Background: Understanding the relationship between diabetes and cardiovascular risk is paramount for achieving holistic and effective healthcare. Diabetes, a complex metabolic disorder, is intricately linked to an increased susceptibility to cardiovascular diseases, making it imperative to unravel the nuanced interplay between these two health parameters. Cardiovascular risk in individuals with diabetes is often heightened due to various factors, including endothelial dysfunction, inflammation, and metabolic disturbances. Insights into this intricate relationship can empower healthcare professionals to adopt a proactive stance, offering timely interventions and personalized care strategies.
Methods: This study leverages a publicly available dataset comprising 212 patients from Dutch hospitals to investigate the intricate connections among patient characteristics, dental pathology, and cardiovascular risk factors. Utilizing tensor decomposition in data science and visual representation, this study explored the bidirectional relationship between diabetes and coronary artery calcification. A multi-way array analysis integrated patient characteristics and dental conditions to construct tensor models for three categories: without diabetes, with diabetes, and with coronary artery calcification. Furthermore, com-1 plementary nonlinear dynamics, visual analyses, and machine learning were utilized to further enrich the investigation.
Results: Patterns across the three categories were discovered through PARAFAC tensor decomposition factors, incorporating both patient characteristics and dental conditions. The k-NN search, examining the similarity among tensor coefficients derived from the 3-way arrays within the three categories, highlighted a bidirectional link between diabetes and cardiovascular risk. Additionally, the utilization of fuzzy recurrence plots and entropy measures enabled the quantification of distinctive patterns among subjects without diabetes , those with diabetes, and individuals experiencing coronary artery calcification.
Conclusion: The reciprocal interaction between diabetes and CAC tertiles 2 and 3 becomes apparent, underscoring the necessity for a broader analytical perspective. The incorporation of patient characteristics and dental health in the 3-way array analysis reveals latent patterns, enhancing current understanding with nuanced insights. Dental conditions emerge as pivotal indicators, providing a more detailed viewpoint on the intricacy between diabetes and cardiovascular risk.