AI that uses breathing, oxygen, and arousal signals to better describe sleep apnea
Physiology guided AI for going beyond the AHI in Sleep Apnea
This project uses an explainable AI that combines breathing patterns, oxygen drops, and brief awakenings to better predict symptoms and long-term risks for adults with obstructive sleep apnea.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Icahn School of Medicine at Mount Sinai NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project ID | NIH-11292423 on NIH RePORTER |
What this research studies
This project builds an explainable AI that looks at your breathing patterns, oxygen drops, and brief awakenings and turns them into easy-to-understand probability scores that link sleep apnea to daytime sleepiness and long-term health risks. The team trains the system on thousands of past sleep studies and medical records so the scores reflect real outcomes like cardiovascular disease and mortality. Early results from over 10,000 people showed the sleepiness score correctly identified daytime sleepiness about 87% of the time, and related scores predicted heart disease and death in multiple cohorts. If this work succeeds, it could help doctors move beyond the standard apnea-hypopnea index (AHI) to personalize care and target treatments to those most at risk.
Who could benefit from this research
Good fit: Adults (18+) with diagnosed or suspected obstructive sleep apnea, especially those with daytime sleepiness or cardiovascular risk factors, are the most relevant candidates.
Not a fit: People without sleep apnea, children, or those whose care does not rely on sleep study data are unlikely to benefit directly from this work.
Why it matters
Potential benefit: If successful, this could help doctors identify who is most likely to experience sleepiness or cardiovascular problems and tailor treatments more precisely than the AHI alone.
How similar studies have performed: Preliminary pooled analyses from the team's cohorts show promising results (87% accuracy for predicting sleepiness), but physiology-guided AI approaches to replace AHI are still an emerging and not yet widely adopted method.
Where this research is happening
New York, United States
- Icahn School of Medicine at Mount Sinai — New York, United States (Active)
Researchers
- Principal investigator: Parekh, Ankit Ashok — Icahn School of Medicine at Mount Sinai
- Study coordinator: Parekh, Ankit Ashok
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.