Predicting census-tract obesity prevalence using integrated environmental, built-environment, and neighborhood data: a scale-aware geospatial machine-learning proof-of-concept

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.

Allen B, 2023. An interpretable machine learning model of cross-sectional U.S. county-level obesity prevalence using explainable artificial intelligence. PLoS ONE 18:e0292341. DOI: https://doi.org/10.1371/journal.pone.0292341

Anselin L, 1988. Spatial econometrics: methods and models. Springer Science & Business Media. (Vol. 4). Kluwer Academic Publishers. DOI: https://doi.org/10.1007/978-94-015-7799-1

Banerjee S, Carlin BP, Gelfand AE, 2003. Hierarchical modeling and analysis for spatial data. Chapman and Hall/CRC. DOI: https://doi.org/10.1201/9780203487808

Befort CA, Nazir N, Perri MG, 2012. Prevalence of obesity among adults from rural and urban areas of the United States: findings from NHANES (2005-2008). J Rural Health 28:392-7. DOI: https://doi.org/10.1111/j.1748-0361.2012.00411.x

Bivand RS, Pebesma EJ, Gómez-Rubio V, 2008. Applied spatial data analysis with R. New York, NY: Springer New York.

Braveman PA, Kumanyika S, Fielding J, Laveist T, Borrell LN, Manderscheid R, Troutman A, 2011. Health disparities and health equity: the issue is justice. Am J Public Health 101:S149-55. DOI: https://doi.org/10.2105/AJPH.2010.300062

Brenning A, 2012. Spatial cross-validation and bootstrap for the assessment of prediction rules in remote sensing: The R package sperrorest. IEEE international geoscience and remote sensing symposium. https://doi.org/10.1109/IGARSS.2012.6352393 DOI: https://doi.org/10.1109/IGARSS.2012.6352393

Brook RD, Rajagopalan S, Pope CA 3rd, Brook JR, Bhatnagar A, Diez-Roux AV, Holguin F, Hong Y, Luepker RV, Mittleman MA, Peters A, Siscovick D, Smith SC Jr, Whitsel L, Kaufman JD; American Heart Association Council on Epidemiology and Prevention, Council on the Kidney in Cardiovascular Disease, and Council on Nutrition, Physical Activity and Metabolism, 2010. Particulate matter air pollution and cardiovascular disease: An update to the scientific statement from the American Heart Association. Circulation 121:2331-78. DOI: https://doi.org/10.1161/CIR.0b013e3181dbece1

Brownson RC, Hoehner CM, Day K, Forsyth A, Sallis JF, 2009. Measuring the built environment for physical activity: State of the science. Am J Preventive Med 36:S99–S123.e12. DOI: https://doi.org/10.1016/j.amepre.2009.01.005

Brulle RJ, Pellow DN, 2006. Environmental justice: human health and environmental inequalities. Ann Rev Public Health 27:103-24. DOI: https://doi.org/10.1146/annurev.publhealth.27.021405.102124

Cain KL, Salmon J, Conway TL, Cerin E, Hinckson E, Mitas J, Schipperijn J, Frank LD, Anjana RM, Barnett A, Dygryn J, Islam MZ, Molina-Garcia J, Moran M, Wan Muda WAM, Oyeyemi AL, Reis R, Santos MP, Schmidt T, Schofield GM, Timperio A, Van Dyck D, Sallis JF, 2021. International Physical Activity and Built Environment Study of adolescents: IPEN Adolescent design, protocol and measures. BMJ Open 11:e046636. DOI: https://doi.org/10.1136/bmjopen-2020-046636

Carroll RJ, Ruppert D, Stefanski LA, Crainiceanu CM, 2006. Measurement error in nonlinear models: a modern perspective. Chapman and Hall/CRC. DOI: https://doi.org/10.1201/9781420010138

Dahu BM, Khan S, Toubal IE, Alshehri M, Martinez-Villar CI, Ogundele OB, Sheets LR, Scott GJ, 2024. Geospatial modeling of deep neural visual features for predicting obesity prevalence in Missouri: quantitative study. JMIR AI 3:e64362. DOI: https://doi.org/10.2196/64362

Diez Roux AV, 2002. A glossary for multilevel analysis. J Epidemiol Community Health 56:588-94. DOI: https://doi.org/10.1136/jech.56.8.588

Diez Roux AV, Mair C, 2010. Neighborhoods and health. Ann N Y Acad Sci 1186:125-45. DOI: https://doi.org/10.1111/j.1749-6632.2009.05333.x

