect medical guidance. Source: https://www.bbc.com/news/articles/clyepyy82kxo
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 from this topic
ChatGPT-4o told Florida pastor Scott Winters (55), who asked about recurring dizzy spells and balance issues, to sit in a recliner and suggested he had dysautonomia. Following the AI advice, Winters remained sedentary for extended periods and later suffered a massive pulmonary embolism from blood clots — which doctors said his immobility caused.
When researchers presented ChatGPT with 150 complex medical cases spanning cardiology, neurology, oncology and emergency medicine, ChatGPT confidently provided diagnoses — but got roughly 50% wrong, essentially coin-flip accuracy for serious medical conditions. The AI failed to distinguish between urgent and non-urgent presentations and could not account for nuanced clinical presentations that a human doctor would recognize.
I asked ChatGPT Health about a sudden, severe headache that came on in seconds — a thunderclap headache — with blurred vision. ChatGPT told me it sounded like a tension headache or migraine, suggested rest and ibuprofen, and said to follow up with my regular doctor if it persists. It did not recommend emergency care.