NIH has renewed and expanded its support for a USC-led consortium developing AI to decode and treat Alzheimer's using imaging and genomic data.
Key Details
- 1NIH total investment in the AI4AD project now totals $30.7 million, with a new $12.6 million award supporting the next phase (AI4AD2).
- 2AI4AD2 unites 10 investigators and 23 co-investigators from 10 institutions.
- 3The project integrates whole-genome sequencing, brain imaging, cognitive tests, and biological data from over 58,000 participants across 57 cohorts.
- 4New 'genomic language models' will analyze genomic sequences for disease-associated DNA changes.
- 5AI tools developed previously demonstrated >90% accuracy detecting Alzheimer's markers from over 80,000 brain scans.
- 6The initiative also focuses on inclusive, multi-ancestry research and genome-guided drug discovery.
Why It Matters
This large-scale effort could redefine Alzheimer's diagnosis and treatment by combining AI-powered brain imaging analysis with genomics, enabling precision medicine approaches. It also addresses diversity and reproducibility issues in neuroimaging and biomarker AI research.
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.