8月10日
11:06
11:06官方账号arXiv cs.AI@Valentin Liévin, Samuel Schmidgall, Tim Strother, Alex Bijamov, Akshay Goel, Anil Palepu, Chunjong Park, Vahid Balazadeh, Min Woo Sun, Marius Guerard, Justin Chen, Dave Steiner, Vikram Dhillon, Ibrahim Azar, Akhil Mehta, Nicholas Spetsieris, Shilpan Shah, Maen Abdelrahim, Amit Dahiya, Yun Liu, Katherine Chou, Yossi Matias, Avinatan Hassidim, Dale R. Webster, Quoc V. Le, Raia Hadsell, Joelle Barral, Carey Radebaugh, Aleksandra Faust, Shekoofeh Azizi, Mike Schaekermann, Po-Hsuan Cameron Chen, Tao Tu, David Racz, Lin Yang
ResidencyRL通过强化学习在模拟临床环境中训练医疗AI,每个轨迹最多包含60轮对话和8次工具调用。在对抗条件下,该智能体的诊断准确率达到88.0%,比基础模型提升7.0%。漏诊红旗率降低31%,表明能有效减少过早闭合。盲审临床专家在87.6%的对比中更偏好训练后的智能体。在AMIE多访基准的六个临床轴上均超过基础模型。
推荐理由:医疗AI训练新方法ResidencyRL,模拟临床对话,诊断准确率涨7%,漏诊率降31%,专家更看好。