《科学》 第392卷 第6797期 · 2026年4月30日 · 中文解读
AI能像医生一样推理——接下来会发生什么?
AI can reason like a physician—what comes next? · Ashley M. Hopkins and Erik Cornelisse
约 7 分钟Perspectives在小程序里点播,20 到 60 分钟做好
这篇讲什么
本文探讨了大型语言模型在临床诊断推理方面达到或超过医生水平的最新研究,并讨论了安全整合这些工具到临床工作流程中的挑战。
原文开头
physician —what comes next? Text-based AI can think like a physician; the challenge is achieving safe clinical implementation Ashley M. Hopkins and Erik Cornelisse L arge language models (LLMs) are artificial intelligence (AI) algorithms that are trained on vast amounts of data to learn patterns that enable them to generate human-like responses. Reasoning models are LLMs with the added capability of working through problems step by step before responding, thus mirroring structured thinking. Such AI systems have performed well in assessing medical knowledge, but whether they can match phy- sician-level clinical reasoning on authentic diagnostic tasks remains largely unknown. On page 524 of this issue, Brodeur et al. …
摘自《科学》(Science)第392卷 第6797期 · 2026年4月30日,Ashley M. Hopkins and Erik Cornelisse。仅引用开头一小段供了解文章,版权归原刊所有,全文请阅读原刊。

微信扫码,在小程序里听完整版
不用登录先听一篇 · 或在微信搜索小程序 晨间信号