Brazilian and French researchers have developed an imaging-based AI tool to predict how multiple sclerosis patients will respond to natalizumab treatment.
Key Details
- 1Combines high-content cell imaging and machine learning to analyze patient blood samples before natalizumab therapy.
- 2Study used over 400 cell morphological features, with 130 key characteristics for prediction.
- 3Tool achieved 92% accuracy in discovery and 88% in validation cohorts for predicting drug response.
- 4Non-responders showed distinct actin remodeling and cell morphology (more elongated CD8+ T cells).
- 5Findings published in Nature Communications, suggesting potential for broader disease and drug applications.
Why It Matters
This research demonstrates how imaging AI and advanced cell analysis can enable more personalized and effective treatment strategies in neurology. Such approaches could optimize resource use, reduce side effects, and accelerate precision medicine adoption in radiology and adjacent fields.
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.