• About
    • Login
    View Item 
    •   Institutional Repository Home
    • Electronic Theses and Dissertations
    • Electronic Theses and Dissertations
    • View Item
    •   Institutional Repository Home
    • Electronic Theses and Dissertations
    • Electronic Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of Institutional RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDepartmentThis CollectionBy Issue DateAuthorsTitlesSubjectsDepartment

    My Account

    LoginRegister

    Quantifying Preterm Birth Risk And Heterogeneity Using Evolutionary History And Electronic Health Records

    Abraham, Abin Thengumtharamedayil
    0000-0002-9951-2879
    : http://hdl.handle.net/1803/16684
    : 2021-04-29

    Abstract

    Preterm birth, defined as a birth before 37 weeks of gestation, is prevalent and leads to significant morbidity and mortality worldwide. The pathogenesis of preterm birth, and more generally the mechanisms of birth timing, remain poorly understood. Twin based studies estimate that up to 30-40% of the variation in birth timing can be explained by genetic variation. Although a few genomic regions have been identified to date, there are likely many more that influence preterm birth risk. In addition, preterm birth is a complex phenotype with multiple etiologies and heterogenous clinical presentations. In this dissertation, I refine the phenotypic heterogeneity using machine learning approaches and evaluate the genomic basis for preterm birth using an evolutionary perspective. First, I identify sub-phenotype of preterm birth with distinct longitudinal trajectories and comorbid signatures. Some of these sub-phenotypes associate with genetic risk scores for known risk factors of preterm birth. Second, using dense phenotyping data from electronic health records, I develop a machine learning model to predict preterm birth and obtain interpretable representation of the learned rules. The model is able to discriminate between preterm and term births and serves as a proof-of-concept for predictive machine learning models for adverse pregnancy outcomes. Third, I test genomic regions associated with preterm birth for evolutionary signatures and identify diverse patterns of selection across many regions. The independent evolutionary signatures enable prioritization of candidate regions for further experimental validation. This dissertation refines the phenotypic definition and illustrates the role of diverse evolutionary forces on genomic regions associated with preterm birth. Disentangling the phenotypic heterogeneity and understanding the genetic basis of preterm birth will aid to isolate specific pathways of birth timing and tailor clinical management to each patient.
    Show full item record

    Files in this item

    Icon
    Name:
    ABRAHAM-DISSERTATION-2021.pdf
    Size:
    10.94Mb
    Format:
    PDF
    View/Open

    This item appears in the following collection(s):

    • Electronic Theses and Dissertations

    Connect with Vanderbilt Libraries

    Your Vanderbilt

    • Alumni
    • Current Students
    • Faculty & Staff
    • International Students
    • Media
    • Parents & Family
    • Prospective Students
    • Researchers
    • Sports Fans
    • Visitors & Neighbors

    Support the Jean and Alexander Heard Libraries

    Support the Library...Give Now

    Gifts to the Libraries support the learning and research needs of the entire Vanderbilt community. Learn more about giving to the Libraries.

    Become a Friend of the Libraries

    Quick Links

    • Hours
    • About
    • Employment
    • Staff Directory
    • Accessibility Services
    • Contact
    • Vanderbilt Home
    • Privacy Policy