Obesity prevalence varies markedly across neighborhoods, reflecting environmental, built-environment, and social influences, yet few studies integrate primary environmental measurements with contextual spatial data under a scale-aware predictive framework. As a proof-of-concept, we evaluated whether household-resolution measurements, laboratory-measured soil metals (Pb, Cd, Zn, Se, Cu) together with housing, soil-context, built-environment, and sociodemographic variables, can be harmonized into a spatial-block machine-learning framework to generate small-area obesity predictions for Greensboro, North Carolina, USA. Predictors were assembled for 475 geocoded households spanning 34 census tracts and aligned across heterogeneous spatial supports. Models were fitted using household-resolution predictors, with predictions aggregated to the census-tract level for evaluation. Five-fold cross-validation used coordinate-based spatial blocks, which reduced geographic proximity between training and testing observations but did not guarantee complete separation of census tracts. In the primary exploratory analysis, Gradient Boosting produced the lowest mean prediction error (root mean squared error, RMSE = 4.57 ± 1.53; R2 = 0.453 ± 0.235), although performance was modest and variable across folds; these values are primary exploratory estimates rather than validated generalization performance. A fully tract-aggregated analysis provided a complementary evaluation using 34 independent observations and indicated that tree-based models remained comparatively strong, although model rankings were not identical. Contextual demographic, housing, and spatial-gradient variables contributed more strongly than measured soil metals; because the PLACES outcome is itself modeled from demographic and socioeconomic structure, these leading predictors are partly circular with the outcome and are best read as markers of structural context. These findings demonstrate the feasibility of the data-integration framework but should not be interpreted as definitive estimates of predictive accuracy or causal environmental effects.
This study aims to analyze the temporal trends, interprovincial differences, and key predictors of Tuberculosis Outpatient Visits (TOV) in China. It provides empirical evidence for understanding regional differences in tuberculosis-related outpatient service uti- lization. Panel data from 30 Chinese provinces from 2012 to 2024 were used. The study included variables related to economic development, health resources, education resources, environmental governance, pollutant emissions, and technological innovation. Correlation analysis, model comparison, and XGBoost-SHAP analysis were applied. From 2012 to 2024, TOV showed a gradual upward trend and clear interprovincial differences. Shanghai, Fujian, Guangdong, and Zhejiang had relatively higher total recorded outpatient volumes. XGBoost showed the best predictive performance among all candidate models (R2 = 0.8154). SHAP results identified Disposable Income Per Capita (DIPC), University Staff (USTF), Domestic Patent Applications (DPA), Hospital Beds (HBED), and Technology Market Turnover (TMT) as the main predictors. Environmental governance and pollutant emission vari- ables had lower overall contributions, but they still showed nonlinear predictive contributions in some value ranges. The findings suggest that interprovincial differences in TOV are jointly associated with economic development, health resources, education resources, environmental governance, and technological innovation. TOV mainly reflects outpatient service utilization and case detection capacity. It should not be interpreted as a direct measure of tuberculosis incidence risk.
Spatial epidemiology provides powerful tools for understanding geographic patterns in health and disease, but methodological and interpretative pitfalls can undermine the validity of spatial analyses. This editorial highlights ten common pitfalls spanning spatial dependence, scale, ecological inference, small-area estimation, spatial confounding, hotspot interpretation, model validation, measurement and statistical uncertainty, and causal interpretation. For each, we provide practical guidance to support more rigorous and reliable spatial epidemiological research. As geospatial data, artificial intelligence, and analytical methods continue to advance, careful spatial reasoning remains essential to ensure that methodological sophistication translates into valid, interpretable, and meaningful public health evidence.
Lyme disease is a growing public health threat driven by interplay of climatic, ecological and social factors. This review adopts an eco-syndemic framework, viewing Lyme disease emergence as the confluence of multiple synergistic drivers rather than a single- cause phenomenon. We synthesize evidence that climate conditions, ecological circumstances and human behavioural patterns inter- sect to amplify Lyme disease risk. By integrating these seemingly separate domains, our review highlights novel insights; for exam- ple, habitat fragmentation and predator loss may magnify the effects of a warming climate on reservoir or host populations, and human activities in suburban green spaces may mediate infection cycles. This holistic perspective is a departure from reductionist explanations and emphasizes the importance of coupled human–environment systems in studies of disease emergence. We discuss how an eco-syndemic frame can improve surveillance and prevention emphasizing One Health approaches that unite environmental management with animal health and public health outreach. Understanding the interactive and non-linear dynamics of Lyme disease drivers is crucial for developing effective interventions and preparing for future tick-borne disease challenges. While selected com- parative evidence from Europe is used where relevant, the review’s primary empirical focus is North America.
This study investigated variations in breast cancer mortality among women in San Luis Potosí, Mexico using an epidemiologicalspatial approach covering the period 2009–2019. Additionally, global and specific survival and its associations with clinical stage, age at diagnosis, marginalization index, recurrence and arsenic concentration in water were evaluated. We conducted a retrospective ecological, study involving1, 626 confirmed breast cancer cases and 264 related deaths registered at a public hospital. Survival analysis was performed using the Kaplan-Meier method and Log-Rank tests. Spatial distribution patterns of municipal average mortality were assessed using Moran’s I and visualized in ArcMap 10.1. At the state-level the mean age at diagnosis among deceased patients was 53.49 years, with 84% presenting at advanced stages (IIB–IV). A progressively increased mortality, particularly in Health Jurisdiction IV and the municipality of Cerro de San Pedro, was observed, with peaks in 2016. The 5-year global survival rate was 83.78%. Factors significantly associated with reduced survival included advanced stage, older age, higher marginalization index and recurrence. Although arsenic exposure was not statistically significant, patients exposed to levels exceeding 0.025 mg/L exhibited longer survival times. The integration of spatial epidemiology with survival analysis underscored critical geographic and sociodemographic disparities and offer valuable insights for targeted healthcare planning and resource allocation, particularly in high-priority regions.
