Computer models to predict cure and guide treatment decisions
Official title: Machine Learning-Based Predictive Models for Disease Cure and Computationally Efficient Methods in High-Dimensional Settings
Funded at University of Texas Arlington · NIH-11323047 · Data updated 2026-11-12
This work builds computer tools that use patient data to predict who is likely cured and who may need more treatment so doctors can avoid unnecessary high‑intensity therapies.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Texas Arlington NIH-funded |
| Lab location | 1 site (Arlington, United States) |
| Project start | May 1, 2025 |
| Project end | April 30, 2030 |
| Funding year | 2026 |
| Award (this year) | $364,926 |
| NIH project number | 5R35GM156859-02 |
| Project ID | NIH-11323047 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates would be people with early‑stage disease who have detailed pre‑treatment clinical information and follow‑up (survival) data available for model training or validation.
✕Less likely to help
Patients without adequate electronic medical records, those with advanced‑stage disease not represented in the data, or conditions outside the tested disease types are unlikely to benefit directly from these models.
What this research studies
From your perspective, researchers will build fast machine‑learning tools that look at many pre‑treatment health details and follow‑up outcomes to guess whether you are likely cured. The team plans to design methods that work well with very large sets of medical features and that are more reliable than current models. They will compare these new approaches to existing ones and create user‑friendly software so hospitals can run the tools without deep programming know‑how. The goal is to test and validate the models using real clinical data so the tools can be useful in everyday care.
Why it matters
Potential benefit: If successful, these tools could help avoid unnecessary aggressive treatments for patients who are already cured and spot those who need earlier intervention.
How similar studies have gone: Previous machine‑learning approaches have shown promise for predicting outcomes, but many existing models struggle with very high‑dimensional data and clinical implementation, so this work aims to improve on those gaps.
Where this research is happening
-
University of Texas Arlington
Arlington, United States Active
Researchers
- Principal investigator: Pal, Suvra — University of Texas Arlington
- Study coordinator: Pal, Suvra
Related research
Other NIH-funded projects on the same topics.
-
New microfluidic platform to study aging and reproduction in C. elegans
Aims to make studying aging and reproductive biology in C. elegans easier and faster by using a new microfluidic chip that automates how worms are loaded, housed, and imaged.
-
Unlocking how transcriptional regulators influence eye health and disease
A patient-friendly overview of a research project that aims to map how genes control eye health using scalable, advanced data methods.
-
Data-driven look at walkability and safety for older adults
A small, patient-friendly study aims to understand what makes neighborhoods easier or harder to walk for adults aged 21 and older, focusing especially on older adults.
-
How changes to public spaces affect hypertension risk in older adults
changes in everyday public spaces like parks and sidewalks may influence blood pressure in adults 21 and older over time.
-
Improving Teenage Driver Safety through Better Training and Safer Roadways
A teen-focused program tests how strengthening driver training and smarter road design can reduce risky driving and crashes for 15–18-year-olds.
-
Light-activated metal tools to image and treat disease
A researcher team at a university is developing tiny osmium metal compounds that light up and can be activated inside the body to help visualize and control disease.
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.