NIH Awards $12.5M to Expand AI4AD Project for Alzheimer's Research
The National Institutes of Health has renewed funding for Artificial Intelligence for Alzheimer's Disease (AI4AD), awarding $12.5 million to advance the next phase of the initiative. The new grant brings total NIH investment in AI4AD to $30.7 million.
The University of Southern California leads the multi-institutional effort, which now involves 10 primary investigators and 23 co-investigators from 10 institutions. The project develops AI tools to identify biological causes of Alzheimer's and related dementias, predict disease progression, and guide treatment development.
Moving Beyond Broad Diagnoses
Paul M. Thompson, associate director of the USC Mark and Mary Stevens Neuroimaging and Informatics Institute, said the core challenge is that dementia manifests differently in each patient. "Each of us has a unique mix of degenerative processes going on in our brains," Thompson said. "We may have a mix of Alzheimer's pathology, vascular disease, and brain changes more typical of Parkinson's disease-all of them proceeding at different rates."
AI4AD2 will use machine learning to categorize patients based on patterns in brain scans, cognitive tests, neuropathology, and genetic data rather than grouping all patients under one diagnosis. Better disease subtypes improve clinical trials by matching treatments to patients most likely to benefit.
Genomic Language Models and Large-Scale Analysis
The project will develop "genomic language models" - AI systems that analyze DNA sequences instead of words to identify genetic combinations associated with Alzheimer's disease and disease progression. Researchers will train these models using data from over 58,000 participants across 57 cohorts.
Earlier AI4AD research demonstrated that machine learning models could identify Alzheimer's-related features on brain scans with over 90% accuracy after learning from 80,000 scans. The new phase will expand this approach across imaging, genomics, and biomarkers at larger scale.
Global Population Focus
A significant gap in biomedical research is the focus on people of European ancestry, which limits understanding of risk factors affecting other groups. AI4AD2 will adapt its tools for global and multi-ancestry cohorts, including datasets from African, Indian, Korean, and US populations.
The project will also identify how ancestry, social, and environmental factors affect Alzheimer's risk and progression to develop more accurate predictive models across populations.
Drug Discovery and Treatment Targets
The initiative will use an AI-based drug discovery system called PreSiBO to identify subtype-specific therapeutic targets. Researchers will evaluate whether existing drugs can be repurposed for patients with specific Alzheimer's-related biological profiles.
Arthur W. Toga, director of the Stevens INI, said the renewal enables work at previously unreachable scale. "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," Toga said.
Sharing Methods Across Research Community
AI4AD2 is structured as a collaborative effort with USC as the lead site. Partner institutions contribute expertise in neuroimaging, genomics, statistics, machine learning, cognitive science, and drug discovery.
The team will share software and tools through public repositories and scientific workshops so researchers worldwide can use and build on the project's methods.
For more information on AI for Healthcare and AI for Science & Research, explore available resources.
Your membership also unlocks:
