PhD, University of Cincinnati, 2024, Nursing: Nursing - Doctoral Program

Background: Many children are directly and indirectly affected by the opioid epidemic and the consequences of opioid use during pregnancy through prenatal opioid exposure. Prenatal opioid exposure is associated with adverse neonatal and long-term outcomes and may develop into neonatal opioid withdrawal syndrome. Although recent reviews largely suggest negative outcomes after prenatal opioid exposure, they are limited by the heterogeneity of identification methods used to ascertain exposure. The impact of varying identification methods on the prevalence and outcomes of exposure is not clearly understood. The use of big data and larger data linkages in nursing science may help illuminate the impact of varying identification methods used to ascertain prenatal opioid exposure. Aims: This three-manuscript dissertation aimed to (1) discuss the use and potential of big data for nurse scientists, (2) conduct a scoping review of the varying identification methods in current literature, and (3) perform a secondary data analysis of a large integrated data to explore the prevalence of prenatal opioid exposure across identification methods to inform research, practice, and support children and families impacted by prenatal opioid exposure. Methods: The first manuscript was a discursive paper that provided an introductory guide for leveraging big data in nursing research. The second manuscript was a scoping review that synthesized the various identification methods used to ascertain opioid exposure in the United States over the last decade. Insights from the scoping review generated three identification methods leveraged in the third dissertation manuscript: (1) Maternal data (e.g., toxicology and diagnoses), (2) Infant data (e.g., toxicology and diagnoses), and (3) Combined method using maternal and infant data. The third manuscript was a secondary data analysis of a large perinatal linkage database in the Midwest to explore the prevalence of prenatal opioid expo (open full item for complete abstract)

Committee: Joshua Lambert Ph.D. (Committee Chair); Sara Arter Ph.D. R.N. (Committee Member); Nichole Nidey Ph.D. (Committee Member); Samantha Boch Ph.D. R.N. (Committee Member) Subjects: Nursing

Doctor of Philosophy, Case Western Reserve University, 0, Nursing

Acute myocardial infarction (AMI) remains one of the most common causes of death in the United States and allocates a tremendous amount of healthcare expenditures that go beyond $12 billion annually. Machine learning (ML), a subset of artificial intelligence, has emerged as valuable methodological tool to advance nursing and biomedical research. The ML has shown to build predictive models that allow detection of risk factors, assist in diagnosis, and propose personalized treatments plans that may lead to enhanced patients' outcomes. From this perspective, the purpose of this study was to develop and evaluate the predictive performance of a random forest machine-learning model with a conventional multivariate logistic regression model established to examine the influence of individuals predisposing, enabling, and need factors on health service use outcomes (in-hospital mortality, 30-day readmission) of AMI patients guided by the Andersen Model (2008). The cross-sectional retrospective study utilized the Medical Information Mart for Intensive Care which comprises patients admitted to a large tertiary-level academic center of the Harvard Medical School in Boston, MA. The variables of interest include age, gender, ethnicity, type of insurance, body mass index, existing comorbidities, in-hospital mortality, 30-day readmission. Patients with a primary diagnosis of ST-segment elevation MI and non-ST-segment elevation MI cared for at emergency department or critical care units were included in the study. Predictive models for each health service use outcomes were built using RStudio. There were a total of 1171 AMI patients included in the study, 255 (21.8%) patients with STEMI and 916 (78.2%) patients with NSTEMI. Predictors of in-hospital mortality and 30-day readmission included age and existing comorbidities. The accuracy rate, sensitivity, specificity, and AUC for the random forest models were 68-75%, 72-81%, 41-50%, and 0.58-0.59, respectively. On the other hand, the a (open full item for complete abstract)

Committee: Ronald Hickman Jr., PhD, RN, ACNP-BC, FNAP, FAAN (Committee Chair); Mary Dolansky PhD, RN, FAAN (Committee Member); Nicholas Schiltz PhD (Committee Member); Richard Josephson MD, MS, FACC, FAHA, FACP, FAACVPR (Committee Member) Subjects: Nursing