Socioeconomic and Behavioral Determinants of Type II Diabetes Outcomes: A Health Data Analytics Approach

Аннотация

Objective: This study investigates the socioeconomic CITATION and behavioral determinants of Type II Diabetes COPYRIGHT outcomes using a health data analytics framework. © 2025 Original content from this work may be used under the terms Drawing from publicly available medical expenditure of the creative commons attributes 4.0 License. and demographic data, the research examines how variables such as age, education, income, employment status, and smoking behavior influence the prevalence and economic impact of the disease. Key findings highlight that older adults and individuals with lower educational attainment or who engage in smoking incur higher medical expenditures. Methods: A Random Forest classifier was employed to predict patient gender based on socioeconomic and behavioral features, demonstrating moderate predictive accuracy and reinforcing the relevance of non-clinical data in chronic disease profiling. Results: Statistical analysis further revealed significant correlations between social disadvantage and elevated diabetes-related costs. The study advocates for an integrated “health in all policies” approach, emphasizing the need for cross-sectoral interventions in education, employment, and community health promotion. Conclusion: These findings contribute to the growing body of literature on the social determinants of health and underscore the value of data-driven strategies in addressing the Type II Diabetes epidemic. Future research should focus on longitudinal and intersectional analyses to enhance causal inference and inform The American Journal of Medical Sciences and Pharmaceutical Research 13 https://www.theamericanjournals.com/index.php/tajmspr The American Journal of Medical Sciences and Pharmaceutical Research targeted policy responses. Moreover, existing interventions have primarily focused on modifying individual behaviors without adequately Keywords: Type II Diabetes, socioeconomic addressing the broader context in which these behaviors determinants, health data analytics, medical occur. Walker et al. (2014) noted that while promoting expenditure, smoking behavior, education level physical activity and dietary changes can temporarily improve outcomes, they are insufficient when 1. Introduction implemented in isolation from broader socioeconomic Type II Diabetes (T2D) has emerged as one of the most supports. This observation aligns with the argument by pressing public health challenges of the 21st century, Marmot and Wilkinson (2006) that improvements in with both developed and developing nations quality of life, rather than isolated health behaviors, are experiencing rising incidence and complications essential for long-term disease prevention. Despite associated with the disease. Globally, T2D accounts for widespread recognition of these issues, there remains a roughly 90 percent of all diabetes cases, driven by significant gap in integrating socioeconomic data into genetic susceptibility and environmental influences, health analytics for chronic disease management. As including socioeconomic conditions and lifestyle Buck and Gregory (2013) point out, local authorities and behaviors (Patel, Bhattacharya, and Butte, 2010). While policymakers often lack access to clear evidence on advances in clinical medicine have improved diagnostic which interventions effectively reduce health and therapeutic capabilities, long-term outcomes inequalities. Researchers have increasingly turned to remain uneven across populations, indicating that large-scale data analytics to quantify and model the medical care alone cannot address the root causes of the complex relationships between social determinants and disease (Hill, Nielsen, and Fox, 2013). The burden of T2D disease outcomes. This paper builds on that work by extends beyond personal health, affecting families, analyzing real-world health expenditure and healthcare systems, and national economies. Alonso- demographic data to uncover how socioeconomic and Moran et al. (2014) observed that T2D leads to higher behavioral variables influence Type II Diabetes rates of multimorbidity and disability, which in turn outcomes. Drawing on publicly available healthcare generate premature mortality, productivity loss, and datasets, the study examines the role of factors such as increased dependence on informal care. As a result, the income level, employment status, smoking behavior, economic and societal costs of the disease continue to diet, age, and education in shaping medical expenditure climb, even in high-income nations with advanced and disease prevalence. It aims to contribute to a deeper health systems. According to Mackenbach et al. (1997; understanding of how health data analytics can inform 2008), persistent inequalities in health outcomes across more equitable and effective diabetes prevention European social strata exist despite universal healthcare strategies. access, suggesting that socioeconomic structures shape health disparities more than he