Fair, reliable computer tools to predict how diseases work and how patients respond to medicines
Robust, Generalizable, and Fair Machine Learning Models for Biomedicine
Building new computer methods that learn from medical records, lab tests, and images to better predict disease causes and how patients will respond to treatments.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Harvard Medical School NIH-funded |
| Lab location | 1 site (Boston, United States) |
| Project ID | NIH-11124821 on NIH RePORTER |
What this research studies
This project builds computer algorithms that combine different kinds of medical information—like genetics, tissue images, and clinical records—to find patterns tied to disease and drug reactions. The team will link pattern-finding methods with techniques that try to identify cause-and-effect so results hold up across different hospitals and patient groups. They will test these methods on real biomedical datasets to reduce bias and make predictions more reliable and explainable. The aim is tools that help clinicians understand why a treatment works or causes side effects and that can be applied broadly.
Who could benefit from this research
Good fit: Patients who can share genetic tests, pathology images, or detailed clinical records would be most useful to this work.
Not a fit: People without relevant medical data or whose conditions are not represented in the datasets may not see direct benefits from this project.
Why it matters
Potential benefit: If successful, this work could lead to clearer, more trustworthy predictions about which treatments will help or harm individual patients.
How similar studies have performed: Previous machine-learning tools have improved some predictions but often fail when moved to new settings, and combining causal-inference methods with ML is relatively new and still being proven.
Where this research is happening
Boston, United States
- Harvard Medical School — Boston, United States (Active)
Researchers
- Principal investigator: Yu, Kun-Hsing — Harvard Medical School
- Study coordinator: Yu, Kun-Hsing
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.