Using the BRFSS Data to Design An Interface that Allows People to Get Individualized Wellness Suggestions and Chronic Health Indicators
Author(s)
Xu, Zhujie
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Chronic diseases pose a significant public health challenge in the United States, exacerbated by barriers to timely medical care such as high costs and accessibility issues. This study leverages the Behavioral Risk Factor Surveillance System (BRFSS) dataset to develop machine learning models capable of predicting multiple chronic diseases. A key innovation of this research is the integration of these models into a user-friendly, front-end-only web interface that provides personalized health risk assessments and lifestyle recommendations. By analyzing user inputs through a questionnaire aligned with BRFSS variables, the system offers actionable feedback to promote early intervention and self-care. Experimental results indicate high model performance, particularly for heart disease and stroke, with F1-scores exceeding 0.96. The study underscores the potential of accessible, privacy-preserving digital health tools in bridging healthcare gaps and fostering proactive disease management.
Sponsor
Date
Extent
Resource Type
Text
Resource Subtype
Undergraduate Research Option Thesis