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.
|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|
|Subjects:||Medicine, Bioinformatics, Genetics|
|Keywords:||Bioinformatics, Biostatistics, Cardiovascular disease, Electronic health records, Machine learning, Precision medicine|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be