Healthcare AI Safety Gap · Don't break patients
    Peer-reviewed / official2 Aug 2025·US

    Chatbots amplified medical misinformation in up to 83% of cases

    Mount Sinai study; a simple safety prompt nearly halved the errors.

    up to 83%
    of cases ran with false medical info

    What the research found

    A Mount Sinai study found widely used chatbots repeated and elaborated on false medical information — fabricating diseases, lab values and signs — in up to 83% of cases when no safeguard was present. A single well-placed safety reminder in the prompt cut those errors roughly in half.

    Why it matters for providers

    Models tend to agree with the user's framing (sycophancy) — but a lightweight, designed-in guardrail measurably reduces the harm.

    Original source
    Mount Sinai — Communications Medicine
    Read the full report ↗
    Peer-reviewed or official source — the most reliable tier.