*********************************
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: Morphological Variability Analysis of Physiologic Waveform for Prediction and Detection of Diseases
Committee:
Dr. Clifford, Advisor
Dr. Inan, Co-Advisor
Dr. Anderson, Chair
Dr. Shah
Abstract:
The objective of the proposed research is to develop a framework for morphological variability (MV) estimation in physiologic waveform data for predicting and detecting disease. Also, the framework is designed to be robust to noise and covariates like heart rate (HR) and respiration rate (RR). The utility of the framework is demonstrated on electrocardiogram (ECG), arterial blood pressure (ABP) and photoplethysmogram (PPG). The ECG is obtained from individuals with post-traumatic stress disorder (PTSD) to identify PTSD individuals as having elevated MV. The ABP signals recorded are from individuals admitted to the ICU that develop sepsis. We hypothesize that MV of ABP will drop before these individuals experience sepsis onset. The PPG signals obtained are from a pediatric sample with congenital heart disease. The PPG data is used to develop a screening test for detecting the presence of disease with high sensitivity. Signal quality thresholds are determined to avoid measuring MV in signals significantly affected by noise. Ranges of values over which covariates like HR and RR significantly elevate MV measurements along with possible mitigation strategies for these covariates are determined.
