Semester of Graduation
Master of Science in Engineering Science (MSES)
Engineering Science-Information Technology Engineering
Overutilization of Emergency Departments (ED) is a major problem among the health care providers in the United States. In this research, a machine learning-based predictive model for predicting ED high utilizers will be designed based on a set of existing and proposed facilities and the population and social determinant of health (SDOH) factors influencing utilization. The purpose of the model will be to alert the healthcare systems and government organizations by identifying the reasons for overutilization of the medical services among the people in a particular community. Also, the novel coronavirus disease 2019 (COVID-19) developed in Whunan city, China has spread quickly to the other parts of the world. It has become a serious health threat to the United States. Moreover, in this research study, the clinical and social characteristics that are responsible for the quick spread of COVID-19 disease across the Louisiana state will be identified. The purpose of this study is to identify what kind of population gets COVID 19 and providing real time care decisions to minimize the risk of an individual acquiring COVID-19. The patient data from Electronic Health Records (EHR) of Francis Missionaries of our Lady Health System (FMOLHS) is geocoded and mapped into ArcGIS software. The socioeconomic factors and social vulnerability Index (SVI) variables available from various online sources are joined to the geocoded patient data with the help of spatial joining techniques available in the ArcGIS software. Correlation analysis between the dependent variables and factors will be conducted.
Tummala, RamyaKrishna, "Predictive Modeling of FMOL Health System Utilization Using Machine Learning Algorithms and Retrospective Study of COVID Tested Patients" (2021). LSU Master's Theses. 5278.
Knapp, Gerald M.