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 medical lie enters the system, can AI pass it on as if it were true?
Analyzing more than a million prompts across nine leading language models, the researchers found that these systems can repeat false medical claims when they appear in realistic hospital notes or social-media health discussions.
The findings, published in The Lancet Digital Health, suggest that current safeguards do not reliably distinguish fact from fabrication once a claim is wrapped in familiar clinical or social-media language. The paper is titled “Mapping LLM Susceptibility to Medical Misinformation Across Clinical Notes and Social Media.”
