The health cost of urbanization: identification and ranking of influencing factors of class A and B infectious diseases based on machine learning.

Aims: With the rapid advancement of urbanization, an increasing number of people are congregating in urban areas, leading to a higher density of economic activities. This may not only accelerate the spread of infectious diseases but also result in pollutants that harm residents' health. Nevertheless, improvements in infrastructure and healthcare services, coupled with heightened awareness of personal protection among residents, can effectively mitigate the spread of infectious diseases. The incidence rates of Class A and B infectious diseases serve as critical indicators of public health status. This study seeks to identify and prioritize the key factors influencing public health during the process of rapid urbanization, thereby providing a scientific basis for decision-making aimed at enhancing residents' living environments and addressing existing gaps in public health systems. Methods: Using provincial-level data from mainland China (2008-2022), this study systematically applied multiple machine learning methods, including Random Forest, Gradient Boosting Tree, and XGBoost, to evaluate the impacts of over 10 indicators across economic, demographic, land use, and social dimensions on the Incidence Rate of Class A and B Infectious Diseases per 100,000 Population. Results: (1) Social factors account for 46.7%, constituting the most significant determinant, succeeded by land use, population, and economic dimensions. (2) Public transportation, urban water supply coverage, healthcare expenditure, and the spatial distribution of healthcare resources exert direct effects on residents' health outcomes and the accessibility of public health services. (3) Regarding land use, effective urban planning-reflected in indicators such as the green coverage rate of built-up areas and the per capita area of paved roads-plays a crucial role in promoting public health, accounting for 17.4% on average, whereas inadequate land-use management often precipitates health risks. (4) Population dynamics, encompassing demographic restructuring, agglomeration, and education levels, simultaneously generate advantages (e.g., improved efficiency in health service delivery) and challenges (e.g., heightened vulnerability to infectious disease transmission). (5) Economic factors, including industrial pollution control (ratio of completed investment in industrial pollution control to GDP), industrial upgrading (ratio of tertiary to secondary industry value-added), international trade (foreign trade dependence), and income levels (per capita disposable income of urban residents), manifest dual effects: advancing health improvements while engendering environmental degradation and cross-border health risks. (6) The health implications of rapid urbanization display regional disparity: social factors (60.2%) predominate in eastern China, economic factors (63.2%) in central China, and land use factors (54.2%) in western regions. Conclusion: During rapid urbanization, governments must prioritize timely enhancements to public health services, rational land use planning, and protection of vulnerable populations. Emphasizing the quality of economic development and fostering synergies between industrial upgrading and environmental governance will improve public health outcomes.