Boston University scientists developed an AI model that predicts Alzheimer's-related protein levels using brain imaging and clinical data.
Key Details
- 1AI tool predicts presence of amyloid beta and tau proteins linked to Alzheimer's disease.
- 2Model incorporates brain scans, cognitive scores, genetics, and health history from 12,185 participants across seven cohorts.
- 3Tool provides location-specific brain information, unlike most blood tests.
- 4Successfully validated on a separate international cohort, showing robust predictive performance.
- 5Aims to enable earlier, cheaper, and more accessible Alzheimer's detection and staging.
- 6Published in Nature Communications on August 11, 2025.
Why It Matters
Accurate, cost-effective early detection of Alzheimer's using non-invasive imaging and AI could transform patient care and expedite selection for clinical trials. This approach highlights the expanding role of imaging AI in neurological disease diagnosis and management.
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.