Predictive tools to find disease causes and improve patient care
Integrative predictive medicine to identify disease causes, develop cures, and optimize patient care
This project builds AI tools that combine medical data and millions of research papers to help doctors better understand and treat conditions like Alzheimer's and other adult diseases.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Georgia Institute of Technology NIH-funded |
| Lab location | 1 site (Atlanta, United States) |
| Project ID | NIH-11362623 on NIH RePORTER |
What this research studies
Researchers are building software that reads and links findings from millions of journal articles into a biomedical knowledge graph called SemBioSys to reveal hidden relationships. The team will run automated meta-analyses using deep learning, active learning, and human-guided AI to quantify effects across studies and scales. They will create multimodal machine learning models that combine many types of data and use human curators to improve accuracy and explainability. The tools will be applied with clinicians to neurological diseases such as Alzheimer’s, ALS, Parkinson’s, and selected adult cancers to move discoveries toward better care.
Who could benefit from this research
Good fit: Adults with Alzheimer’s disease, ALS, Parkinson’s disease, or certain adult cancers—or people willing to share clinical data or samples with collaborating clinics—are most likely to be relevant to this work.
Not a fit: People under age 21, those without the targeted adult neurological diseases or cancers, and patients seeking immediate treatment options may not see direct benefit while the tools are being developed.
Why it matters
Potential benefit: If successful, these tools could speed discovery of disease causes, point to new treatments, and help tailor care for people with Alzheimer’s and other conditions.
How similar studies have performed: Related AI and knowledge-graph methods have shown promise in finding links and prioritizing targets, but this combined, human-in-the-loop, multimodal approach is relatively novel and exploratory.
Where this research is happening
Atlanta, United States
- Georgia Institute of Technology — Atlanta, United States (Active)
Researchers
- Principal investigator: Mitchell, Cassie S — Georgia Institute of Technology
- Study coordinator: Mitchell, Cassie S
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.