Improving Sleep Apnea Detection with Smart Technology
Knowledge-informed Deep Learning for Apnea Detection with Limited Annotations
This project aims to create a smarter computer program that can quickly and accurately detect sleep apnea using less detailed information from wearable devices.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Georgia Institute of Technology NIH-funded |
| Lab location | 1 site (Atlanta, United States) |
| Project ID | NIH-11262405 on NIH RePORTER |
What this research studies
Diagnosing sleep apnea often requires doctors to manually review sleep data, which takes a lot of time and money. While new computer programs can help, they usually need very specific and detailed data to work well, which is hard to get. Our goal is to build a new type of computer program that can learn from less detailed information and still accurately find sleep apnea. This program will also use medical knowledge to make its detection even better.
Who could benefit from this research
Good fit: This research is for anyone interested in how technology can improve the diagnosis of sleep apnea.
Not a fit: Patients who do not have or suspect they have sleep apnea would not directly benefit from this diagnostic tool development.
Why it matters
Potential benefit: If successful, this could lead to faster, more affordable, and more accurate ways to diagnose sleep apnea for many people.
How similar studies have performed: While machine learning has been used for apnea detection, this project proposes a novel approach by using less detailed data and incorporating clinical knowledge.
Where this research is happening
Atlanta, United States
- Georgia Institute of Technology — Atlanta, United States (Active)
Researchers
- Principal investigator: Xian, Xiaochen — Georgia Institute of Technology
- Study coordinator: Xian, Xiaochen
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.