Dissertation/Thesis Abstract

Applications of Data Science for Precision Cardiology
by Johnson, Kipp William, Ph.D., Icahn School of Medicine at Mount Sinai, 2020, 266; 27737998
Abstract (Summary)

Research and treatment of the pathological mechanisms underlying cardiovascular disease have made remarkable progress in the past hundred years. Simultaneously, however, the incidence and prevalence of cardiovascular disease have increased dramatically. Despite our success treating heart disease, new and better methods are urgently needed. The main hypothesis of this dissertation is that concepts drawn from statistical learning and data science can enable more precise approaches to cardiovascular medicine. I demonstrate this idea by first presenting a predictive model for personalized response to statin therapy. I then build upon this analysis of pharmacological agent response by reporting a discovery that the atypical antidepressant trazodone functions as an atherosclerosis-preventing agent and validate this finding with animal models and electronic health records from multiple sites. Continuing with the repurposing of electronic health records, I demonstrate how they may be coupled with genetic data to diagnose previously undiagnosed disease in the setting of monogenic hypertension. I then explore how hypertension may be causally modeled to validate treatment guidelines in a real-world setting. Finally, I demonstrate that even ‘deidentified’ electronic records can be used to reidentify patients in common situations and then provide a proof-of-concept deep-learning based method for mitigation of privacy concerns. I conclude with a discussion of the dissertation subject, precision cardiology, as a whole.

Indexing (document details)
Advisor: Dudley, Joel T.
Commitee: Houten, Sander, Baber, Usman, Kovacic, Jason, Mason, Christopher, Scott, Stuart
School: Icahn School of Medicine at Mount Sinai
Department: Genetics and Genomic Sciences
School Location: United States -- New York
Source: DAI-B 81/9(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Medicine, Bioinformatics, Genetics
Keywords: Bioinformatics, Biostatistics, Cardiovascular disease, Electronic health records, Machine learning, Precision medicine
Publication Number: 27737998
ISBN: 9781658444613
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest