Towards accurate differential diagnosis with large language models

作者：Daniel McDuff, Mike Schaekermann, Tao Tu, Anil Palepu, Amy Wang, Jake Garrison, K. K. Singhal, Yash Pal Sharma, Shekoofeh Azizi, Kavita Kulkarni, Le Hou, Yong Cheng, Yun Liu, S. Sara Mahdavi, Sushant Prakash, Anupam Pathak, Christopher Semturs, Shwetak Patel, Dale R. Webster, Ewa Dominowska, Juraj Gottweis, Joëlle Barral, Katherine Chou, Greg S. Corrado, Yossi Matias, Jacob E. Sunshine, Alan Karthikesalingam, Vivek Natarajan · 发表于：Nature · 年份：2025 · DOI：10.1038/s41586-025-08869-4 · 被引用次数：228 · 研究领域：Artificial Intelligence in Healthcare and Education、Machine Learning in Healthcare、Topic Modeling

Abstract A comprehensive differential diagnosis is a cornerstone of medical care that is often reached through an iterative process of interpretation that combines clinical history, physical examination, investigations and procedures. Interactive interfaces powered by large language models present new opportunities to assist and automate aspects of this process 1 . Here we introduce the Articulate Medical Intelligence Explorer (AMIE), a large language model that is optimized for diagnostic reasoning, and evaluate its ability to generate a differential diagnosis alone or as an aid to clinicians. Twenty clinicians evaluated 302 challenging, real-world medical cases sourced from published case reports. Each case report was read by two clinicians, who were randomized to one of two assistive conditions: assistance from search engines and standard medical resources; or assistance from AMIE in addition to these tools. All clinicians provided a baseline, unassisted differential diagnosis prior to using the respective assistive tools. AMIE exhibited standalone performance that exceeded that of unassisted clinicians (top-10 accuracy 59.1% versus 33.6%, P = 0.04). Comparing the two assisted study arms, the differential diagnosis quality score was higher for clinicians assisted by AMIE (top-10 accuracy 51.7%) compared with clinicians without its assistance (36.1%; McNemar’s test: 45.7, P < 0.01) and clinicians with search (44.4%; McNemar’s test: 4.75, P = 0.03). Further, clinicians assis...