Personalized diabetes and heart-disease treatment plans using real-world health data and AI
Statistical and Machine Learning Methods to Improve Dynamic Treatment Regimens Estimation Using Real World Data.
Researchers are combining medical records and smart computer methods to help doctors choose step-by-step treatments for people with type 2 diabetes and atherosclerotic heart disease.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Michigan at Ann Arbor NIH-funded |
| Lab location | 1 site (Ann Arbor, United States) |
| Project ID | NIH-11321551 on NIH RePORTER |
What this research studies
This project uses real-world data such as electronic health records, registries, and survey data together with results from clinical trials to learn treatment rules that change over time. The team will apply statistical and machine-learning methods to pick patient features that matter for tailoring care and to combine data sources in a way that reduces bias. They will develop techniques to make trial findings work better for everyday patients and to account for missing or confounding information. The goal is to produce dynamic treatment regimens—personalized treatment plans that adapt as a patient's condition evolves.
Who could benefit from this research
Good fit: Adults with type 2 diabetes, especially those who have or are at risk for atherosclerotic cardiovascular disease and whose care is recorded in electronic health records or disease registries, are the best fit for this work.
Not a fit: People without type 2 diabetes, those with uncommon diabetes types, or patients whose care is not captured in the data sources used may not see benefit from this project.
Why it matters
Potential benefit: If successful, clinicians could receive more personalized, stage-by-stage treatment recommendations that improve blood sugar control and lower future heart attack or stroke risk.
How similar studies have performed: Related efforts combining trial data and real-world health records have shown promise but remain relatively new, so this work builds on early successes while addressing key methodological gaps.
Where this research is happening
Ann Arbor, United States
- University of Michigan at Ann Arbor — Ann Arbor, United States (Active)
Researchers
- Principal investigator: Zeng, Donglin — University of Michigan at Ann Arbor
- Study coordinator: Zeng, Donglin
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.