Abstract
The domain of regional healthcare and personalized medicine holds significant promise, particularly concerning predictive models for blood glucose levels. This thesis endeavors to shed light on the initial factor analysis of blood glucose levels utilizing. It acknowledges the variability in health outcomes across a range of variables, including ethnicity, race, key biomarkers, health indicators, and adult lifestyles. By laying this foundation, it paves the way for future research in adaptable blood glucose modeling, tailored to the diverse backgrounds of various populations.
Research emphasizes the importance of meticulous data selection and appropriate factor analysis techniques, recognizing variations in optimal blood glucose levels among diverse variables. These variables encompass demographics, physical examination measurements, laboratory biomarker testing results, and outcomes from population questionnaires. Through the application of Exploratory Factor Analysis (EFA), the thesis identified 15 strong factors in affecting blood glucose levels from 47 variables based on 4 different categories of dataset. Leveraging these identified prifactors can optimize treatment outcomes and enhance patient healthy monitoring.
The advantages afforded by suitable factor identification and proper data operation facilitate the development of tailored predictive models, representing a significant stride forward in medicine. These models not only provide targeted interventions for diverse audiences but also contribute to financial sustainability and elevate life quality on both individual and societal scales worldwide.