The National Institutes of Health (NIH) has granted $12.6 million to support the next phase of the Artificial Intelligence for Alzheimer’s Disease (AI4AD) initiative, now called AI4AD2. This funding brings the total NIH investment to $30.7 million and aims to develop more accurate AI tools for identifying disease subtypes, predicting progression, and accelerating personalized treatments through integrated genomic, imaging, and clinical data.
Glimpse:
Launched in 2020, the original AI4AD project used machine learning to detect Alzheimer’s related changes in brain scans with over 90% accuracy. The new AI4AD2 phase, led by researchers at the USC Mark and Mary Stevens Neuroimaging and Informatics Institute, will expand this work by analyzing whole genome sequencing from over 58,000 individuals, incorporating diverse global datasets (including Indian cohorts), and building genomic language models to uncover hidden biological pathways and treatment targets.
The National Institutes of Health has provided fresh funding of $12.6 million to propel the Artificial Intelligence for Alzheimer’s Disease initiative into its next stage, known as AI4AD2. This latest award raises the overall NIH support for the project to $30.7 million since its launch in 2020. The multi institutional consortium seeks to harness advanced artificial intelligence techniques to decode the complex biology behind Alzheimer’s and related dementias, moving away from broad disease categories toward precise, biologically defined subtypes that could transform how treatments are developed and tested.
At the heart of AI4AD2 is the integration of massive and varied datasets, including whole genome sequencing, advanced neuroimaging, and detailed cognitive assessments. Researchers plan to develop “genomic language models” that apply AI methods similar to natural language processing to examine DNA sequences from more than 58,000 people. By connecting these genetic insights with observable changes in brain structure and behavior, the team hopes to reveal new molecular pathways involved in neurodegeneration and identify opportunities for targeted therapies, including drug repurposing through systems like PreSiBO.
A key emphasis of the renewed project is improving inclusivity and reliability of AI models across different populations. To address biases in existing data that often favor individuals of European ancestry, AI4AD2 will incorporate cohorts from African, Indian, Korean, and U.S. groups. This diversity focused approach is expected to make predictive tools more accurate and equitable, ultimately supporting better clinical trial design and therapies tailored to individual patient profiles.
Led by experts at the USC Mark and Mary Stevens Neuroimaging and Informatics Institute, the initiative promotes open collaboration by planning to share tools and findings widely with the global research community. The project represents a significant step toward using AI not just for detection but for deeper biological understanding that can accelerate the discovery of effective, personalized interventions for Alzheimer’s disease.
“Artificial intelligence is only as powerful as the data and scientific questions behind it. This renewal allows our team and collaborators to work at a scale that was previously out of reach, integrating imaging, genomics, and other biomarkers to better capture the complexity of Alzheimer's disease. It represents an important step toward more precise, inclusive, and actionable brain health research.”
By
HB Team
Related News
