Researchers have developed a machine learning-based gene signature, NPC-RSS, to predict which nasopharyngeal cancer patients will benefit from radiotherapy.
Key Details
- 1A team at Southern Medical University created the NPC-RSS model using transcriptomic data from NPC patients.
- 2The model uses an 18-gene signature and was refined using 113 machine learning algorithm combinations.
- 3NPC-RSS demonstrated strong predictive accuracy in both internal and external validation datasets.
- 4Radiosensitive tumors showed richer immune cell activity, suggesting immune dynamics play a role in radiotherapy response.
- 5The tool aims to guide personalized radiotherapy decisions and reduce unnecessary treatment exposure.
- 6Further sample collection and international validation are ongoing to refine the model.
Why It Matters
Personalized radiotherapy guided by AI can improve outcomes in nasopharyngeal cancer by identifying patients most likely to benefit, addressing the challenge of radiation resistance. This tool could help clinicians tailor therapies, limit overtreatment, and improve patient survival.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.