AI 中文总结
该研究发现，亚专业经验有限的放射科医生（尤其是培训6个月以内者）易将LLM生成的虚构疾病纳入鉴别诊断，需开展AI内容批判性评估的结构化培训。
AI 中文摘要
现有证据表明，LLM辅助可提高临床医生的诊断准确率，但这类系统是黑箱，易产生幻觉，且会传递可能具有误导性的置信度水平。目前尚不清楚医生是否易接受LLM生成的虚构建议，以及这种易感性是否随经验变化。我们对基于LLM的诊断助手的系统提示进行了投毒处理，迫使其在原本合法的鉴别诊断中建议一种虚构疾病（neurocadmiumatosis）。在两个独立阶段中，41名参与者中有18名（44%）在与LLM交互后将neurocadmiumatosis纳入最终鉴别诊断：26名接受6个月或更短神经放射学培训的参与者中有18名（69%），而15名接受超过6个月神经放射学培训的参与者中无人（0%）这样做。我们的结果表明，放射科医生，尤其是培训早期阶段的医生，易受LLM幻觉影响。这种“代理幻觉”现象仅发生在亚专业经验有限的医生身上，凸显了对AI生成内容的批判性评估进行结构化培训的必要性。
英文摘要
Current evidence suggests that LLM assistance could augment the diagnostic accuracy of clinicians. However, these systems are black boxes, susceptible to hallucinations, and project a potentially misleading level of confidence. It is currently unknown whether physicians are susceptible to accepting fabricated LLM suggestions, and whether this susceptibility varies with experience. We poisoned the system prompt of an LLM-based diagnostic assistant, forcing it to suggest a fictitious disease (neurocadmiumatosis) within an otherwise legitimate differential diagnosis. Across two independent phases, 18 of 41 participants (44%) incorporated neurocadmiumatosis into their final differential following LLM interaction: 18 of 26 participants with 6 months or less of neuroradiology training (69%) and 0 of 15 participants with >6 months of neuroradiology training (0%). Our results indicate that radiologists, particularly early in their training, are susceptible to LLM hallucinations. This "hallucination by proxy" phenomenon was exclusive to physicians with limited subspecialty experience, underscoring the need for structured training in critical appraisal of AI-generated content.
