Spatiotemporal data analysis to identify environmental impact on chronic diseases for disease management and control: A data-driven approach

The World Health Organization reported that 23% of global deaths and 22% of the disease burden were from modifiable environmental risks highlighting the need to understand the impact of such factors on chronic diseases. This research focuses on two-fold objectives: theoretical, aiming to develop a comprehensive framework for analyzing spatiotemporal data using sensor-generated data to assess the influence of environmental factors on diseases, particularly those with prolonged exposure; and application-based, to identify disease hotspots, and extract associated environmental profiles, and identify vulnerable populations for effective disease management.

Analyzing data from multiple sources, including admitted patients’ data, daily air pollutant concentrations, and meteorological conditions in Greater Sydney and parts of Victoria, this research introduces a novel methodological framework. It distinguishes methodologies for diseases linked to long-term and short-term environmental exposure, focusing primarily on the former. The framework identifies spatial and spatiotemporal disease hotspots and introduces modified cluster pattern categories to prioritize locations requiring immediate attention. A unique process flow estimates prolonged population exposure using sparsely located, daily sensor-generated data. Additionally, bivariate spatiotemporal hotspot pattern categories revealed the link between disease prevalence and prolonged exposure, aiding in pinpointing regions requiring urgent attention.

Findings revealed that taking area-specific measures helps in disease management and control in an economically efficient manner for cataract admissions in Greater Sydney. These findings will help policymakers to come up with strategies for disease management and control and air quality maintenance, fostering a healthier population.