ORBIL-AI: Making medical AI more reliable and easier to trust
Official title: ORBIL-AI: Orthogonality-Regularized Biomedical Information-theoretic Learning
Funded at Morgan State University · NIH-11424508 · Data updated 2026-11-12
Aims to create a smarter, safer AI system that learns from multiple medical signals without repeating the same information, so it can be trusted in real clinical use.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Morgan State University NIH-funded |
| Lab location | 1 site (Baltimore, United States) |
| Project start | September 10, 2026 |
| Project end | July 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $130,134 |
| NIH project number | 1R16LM015384-01 |
| Project ID | NIH-11424508 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are individuals whose clinical care involves multimodal physiological signals (e.g., ECG data) that could benefit from improved AI interpretation.
✕Less likely to help
Patients not involving multimodal biomedical signals or those not receiving AI-assisted analyses may not directly benefit.
What this research studies
This project will develop ORBIL-AI, a new AI framework that avoids redundant information in multimodal biomedical signals like ECG data. By introducing an orthogonality regularizer and information-theoretic penalties, the method seeks to make AI models more generalizable, interpretable, and well-calibrated for clinical settings. The work includes rigorous testing on large ECG datasets and evaluating performance on data the model hasn’t seen before to ensure reliability in real-world use.
Why it matters
Potential benefit: If successful, patients could receive AI-driven analyses that are more accurate, transparent, and dependable across diverse clinical scenarios.
How similar studies have gone: Prior work on multimodal ECG AI has shown benefits, but this project aims for stronger non-redundant feature learning for better trust and calibration.
Where this research is happening
-
Morgan State University
Baltimore, United States Active
Researchers
- Principal investigator: Oladunni, Timothy — Morgan State University
- Study coordinator: Oladunni, Timothy
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.