Health Informatics Program electronic theses and dissertations (MU)
Permanent URI for this collection
The items in this collection are the theses and dissertations written by students of the Health Informatics Program. Some items may be viewed only by members of the University of Missouri System and/or University of Missouri-Columbia. Click on one of the browse buttons above for a complete listing of the works.
Browse
Recent Submissions
Item Relationship among body mass index, survival, and health-related quality of life among older patients with bladder cancer(University of Missouri--Columbia, 2024) Rajpurohit, Mitesh; Golzy, MojganINTRODUCTION: The relationship between body composition and bladder cancer outcomes is complex. A higher Body Mass Index (BMI) seems to predispose to the development of bladder cancer, though the impact on survival is more convoluted. We sought to study this relationship in a cohort of older patients with bladder cancer and to examine the relationship between BMI and Health-related quality of life. METHODS: We included patients from the Surveillance, Epidemiology, and End Results-Medicare Health Outcomes Survey database, 1998 to 2021, with a diagnosis of bladder cancer. We assessed demographic characteristics, BMI, overall survival, and the Physical Component Summary(PCS) and Mental Component Summary(MCS) of the Short Form 36 Health Survey. We used ANOVA for univariate analysis and generalized linear models for multivariate analyses. Log-rank test was used to compare survival curves. RESULTS: The analysis found that BMI was predictive of overall survival, with improved survival for those who were overweight, obese, or severely obese when compared to those in the healthy range or underweight. PCS and MCS were correlated with BMI, with overweight patients demonstrating the highest scores These relationships remained statistically significant in multivariable analysis that accounted for other variables. CONCLUSIONS: We that the quality of life was highest among patients who were overweight (BMI 25-30) with severely obese patients having the worst quality of life. Increased BMI appears to offer a survival advantage among older patients with bladder cancer, while moderately elevated BMI offers a quality of life advantage as well.Item Design and implementation of a tailored data management system for a rural cardiovascular clinic(University of Missouri--Columbia, 2024) Nelson, Noah Christian; Popescu, MihailHealth Information Technology (HIT) adoption and meaningful use continues to be a challenge in rural healthcare, specifically in Critical Access Hospitals (CAHs) and smaller clinics. This study addresses the gap in effective HIT deployment in a rural cardiovascular clinic in Alabama by providing a data management solution for the authorization and validation of implantable cardioverter-defibrillator (ICD) procedures. This software was deployed via the Google Cloud, and by using this platform alongside its integrated API system via AppsScript, the specific financial and operational needs of the clinic and support staff were satisfied. This system was deployed from January to August 2023, and led to the identification and subsequent treatment of patients who otherwise would have been overlooked (71 identified, 13 treated). This thesis focuses on the need for tailored, low-tech approaches in high-need environments, emphasizing the opportunities to leverage scalable, affordable technologies to enhance HIT in high need areas.Item Association between Health-Related Quality of Life measures with bladder cancer characteristics and survival outcomes in older bladder cancer patients : a clustering approach(University of Missouri--Columbia, 2023) Beheshti, Mohammad; Popescu, Mihail; Golzy, Mojgan[EMBARGOED UNTIL 12/01/2024] Introduction: Bladder cancer significantly impacts the physical and mental well-being of elderly patients. This study employs clustering algorithms to 1) categorize patient survival based on Health-Related Quality of Life (HRQOL) and Activities of Daily Living (ADLs), 2) explore the influence of bladder cancer characteristics on HRQOL, and 3) evaluate changes in patient clusters over a two-year follow-up. Methods: Data from bladder cancer patients aged 65 and above in the SEER-MHOS database (1998-2020) were analyzed using machine learning algorithms. Clusters of elderly bladder cancer patients with similar HRQOL (measured by PCS, MCS, and ADLs) were identified, and the log-rank test was employed to assess their association with survival outcomes. Results: The analysis revealed three distinct clusters, showing significant differences in demographics and socioeconomic variables (excluding smoking status, p=0.26). Variations in outcomes, such as depression and falls, were observed. Kaplan-Meier survival analysis with the log-rank test indicated substantial differences in survival probabilities among clusters. However, no significant differences were found in bladder cancer characteristics, including cancer staging (p=0.12), surgical type (p=0.07), and time from the first cancer diagnosis to the survey (p=0.50) among the clusters. Conclusion: The study suggests the independence of HRQOL measures (PCS, MCS, and ADLs) from bladder cancer characteristics. These findings provide valuable insights for urologists to guide patients on the potential impact of their functional status on cancer outcomes and overall well-being, enhancing patient care and understanding the link between cancer, its treatments, and emotional and physical health.Item A case-control based genomic analysis of Chronic Obstructive Pulmonary Disease(University of Missouri--Columbia, 2023) Ramnath, Anjana; Moxley, DavidChronic Obstructive Pulmonary Disease is a respiratory illness that affects a large number of people all over the world. It is a major cause of chronic morbidity and mortality and a serious global public health problem. COPD is the fourth leading cause of death worldwide. Although the environmental causes of COPD which predominantly include cigarette smoking are well-documented, to this date the genetic underpinnings of COPD remain largely unknown. Furthermore, in the current landscape of a respiratory pandemic, COPD patients are at a much higher risk for developing other respiratory illnesses and co-morbidities. Treatment methods for this disease have remained the same over the years. In this study we use genomic data from case-control based cohorts to study the genetic patterns and profiles of patients with this illness in order to identify key genetic factors and thereby gain a deeper understanding of the disease. This understanding would lead to greater insight on how to better diagnose, manage and treat this disease. A clearer insight at the genomic level would assist in actionable outcomes than could be leveraged to adopt a more Precision Medicine based modality to manage this disease thereby leading to more effective and better treatment options which would improve overall patient health outcomes.Item A study to reduce the number of preventable emergency visits at community level(University of Missouri--Columbia, 2023) Kanoongo, Anushka; Alafaireet, PatriciaIntroduction: Emergency Department overcrowding is a worldwide issue. The impact of increased unnecessary and preventable emergency visits in hospitals leads to reduced quality of care, inability to care for critically ill patients, increased errors, and mortality rates. The study aims at identifying ways to predict avoidable ER visits through implementing machine learning algorithms and intervening them at a community level. Materials and Method: The data was collected on a community level Electronic Health Record (CCMO) database and was provided for further investigation by the Randolph Caring Community Partnership (RCCCP). The exploratory data analysis was conducted in the RStudio and later the machine learning models were implemented in the jupyter notebook. 14 features were selected out of the 43 features through step wise logistic regression method to predict the ER visits. Result: The data of 595 patients was collected during the period of 2018 to 2021. The AUC score of the Decision Tree and the logistic regression model was 0.54 and 0.61 respectively. The support vector machine had the accuracy of 0.58 in predicting ER visits. Conclusion: The study depicted that it is possible to have prediction models at the community level to reduce the burden at emergency department. A more focused data collection specific for the prediction of unnecessary ER visit will be able to produce a more feasible model.