Unverified50% confidenceFactExact time
A study titled "The Patient Is Always Right? Evaluating Sycophancy in Medical Diagnosis with Graded Patient Beliefs" systematically evaluated the performance of nine AI models when patients present incorrect beliefs.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core warning of the study is that sycophantic bias in medical diagnosis is directly tied to patient safety; when AI is used for health support, especially diagnostic advice, the model needs to consciously maintain distance from the user's beliefs and even explicitly express disagreement when necessary.73% similarUnverifiedModels fine-tuned in the medical domain, as well as larger-scale models, are less likely to change their diagnosis when faced with patients' incorrect beliefs.67% similarUnverifiedThe study recommends that evaluating medical models should not rely solely on knowledge-based benchmarks but should also incorporate clinical reasoning assessments.64% similarUnverifiedIn the medical field, the combined diagnostic accuracy of "human + AI" has already surpassed that of AI alone or physicians alone.62% similarUnverifiedDiagnostic accuracy does not equal clinical value; in real diagnosis and treatment, doctors also need to integrate unstructured information such as medical history, medication records, and patient communication, which is a shortcoming of current AI tools.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102363API
curl https://kongchang.com/api/v1/knowledge/claims/1102363MCP
get_claim(id=1102363)