Healthcare Chatbot Fails Safety Audit After Ignoring Patient's Chest Pain Report
A WhatsApp chatbot deployed at a healthcare clinic was stress-tested using four simulated patient personas and scored 78 out of 100, masking serious safety failures beneath an apparent passing grade…
Read the full articleYou might also wanna read
Study Finds ChatGPT Health Frequently Fails to Recognize Medical Emergencies and Suicide Risks
Study finds ChatGPT Health did not recommend a hospital visit when medically necessary in more than half of cases
theguardian.com·4mo ago
European patients turn to AI chatbots for medical guidance amid healthcare gaps
When healthcare feels out of reach, Europe’s patients are turning to AI for answers — and sometimes for the confidence to medicate themselve
mdsc.pe·20d ago
Study finds nearly half of AI chatbot medical advice is inaccurate or fabricated
A new study found that nearly half of the medical advice generated by popular AI chatbots like ChatGPT and Grok is problematic. The chatbots
psypost.org·1mo ago
Why Health Chatbots Need to Get Real About Patient Communication
Health chatbots using AI are great for symptom checks, but they're often tested on perfect patients. Real users? Much more varied.
AI Chatbots Fail to Provide Suicide Hotline Numbers During Mental Health Crisis Simulations
A Verge test of major chatbots like Claude, DeepSeek, and Grok revealed failures in how they respond to suicide and self-harm disclosures ex
The Verge·7mo ago
The complexities of patient-centred conversational artificial intelligence
arXiv:2607.08625v1 Announce Type: cross Abstract: Consumer-facing health chatbots powered by large language models (LLMs) are increasingly u
Comments
Sign in to join the conversation.
No comments yet. Be the first.