Date of Award
Summer 2021
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Mathematical and Statistical Sciences
Program
Computational Mathematical and Statistical Sciences
First Advisor
Ahamed, Sheikh-Iqbal
Second Advisor
Bansal, Naveen
Third Advisor
Madiraju, Praveen
Abstract
Considering morbidity, mortality, and annual treatment costs, the dramatic rise in the incidence of sepsis and septic shock among intensive care unit (ICU) admissions in US hospitals is an increasing concern. The recent excruciating statistics regarding sepsis mortality, the average length of hospital stay, and annual treatment costs made sepsis treatment and research a critical domain in medical informatics. The aims of this dissertation center around four research questions. First, we discuss how we can investigate the prevalence and underlying relation of the sepsis diagnosis criteria (qSOFA and SIRS) and its implications in Medical Informatics and predictive analytics. Second, we delved into how we can develop a more sustainable medical informatics assistive solution that will help make evidence-based judgments instead of flummoxing the caregivers in decision making. Third, we aim to develop a data-driven tool as a medical informatics solution that helps ICU practitioners and researchers to monitor and intervene on the existing sepsis patients more efficiently and interactively and conduct retrospective studies to seek rationales to different sepsis scenarios in ICU. Fourth, we unravel the computational sustainability perspective of our medical informatics research. Computational Sustainability is a movement facilitated by CompSustNet–- a virtual network led by Cornell University and supported by NSF–- so that a novel scientific method, algorithm, or solution innovated to solve one particular problem of one domain can be repurposed for another distinct problem of another domain with a similar computational nature. Our discussion is twofold. Initially, we contextualized different perspectives and conceptual elements of Internet-of-Energy and Computational Sustainability implications. Then, we unravel how the Contextually-tailored Bayesian Online Change Point Detection Algorithm can be repurposed to address the Public Safety Power Shutoff issues impacting grid resiliency of IoE and Wildfire threat in the West of the United States.