| |
|
|
|
One-Year Anniversary
|
December 13, 2025 |
|
|
|
To mark the one-year anniversary of JAMA+ AI, we’ve invited the JAMA+ AI editors to share articles that they found memorable this year.
This week, JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, and JAMA Oncology AI editor Yu Shyr, PhD, share the articles they deemed transformative.
|
|
 Yulin Hswen, ScD, MPH, is the JAMA+ AI Associate Editor and an Associate Professor in the Department of Epidemiology and Biostatistics at the University of California, San Francisco and the Computational Precision Health Program at the University of California, Berkeley. Her research integrates artificial intelligence, machine learning, and social media analytics to analyze how narratives gain traction in digital spaces, influence population-wide perceptions, and impact real-world decisions.
|
|
|
Dr Hswen’s selection is “Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks: A MELD Study,” published in JAMA Neurology on February 24, 2025.
"This study focuses on focal cortical dysplasia, which is small brain malformations that often go undetected on MRI scans.
What makes this work notable is its use of a graph neural network (GNN), an AI model that analyzes how neighboring brain regions connect and interact along the cortical surface. Using MRI data from hundreds of patients, the GNN identified 64% of lesions previously missed by expert radiologists, while maintaining a high positive predictive value.
This approach is especially exciting because the AI model leverages neighbor-connected brain features to uncover subtle abnormalities that are difficult for the human eye to detect. The work demonstrates how AI can augment neuroradiology, improving the detection of hidden lesions and paving the way for earlier diagnosis and more effective surgical treatment for epilepsy."
|
| Read the Article |
|
|
|
|
 Yu Shyr, PhD, is the Chair of the Department of Biostatistics at Vanderbilt University School of Medicine and the Director of the Vanderbilt Center for Quantitative Sciences. He is a leading expert in clinical trial methodology, high-dimensional data analysis, and modern statistical and machine learning approaches for large-scale biomedical data. Dr Shyr’s research spans the development of advanced statistical machine learning and bioinformatic methods as well as extensive collaborative work in cancer biology, cancer epidemiology, precision medicine, and clinical research.
|
|
|
Dr Shyr’s selection is “Deep Learning Model for Predicting Immunotherapy Response in Advanced Non−Small Cell Lung Cancer,” published in JAMA Oncology on December 26, 2024.
"This multicenter cohort study demonstrates that a supervised deep learning model (Deep-IO), derived from routine hematoxylin and eosin whole-slide images, can directly predict the response to immune checkpoint inhibitor monotherapy in advanced non–small cell lung cancer.
The Deep-IO score showed significant associations with objective response rate, progression-free survival, and overall survival in a large external validation cohort drawn from three European centers. When combined with the PD-L1 tumor proportion score, the integrated model further improved classification accuracy, achieving higher AUC and stronger responder stratification than either biomarker alone.
This work highlights a practical path toward AI-enabled, pathology-based immunotherapy decision-making by leveraging digital histology data already produced in standard clinical workflows."
|
| Read the Article |
|
|
|
|
If you enjoy JAMA+ AI, we invite you to forward this email to a colleague and spread the word.
|
|
|
|
|
|
Thank you for subscribing to JAMA Network email alerts. This message was sent to buiduytam1@gmail.com by updates@email.jamanetwork.com.
To update your contact information, change your email preferences, or unsubscribe, click here.
To ensure you always receive JAMA Network emails, add the email address updates@email.jamanetwork.com 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.
|
|
 |
|
Advertisement
|
|
|
