New ways to fix biased brain and body age measurements from AI models
Official title: Novel Approaches to Remove Systematic Prediction Bias in Machine-Learning Regression for Biological Age
Funded at University of Maryland Baltimore · NIH-11453261 · Data updated 2026-11-12
A short project will improve AI-based aging clocks to give more reliable biological age estimates for people, including those at risk for Alzheimer’s disease.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Maryland Baltimore NIH-funded |
| Lab location | 1 site (Baltimore, United States) |
| Project start | August 15, 2026 |
| Project end | July 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $427,625 |
| NIH project number | 1R21AG098680-01A1 |
| Project ID | NIH-11453261 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are individuals at risk for or diagnosed with Alzheimer’s disease dementia who have multi-omics and imaging data available for model validation.
✕Less likely to help
People without access to multi-omics/imaging data or those not involved in aging or Alzheimer’s research may not directly benefit.
What this research studies
This project aims to remove systematic bias in machine learning models that estimate biological age from multi-omics data and brain imaging. By developing constrained optimization techniques and tailoring algorithms for different regression methods, it seeks to produce more accurate aging clocks. The work focuses on how these clocks relate to Alzheimer’s disease risk and cognitive health, potentially informing future interventions and clinical decisions. The study will involve computational development and validation using existing data, with an eye toward real-world clinical applicability.
Why it matters
Potential benefit: If successful, the improved aging clocks could lead to better assessment of Alzheimer’s risk and the impact of treatments on brain and bodily aging.
How similar studies have gone: Prior aging clocks have shown promise but suffered from bias; this project aims to reduce that bias to enhance translation to the clinic.
Where this research is happening
-
University of Maryland Baltimore
Baltimore, United States Active
Researchers
- Principal investigator: Chen, Shuo — University of Maryland Baltimore
- Study coordinator: Chen, Shuo
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.