|
|
|
|
|
Weekly Update
|
April 5, 2025 |
|
|
|
Can open-source LLMs like the Llama series diagnose complex cases as well as a proprietary cloud-based model like ChatGPT? In this week’s JAMA+ AI Conversations, JAMA+ AI Editor in Chief Roy Perlis, MD, talked to two researchers who found that open-source models could be viable alternatives with advantages in accessibility, customization, and data privacy.
Also this week:
- A JAMA Viewpoint discussed preparing medical students to succeed in AI-integrated medical schools.
- An Editor’s Note from JAMA Health Forum invited submissions of research on AI applications in health care delivery, population health, and health policy.
|
|
Medical News & Perspectives
JAMA
Can Open-Source AI Models Diagnose Complex Cases as Well as GPT-4?
Roy Perlis, MD, MSc; Nora Collins
VIEWPOINT
JAMA
Building the AI-Enabled Medical School of the Future
Marc D. Succi, MD; Bernard S. Chang, MD; Arya S. Rao, BA
RESEARCH LETTER
JAMA Health Forum
Comparison of Frontier Open-Source and Proprietary Large Language Models for Complex Diagnoses
Thomas A. Buckley, BS; Byron Crowe, MD; Raja-Elie E. Abdulnour, MD; et al
EDITOR'S NOTE
JAMA Health Forum
Prospects for Artificial Intelligence in Health Policy and Practice
John Z. Ayanian, MD, MPP; Zirui Song, MD, PhD
AUDIO
 Can Open-Source LLMs Compete With Proprietary Ones for Complex Diagnoses?
|
|
|
|
|
|
|
Thank you for subscribing to JAMA Network email alerts. This message was sent to buiduytam1@gmail.com by updates@jamanetwork.org.
To sign up for additional alerts, or to unsubscribe, click here.
To ensure you always receive JAMA Network emails, add the email address updates@jamanetwork.org to your address book.
To unsubscribe by mail, contact:
JAMA Network
AMA Plaza
330 N Wabash Ave
Chicago, IL 60611
Or call (800) 621-8335.
|
      |
|
©2025 American Medical Association. All rights reserved.
|
|
|
|
|
