IP Requirement: Emory/CHOA IP

Experience Requirement:

– Rapid prototyping

– Strong coding background

– UI/UX design

Every night, an estimated 3 million U.S. children struggle with obstructive sleep apnea (OSA), a condition linked to poor school performance, attention difficulties, chronic headaches, bedwetting, behavioral problems, cardiovascular stress, and chronic inflammation. The gold-standard test — in-lab polysomnography (PSG) — is expensive, logistically challenging, and often inaccessible. Children must spend a night in a lab hooked to multiple wires and sensors, in an unfamiliar environment, often waiting 3–6 months just to be tested, even at major pediatric medical centers.  Rural areas may not have any labs focused on care for children.  Many children fail to sleep normally under these conditions, producing unrepresentative results.  A parent needs to stay with the testing child as well, often leading to missed work or difficulty caring for other siblings at home.

Current pediatric PSG scoring systems lump children birth-18 into the same categories, despite vast developmental differences in sleep patterns. Normative sleep data for infants is lacking, as is data on adolescents as they progress through and past puberty, potentially leading to over- or under-treating vulnerable populations.  Research in this area is hampered by the same access issues that plague patient care – not enough labs to service all the children who need to be evaluated.

Meanwhile, adult care has embraced at-home PSG: simplified wearable setups and ambient monitoring allow natural sleep in familiar surroundings, support multi-night testing, and speed access to care. Detailed, in-lab testing remains an option for those who need it, but effective screening for treatment initiation can be conducted at home. Currently no validated at-home PSG exists for children — a gap ripe for innovation.  Researchers have experimented with machine learning and deep learning models of snoring diagnosis in adults with some success, but deep learning-driven diagnosis of OSA is not yet commonplace.

A validated, child-friendly, at-home sleep study system combining wearable comfort, minimal intrusion, and intelligent ambient sensing could:

• Deliver accurate diagnoses in real-world sleep environments
• Reduce wait times and testing costs
• Minimize barriers to testing for patients with social challenges
• Enable multi-night data collection for richer insights
• Build age-specific normative datasets for better understanding of how sleep patterns change during different stages of development 

The impact could be truly transformative: better diagnostics, targeted treatments, and a leap forward in pediatric sleep medicine research — all while improving the nightly lives of millions of children and their families.