一种用于加速罕见病诊断的专用推理大语言模型：随机AI辅助医生试验
A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
AI总结：
提出开源推理大模型RaDaR（32B参数），通过增强推理训练和合成数据，在罕见病诊断中超越DeepSeek-R1等模型，随机试验显示其辅助使医生诊断准确率提升21.44个百分点。
摘要：
罕见病影响着全球数百万人，但由于缺乏专业临床专业知识，及时诊断仍然是一个主要的公共卫生挑战。虽然大语言模型（LLMs）在支持罕见病诊断方面显示出潜力，但当前模型受到临床可部署性不足、临床证据有限以及训练数据稀缺的限制。本文提出RaDaR（Rare Disease navigatoR），一个开源的、紧凑的推理大语言模型（32B参数），用于罕见病诊断。RaDaR使用49,170个公开可用的自由文本病例和104,666个合成病例进行训练，并采用了推理增强训练。在公开基准测试和四个外部验证中心中，RaDaR在评估的开源模型中表现最强，包括671B的DeepSeek-R1。在一个回顾性队列中，RaDaR在61.06%的病例中优先于记录的临床怀疑给出最终诊断，对应的潜在提前时间为1.87个月，占中心内间隔的50.18%。在一项随机医生辅助试验中，与仅使用互联网搜索相比，RaDaR辅助将医生的罕见病诊断准确率提高了21.44个百分点。合成数据消融实验表明，表型锚定的叙述为长尾罕见病提供了有用的训练信号，在测试数据范围内呈现单调扩展趋势。综上所述，RaDaR及其开发和验证框架提供了一个可部署的罕见病推理模型，以及一个在数据稀缺条件下可复现的诊断AI开发框架。
英文摘要：
Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clinical expertise. While large language models (LLMs) show promise to support rare disease diagnosis, current models are constrained by insufficient clinical deployability, limited clinically grounded evidence, and scarcity of training data. Here we present RaDaR (Rare Disease navigatoR), an open-source, compact reasoning LLM (32B parameters) for rare disease diagnosis. RaDaR was trained with 49,170 publicly available free-text cases and 104,666 synthetic cases with reasoning-enhanced training. RaDaR showed the strongest performance among evaluated open-source models, including the 671B DeepSeek-R1, across public benchmarks and four external validation centers. In a retrospective cohort, RaDaR prioritized the final diagnosis before documented clinical suspicion in 61.06 percent of cases, corresponding to a potential lead time of 1.87 months and 50.18 percent of the within-center interval. In a randomized physician-assistance trial, RaDaR assistance improved physicians' rare-disease diagnostic accuracy by 21.44 percentage points compared with internet search alone. Synthetic-data ablations suggested that phenotype-anchored narratives provide useful training signal for long-tail rare diseases, with a monotonic scaling trend within the tested data range. Together, RaDaR and its development and validation framework provide a deployable rare-disease reasoning model and a reproducible development framework for diagnostic AI under data scarcity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
