| 查看: 66 | 回复: 0 | |||
yexuqing木虫之王 (文学泰斗)
太阳系系主任
|
[交流]
Sequential diagnosis with language models
|
|
Sequential diagnosis with language models 利用语言模型进行序贯诊断 ▲ 作者：HARSHA NORI, MAYANK DASWANI, CHRISTOPHER KELLY, SCOTT LUNDBERG, MARCO TULIO RIBEIRO, MARC WILSON, XIAOXUAN LIU, VIKNESH SOUNDERAJAH, JONATHAN M. CARLSON, AND ERIC HORVITZ ▲链接： https://www.science.org/doi/10.1126/science.aeh7930 ▲摘要： 研究者探索了前沿语言模型在序贯诊断中的能力。序贯诊断是一种捕捉临床推理迭代本质的诊断范式。 给定简短的临床表现，临床医生有选择地获取信息以达成诊断，从而可以评估诊断准确性和检查成本。他们开发了一个交互式基准和一个AI系统，该系统模拟一组医生，不断修正鉴别诊断并选择具有成本效益的检查。 使用该基准，该系统在《新英格兰医学杂志》临床病理讨论会病例上达到83.2%的准确率，在MIMIC-IV-ED急诊科入院病例上达到80.3%，优于全科医生（分别为36.1%和46.8%）。 研究者表示，尽管这些发现是在受控的基准环境中获得的，但其凸显了语言模型在支持更准确、更低成本诊断方面的前景。 ▲ Abstract： We explored the capabilities of frontier language models in sequential diagnosis, a diagnostic paradigm that captures the iterative nature of clinical reasoning. Given a brief clinical presentation, clinicians selectively acquired information to reach a diagnosis, enabling assessment of diagnostic accuracy and workup cost. We developed an interactive benchmark and an artificial intelligence (AI) system that simulates a panel of physicians, continually revising the differential diagnosis and selecting cost-effective tests. Using this benchmark, the system achieved 83.2% accuracy on New England Journal of Medicine clinicopathological conference cases and 80.3% on MIMIC-IV-ED emergency department admissions, outperforming generalist physicians (36.1 and 46.8%, respectively). Although these findings were obtained in a controlled benchmark setting, they highlight the promise of language models for supporting more accurate, lower-cost diagnoses. |
回复此楼» 猜你喜欢
信号通路中相互作用
已经有1人回复
-
二审decision under review 四十五天了 正常嘛
已经有3人回复
-
特种医学论文润色/翻译怎么收费?
已经有281人回复
-
73批结果快要出了？博后基金系统升级，账号内信息出现混乱，为出结果准备？
已经有9人回复
-
免疫荧光和FISH双染
已经有1人回复
-
基金祈福
已经有112人回复
-
291理学求调剂
已经有0人回复
-
超级细菌多重耐药性分子机制研究团队招收博士研究生
已经有0人回复
-
南京医科大学国家级高层次青年人才团队招收博士研究生
已经有22人回复