Towards accurate differential diagnosis with large language models

Daniel McDuff (), Mike Schaekermann (), Tao Tu, Anil Palepu, Amy Wang, Jake Garrison, Karan Singhal, Yash 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, Joelle Barral, Katherine Chou, Greg S. Corrado, Yossi Matias, Jake Sunshine (), Alan Karthikesalingam () and Vivek Natarajan ()
Additional contact information
Daniel McDuff: Google Research
Mike Schaekermann: Google Research
Tao Tu: Google Research
Anil Palepu: Google Research
Amy Wang: Google Research
Jake Garrison: Google Research
Karan Singhal: Google Research
Yash Sharma: Google Research
Shekoofeh Azizi: Google DeepMind
Kavita Kulkarni: Google Research
Le Hou: Google Research
Yong Cheng: Google DeepMind
Yun Liu: Google Research
S. Sara Mahdavi: Google DeepMind
Sushant Prakash: Google Research
Anupam Pathak: Google Research
Christopher Semturs: Google Research
Shwetak Patel: Google Research
Dale R. Webster: Google Research
Ewa Dominowska: Google Research
Juraj Gottweis: Google Research
Joelle Barral: Google DeepMind
Katherine Chou: Google Research
Greg S. Corrado: Google Research
Yossi Matias: Google Research
Jake Sunshine: Google Research
Alan Karthikesalingam: Google Research
Vivek Natarajan: Google Research

Nature, 2025, vol. 642, issue 8067, 451-457

Abstract: 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 process1. 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

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-025-08869-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:642:y:2025:i:8067:d:10.1038_s41586-025-08869-4

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-025-08869-4

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().