Machine learning-based sleep quality monitoring
- Quality of sleep monitoring for patients with sleeping disorder
Researchers at the University of Minnesota have developed an end-to-end framework that uses deep neural networks to extract temporal transition structure of the sleep stages using raw flow signals. This method can be used to accurately track sleep metrics like sleep efficiency calculated from sleep stages as the response of CPAP therapy. Health-care providers can monitor the patients from the convenience of the patient's home, allowing for personalized proactive management of CPAP therapy, which currently suffers from substantial abandonment issues. In addition, automated daily reports and longitudinal tracking of a patient's response to the therapy could improve patient compliance to CPAP therapy.
MESA (Multi-Ethnic Study of Atherosclerosis) dataset
- 400 Sleep Apnea patients
- 7.5 hours of sleep data per person
- Flow signal is sampled at 32 Hz -> 960 samples for every 30 second epoch
- Has inter-rater agreement of 85% on the annotated sleep stages
Phase of Development
Algorithm developed and validated in a pilot study. Currently validating against a larger patient population.
This technology is now available for:
- Sponsored research