*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Disease State Prediction using Multiscale Dynamics
Committee:
Dr. Gari Clifford, Emory, Chair , Advisor
Dr. Christopher Rozell, ECE, Co-Advisor
Dr. Omer Inan, ECE
Dr. Eva Dyer, BME
Dr. David Anderson, ECE
Dr. Amit Shah, Emory
Abstract: Treatment of many disorders requires clinic visits, with a strong reliance on patient self-reports for filling in the gaps between these in-person assessments. This lack of monitoring leads to biases in the data and a lack of provision for responding to rapid changes in health. Objective tools for monitoring patients in between clinical visits are mainly absent. In recent years, advances in wearable technology have enabled almost real-time monitoring of changes in physiology. These advances have the potential to transform the landscape for monitoring diseases. The objective of this research is to build non-invasive and continuous monitoring methods using wearables in naturalistic settings. In the first part, a novel wearable-based sleep detection approach is developed. The proposed approach uses the variations observed in the physiological data and detects patterns in these change events associated with sleep-wake transitions. The second part focuses on features derived from wearables to separate healthy controls and participants with health disorders in two different applications. In the first application, research watch data is used for monitoring patients post-trauma. Lastly, the second application presents the use of both passive (motion, location, social contact) and active (clinically validated survey) data collected by a smartphone app for heart failure outcome estimation.
