Browsing by Subject "risk prediction"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Assessment Of Urinary Metabolites In Risk Prediction Of Acute Kidney Injury
    (2020-05) Gisewhite, Sarah
    Acute kidney injury (AKI) is the sudden decrease or loss of kidney function caused by direct kidney injury or functional impairment. Many patients do not recover renal function, leading to poor quality of life and high healthcare costs. Previous work has been done to evaluate urinary biomarkers associated with AKI, but these studies have focused on a few proteins with questionable diagnostic ability. Due to the complex pathophysiology of AKI, it may be necessary to create a panel of biomarkers for diagnostic and prognostic assessment of AKI. We explored metabolic biomarkers of AKI in combat casualties using metabolomics. In this study, we used proton nuclear magnetic resonance (1H-NMR) spectroscopy to identify urinary metabolic biomarkers associated with the following outcomes: AKI diagnosis, injury severity score (ISS), AKI stage, or a primary outcome of death or need for renal replacement therapy (RRT).
  • Thumbnail Image
    Item
    Cardiovascular Disease In Cancer Survivors
    (2023) Polter, Elizabeth
    Over 18 million cancer survivors are living in the United States. Cancer survivors are at high risk for numerous adverse events, including cardiovascular disease (CVD). As the community of cancer survivors grows, there is a need to disentangle the complex causal relationships between cancer and CVD.In our first two manuscripts, we investigated two potential causes of CVD in cancer survivors. Manuscript 1 evaluated the associations between cancer, T-Cell immunosenescence (immune system aging), and CVD using data from the Health and Retirement Study. Prevalent cancer was strongly associated with T-cell immunosenescence, with stronger associations among participants who received chemotherapy and radiation. However, T-cell Immunosenescence was not prospectively associated with CVD or cancer. For Manuscript 2, we used the Marketscan® administrative healthcare claims databases to estimate the cardiovascular risk associated with the use of two hormone therapies, aromatase inhibitors (with ovarian suppression) and tamoxifen in premenopausal female breast cancer survivors. Although CVD events were rare in this population, enrollees who used aromatase inhibitors with ovarian suppression had an elevated risk of CVD compared to those who used tamoxifen. Finally, Manuscript 3 assessed the performance of the Pooled Cohort Equations (PCEs), risk prediction tools used to estimate ten-year cardiovascular risk and prescribe interventions. Analyses included cancer survivors and cancer-free participants in the Atherosclerosis Risk in Communities Study. Although the PCEs overestimated CVD risk in each group, we found no evidence that prediction differed by cancer history. Together, these findings provide insights that can be used to improve cardiovascular healthcare and prevention for cancer survivors.
  • Thumbnail Image
    Item
    Fairness Estimation For Small And Intersecting Subgroups In Clinical Applications
    (2024-03) Wastvedt, Solvejg
    Along with the increasing availability of health data has come the rise of data-driven models to inform decision-making and policy. These models have the potential to benefit both patients and health care providers but can also exacerbate health inequities. Existing "algorithmic fairness" methods for measuring and correcting model bias fall short of what is needed for health policy in several ways that we address in this dissertation. First, in clinical applications, risk prediction is typically used to guide treatment, creating distinct statistical issues that invalidate most existing techniques. Second, methods typically focus on a single grouping along which discrimination may occur rather than considering multiple, intersecting groups. Third, most existing techniques are only usable for relatively large subgroups. Finally, most existing algorithmic fairness methods require complete data on the grouping variables, such as race or gender, along which fairness is to be assessed. However, in many clinical settings, this information is missing or unreliable. In this dissertation, we address each of these challenges and propose methods that expand the possibilities for algorithmic fairness work in clinical settings.