Visual Analytics of Multidimensional Oral Health Surveys: Data Mining Study (Preprint)

Abstract

BACKGROUND Oral health surveys largely facilitate the prevention and treatment of oral diseases as well as the awareness of population health status. As oral health is always surveyed from a variety of perspectives, it is quite a difficult and complicated task to gain insights from multidimensional oral health surveys. OBJECTIVE In this paper, we develop a visualization framework for the visual analytics and deep mining of multidimensional oral health surveys. METHODS First, diseases and groups are embedded into data portraits based on their multidimensional attributes. Based on group classification, correlation patterns are then built for diseases, behaviors, symptoms and cognition to reveal their correlation features. Given the extricated knowledge of diseases, groups, behaviors and their attributes, a knowledge graph is further constructed to reveal semantic information, integrate the graph query function, and describe the features of intrigue to users. RESULTS A set of meaningful user interactions are integrated, enabling users to intuitively understand the oral health situation and conduct in-depth data exploration and analysis. Case studies based on real-world datasets and interviews with domain experts have demonstrated the effectiveness of our system. CONCLUSIONS In this paper, we propose a visualization framework for multidimensional oral health surveys. A series of user-friendly interactions are integrated to propose a visual analysis system that can help users further explore the regulations of oral health conditions. Case studies based on real-world datasets demonstrate the effectiveness of our system in the exploration of oral diseases.