SBIR Phase II: Non-invasive Neonatal Brainstem Monitoring to Improve Sleep, Minimize Disruptions and Enhance Feeding Stamina Leading to Earlier Discharge and Healthier Development

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is improved health and lowered cost of care for 15 million babies who are born prematurely or severely underweight each year. These 'premies' require weeks or months of care in specialized hospital units (e.g. NICU). In the United States, a typical NICU stay costs about $80K, and the total cost of healthcare during the first year of life is about $16B annually. These babies are at elevated risk for a range of serious lifelong complications that economically burden society by over $30B. This project has the potential to make a substantial impact to one of the most core vital elements of neonatal growth and development by improving the baby's sleep-wake-feed cycle. Today that cycle is irregular, episodic and disrupted almost 80% of the time which prolongs hospitalization. If successful, this project and technology would provide clinicians with a new tool and approach to help babies establish regularity, build up more energy and take on more calories so they can be discharged 20% faster. More importantly, this technology could lower the rate of downstream neuro developmental complications which are linked directly to poor sleep patterns. This Small Business Innovation Research (SBIR) Phase II project will result in a simple miniature wearable patch and display system that clinicians can use to monitor neonatal sleep and development patterns. This new tool will help clinicians achieve their goals of improving sleep-wake-feed cycles. In Phase I the team developed a prototype sensor configured to work on tiny babies and demonstrated that it could be used to accurately measure sleep cycles. In Phase II, the main objective is to advance the design and performance of this instrument to enable routine reliable use. It should be simple and non-intrusive for any clinician to reliably position the sensor and monitor any baby for multi-day periods. Analysis data should be presented real-time in an easy-to-interpret and actionable format. The work includes further biomedical engineering to improve attachment, amplifier circuit modelling to widen dynamic range and signal processing to automate artifact handling. The team will develop and test machine learning routines that will display detailed accurate and reliable instantaneous and trend data of brainstem-based sleep patterns that are not available today. These new advances, built on novel brainstem biomeasures will open up broad adoption supporting the development of a business and substantial medical advances. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.