Using advanced computer methods to make sense of incomplete health records for heart disease and obesity
Bayesian machine learning for complex missing data and causal inference with a focus on cardiovascular and obesity studies
This project uses Bayesian machine learning to fill gaps in electronic health records and better understand causes and treatment effects for people with heart disease or obesity.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Florida NIH-funded |
| Lab location | 1 site (Gainesville, United States) |
| Project ID | NIH-11301000 on NIH RePORTER |
What this research studies
Researchers will develop advanced Bayesian nonparametric computer models to handle missing information in electronic health records and in repeated measurements over time. They will combine multiple sources of data and auxiliary information to more reliably estimate how treatments lead to outcomes and how intermediate factors (mediators) contribute. The methods will be tailored to challenges that arise in cardiovascular and obesity research, including cluster randomized trial data. The goal is to make conclusions about causes and treatment effects more trustworthy even when some patient data are missing.
Who could benefit from this research
Good fit: People with cardiovascular disease or obesity whose electronic health records are included in research datasets or who take part in related trials would be most relevant to this work.
Not a fit: People without cardiovascular conditions or obesity, or whose records are not represented in the datasets used, are unlikely to see direct benefits.
Why it matters
Potential benefit: If successful, this work could lead to more accurate understanding of which treatments help people with heart disease or obesity and why, improving future care decisions.
How similar studies have performed: Existing statistical methods address missing EHR data and causal questions, but applying Bayesian nonparametric machine learning to these complex, nonignorable missingness and mediation problems is relatively novel.
Where this research is happening
Gainesville, United States
- University of Florida — Gainesville, United States (Active)
Researchers
- Principal investigator: Daniels, Michael J — University of Florida
- Study coordinator: Daniels, Michael J
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.