Can medical AI lie? Large study maps how LLMs handle health misinformation
medicalxpress - Medical artificial intelligence (AI) is often described as a way to make patient care safer by helping clinicians manage information. A new study by the Icahn School of Medicine at Mount Sinai and collaborators confronts a critical vulnerability: when a m…
AI Summary: A broad analysis — including Mount Sinai research — shows large language models and medical AI systems can propagate false or misleading health claims when presented in realistic clinical language. Findings expose safety gaps, underline risks of unchecked deployment, and call for tighter guardrails, validation and clinician oversight before clinical use.
Warning: Undefined variable $thumbnail in /home3/thegood9/public_html/website_70aad9ea/cluster.php on line 61
Related Stories
Warning: Undefined variable $top_stories in /home3/thegood9/public_html/website_70aad9ea/cluster.php on line 128
Independent study flags safety issues in ChatGPT Health triage / 3 months
DeepRare AI beats clinicians at diagnosing rare diseases / 3 months
Alabama's robot maternity care plan sparks physician pushback / 3 months
Researchers report extracorporeal cross‑circulation using genetically modified pig livers / 3 months
TEFCA hits 500 million records exchanged milestone / 3 months
Epic Systems, providers sue Health Gorilla over data misuse / 4 months
OpenAI debuts ChatGPT Health for integrated wellness data / 4 months
StackHealth RSS
You can now follow topics by RSS - browse the complete list of topics, people, and organizations. Or, try Supplements, Medicare Advantage (not listed), Animal Health, Food Safety and look for the RSS link.
StackHealth Time Machine