Wednesday, December 4, 2019, 11 am to 1 pm
311 Russ Engineering - Conference Room
Ph.D. Committee: Drs. Tanvi Banerjee (advisor), Mateen Rizki, Krishnaprasad Thirunarayan, William Romine (Biological Sciences), and Ali Azarbarzin (Brigham and Women’s Hospital/Harvard University)
Humans spend almost a third of their lives asleep. Sleep has a pivotal effect on job performance, memory, fatigue recovery, and both mental and physical health. Sleep quality (SQ) is a subjective experience and reported via patients’ self-reports. Predicting subjective SQ based on objective measurements can enhance diagnosis and treatment of SQ defects, especially in older adults who are subject to poor SQ. In this study, we assessed enhancement of subjective SQ prediction using an easy-to-use E4 wearable device in addition to discovering significant sleep-related risk factors from PSG data in elder people.
First, we designed a clinical decision support system to estimate SQ and feeling refreshed after sleep using data extracted from an E4 wearable device. Specifically, we processed four raw physiological signals of heart rate variability (HRV), electrodermal activity, body movement, and skin temperature using ensemble machine learning methods. Overall, the achievement of our system in predicting SQ demonstrated the capability of using wearable sensors in monitoring sleep.
Second, we investigated discovering more effective features in SQ prediction using HRV features which are not only effortlessly measurable but also can reflect sleep stage transitions and some sleep disorders. Evaluation of three machine learning methodologies demonstrated the outperformance of a convolutional neural network (CNN) methodology in predicting light, medium, and deep SQ. This outcome verified the capability of using HRV features, which are effortlessly measurable by easy-to-use wearable devices, in predicting SQ.
Third, we scrutinized daytime sleepiness risk factors as a sign of poor SQ from physiological signals. The analysis demonstrates distinguishability of the main risk factors of excessive daytime sleepiness (EDS) in patients suffering from fragmented sleep (e.g. apnea) vs sleep propensity (e.g. dementia). We also predicted EDS using new, sleep-related biomarkers.
Finally, we designed a framework to further categorize the risk factors of poor SQ. We will use this framework to assess the role of dementia severity (cognitive decline) in SQ of older community-dwelling men, who are susceptible to poor sleep and dementia. We will specifically assess EDS in different levels of cognitive decline severity using objective sleep-related biomarkers.
Log in to submit a correction for this event (subject to moderation).