AI that uses social and health information to improve heart disease risk predictions
Official title: AI2Equity: AI Integrating Social Determinants of Health to Advance Health Equity in Cardiovascular Risk Prediction
Funded at Univ of Massachusetts Med Sch Worcester · NIH-11323993 · Data updated 2026-11-12
This project creates AI tools that combine medical records and social factors to give fairer, more accurate heart disease risk predictions for people from racial, ethnic, and low-income backgrounds.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Univ of Massachusetts Med Sch Worcester NIH-funded |
| Lab location | 1 site (Worcester, United States) |
| Project start | April 20, 2024 |
| Project end | March 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $691,991 |
| NIH project number | 5R01HL171599-03 |
| Project ID | NIH-11323993 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are adults receiving care at the participating community health centers or the two academic hospitals, especially people from racial or ethnic minority groups or lower-income communities.
✕Less likely to help
People without linked social or clinical data in the participating sites, or whose risk comes from factors not captured by the model, may not benefit directly.
What this research studies
If I were a patient at one of the participating clinics or hospitals, researchers would use my medical history together with social information like housing, income, and neighborhood to build a risk profile. They will apply advanced machine learning to learn how clinical and social factors interact and to highlight which risks matter most. The team aims to make the AI fair across racial and socioeconomic groups and explainable so clinicians and community partners can act on results. They will test the model across data from a national community health center network and two academic hospitals to try to make it useful for different populations.
Why it matters
Potential benefit: If successful, this could help identify people at higher risk of heart disease earlier and guide medical and social interventions to reduce inequities.
How similar studies have gone: Previous AI models have improved cardiovascular risk prediction but often missed social determinants and fairness, so this builds on promising methods while explicitly addressing those gaps.
Where this research is happening
-
Univ of Massachusetts Med Sch Worcester
Worcester, United States Active
Researchers
- Principal investigator: Liu, Feifan — Univ of Massachusetts Med Sch Worcester
- Study coordinator: Liu, Feifan
Related research
Other NIH-funded projects on the same topics.
-
Cardiovascular risk planning and reduction for men with prostate cancer
A program to better predict and reduce heart disease risk in men treated for prostate cancer, especially older patients.
-
Traumatic Stress, Epigenetic Aging, and Heart Risk in Veterans
A large study using Veterans Affairs data to see if traumatic stress and faster biological aging relate to higher risk of stroke and heart disease.
-
Lifestyle plan to protect muscle and heart health for adults with obesity using GLP-1 medications
A real-world trial tests a combined nutrition and resistance-training program versus standard care for adults starting GLP-1 weight loss drugs to preserve lean mass and cardiovascular health.
-
Role of the body's natural cannabis-like system in diabetes progression and heart risk
This grant studies how the body's endocannabinoid system affects the progression from obesity to diabetes and the associated risk for cardiovascular disease in adults.
-
Community and Peer Support for Reducing Cardiovascular Risk
Aims to understand how community and peer programs can help people lower cardiovascular risk, by analyzing existing programs and how their implementation and social support influence outcomes.
-
CardioPredict ML: A smarter way to gauge heart risk before pregnancy
A machine learning tool helps identify women at risk for pregnancy-related heart problems before conception, using health records and prior pregnancy data.
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.