*********************************
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
*********************************
Felipe Giuste
BME PhD Defense Presentation
Date: 2023-02-16
Time: 1-3pm
Location / Meeting Link: https://zoom.us/j/2498575581
Committee Members:
May D. Wang, PhD (Advisor); David Wright, MD; Robert Gross, MD/PhD; Blake Anderson, MD; Shriprasad Deshpande, MD
Title: A Translational Informatics Framework for Generating Data-Driven Solutions to Clinical Challenges
Abstract:
In this work, I defend the thesis that a framework may be developed to generate data-driven solutions to real clinical problems by solving major translational informatics challenges. I breakdown the major challenges into three categories: 1. Standardization: The process of encoding existing healthcare data into standardized vocabularies in order to obtain insights into patient populations. 2. Explanation: Generation of meaningful insights into data patterns used by AI models to reach clinical decisions. 3. Decision Support: Establishing systems to facilitate the integration of predictive models into clinical workflows to support expert decision-making. A solution to the lack of healthcare information standardization is provided through the creation of a web-based application to standardize pediatric bone diseases data at Shriners Children’s Hospital using the Fast Health Interoperability Resource (FHIR) standard. Next, I pursue model explainability by leveraging recent and novel explainable AI methods to predict COVID-19 positive patient outcomes. Finally, I implement insights gained from the first two solutions to generate a data-driven decision support tool for pediatric heart transplant rejection detection. Specifically, I generated a user interface to support expert detection of pediatric rejection from images of biopsied tissue. The presented accomplishments demonstrate the value of the proposed translational informatics framework to solve major challenges across a wide variety of real clinical contexts. My work will advance translational informatics by offering practical solutions to clinical challenges via data-driven solutions.
