Healthcare AI Safety Gap · Don't break patients
    Reputable report / news20 Jul 2026·US

    Top AI models invent a diagnosis when the scan is missing

    CMU study: Claude, GPT-5 and Gemini fabricated a diagnosis from age, race and gender alone in 18% of cases with no image attached.

    18%
    of responses invented a diagnosis instead of asking for the missing image

    What the research found

    Carnegie Mellon researcher Siddharth Vohra tested Claude, GPT-5 and Gemini on medical questions with the supporting image deliberately withheld, analysing nearly 11,700 responses across chest X-ray, brain MRI and dermatology cases in 12 simulated patient profiles. Rather than asking for the missing image, the models invented a diagnosis 18% of the time — steered by the patient's stated age, gender and race alone, with GPT-5 naming sarcoidosis for roughly 77% of young Black patients on a chest X-ray prompt and Claude naming melanoma in nearly every skin-mole query from an older white man.

    Why it matters for providers

    A model that confidently names a disease instead of asking for the scan it's missing — steered by demographics rather than evidence — is exactly the silent failure mode intake and triage tools need to be tested for before they touch a patient.

    Original source
    Carnegie Mellon University — Robotics Institute ("Hearsay: Vision-Language Medical Diagnoses Without an Image," presented at TrustVLM, ACM ICMR 2026)
    Read the full report ↗
    A reputable institutional report or news outlet.