Drewnowski A, 2009. Obesity, diets, and social inequalities. Nutrition Rev 67:36-S39. DOI: https://doi.org/10.1111/j.1753-4887.2009.00157.x

Filippelli GM, Laidlaw MAS, 2010. The elephant in the playground: confronting lead-contaminated soils as an important source of lead burdens to urban populations. Perspect Biol Med 53:31-45. DOI: https://doi.org/10.1353/pbm.0.0136

Fotheringham AS, Wong DW, 1991. The modifiable areal unit problem in multivariate statistical analysis. Environ Planning A 23:1025-44. DOI: https://doi.org/10.1068/a231025

Frank LD, Andresen MA, Schmid TL, 2004. Obesity relationships with community design, physical activity, and time spent in cars. Am J Prevent Med 27:87-96. DOI: https://doi.org/10.1016/j.amepre.2004.04.011

Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451 DOI: https://doi.org/10.1214/aos/1013203451

GBD 2017 Risk Factor Collaborators, 2018. Global, regional, and national comparative risk assessment of 84 behavioural, environmental and occupational, and metabolic risks or clusters of risks for 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet 392;1923-94.

Gotway CA, Young LJ, 2002. Combining incompatible spatial data. J Am Statist Assoc 97:632-48. DOI: https://doi.org/10.1198/016214502760047140

Grinsztajn L, Oyallon E, Varoquaux G, 2022. Why do tree-based models still outperform deep learning on typical tabular data? Adv Neural Informat Proces Systems 35:507–520. DOI: https://doi.org/10.52202/068431-0037

Hales CM, Carroll MD, Fryar CD, Ogden CL, 2020. Prevalence of obesity and severe obesity among adults: United States, 2017–2018 (NCHS Data Brief No. 360). National Center for Health Statistics. Available from: https://www.cdc.gov/nchs/products/databriefs/db360.htm

Hammond RA, 2009. Complex systems modeling for obesity research. Preventing Chronic Dis 6:A97.

Heindel JJ, Blumberg B, Cave M, Machtinger R, Mantovani A, Mendez MA, Nadal A, Palanza P, Panzica G, Sargis R, Vandenberg LN, Vom Saal F, 2017. Metabolism disrupting chemicals and metabolic disorders. Reprod Toxicol 68:3-33. DOI: https://doi.org/10.1016/j.reprotox.2016.10.001

Hruby A, Hu FB, 2015. The epidemiology of obesity: A big picture. Pharmacoeconomics 33:673–89. DOI: https://doi.org/10.1007/s40273-014-0243-x

James G, Witten D, Hastie T, Tibshirani R, Taylor J, 2023. An introduction to statistical learning: with applications in Python. Springer. DOI: https://doi.org/10.1007/978-3-031-38747-0

Jerrett M, Burnett RT, Ma R, Pope III CA, Krewski D, Newbold KB, Thun MJ, 2005. Spatial analysis of air pollution and mortality in Los Angeles. Epidemiology 16:727-36. DOI: https://doi.org/10.1097/01.ede.0000181630.15826.7d

Krieger N, Chen JT, Waterman PD, Rehkopf DH, Subramanian SV, 2003. Choosing area-based socioeconomic measures to monitor social inequalities in low birth weight and childhood lead poisoning: The Public Health Disparities Geocoding Project (US). J Epidemiol Comm Health 57:186–99. DOI: https://doi.org/10.1136/jech.57.3.186

Kuhn M, Johnson, K, 2013. Applied predictive modeling, Vol. 26. New York: Springer. DOI: https://doi.org/10.1007/978-1-4614-6849-3

Lawson AB, 2018. Bayesian disease mapping: hierarchical modeling in spatial epidemiology (3rd ed.). CRC Press. DOI: https://doi.org/10.1201/9781351271769-1

LeCun Y, Bengio Y, Hinton G, 2015. Deep learning. Nature 521:436–44. DOI: https://doi.org/10.1038/nature14539

Levin R, Brown MJ, Kashtock ME, Jacobs DE, Whelan EA, Rodman J, Schock MR, Padilla A, Sinks T, 2008. Lead exposures in U.S. Children, 2008: implications for prevention. Environ Health Perspect 116:1285-93. DOI: https://doi.org/10.1289/ehp.11241

Lind PM, Olsen L, Lind L, 2012. Elevated circulating levels of copper and nickel are found in elderly subjects with left ventricular hypertrophy. Ecotoxicol Environ Safety 86:66-72. DOI: https://doi.org/10.1016/j.ecoenv.2012.08.033

Longley PA, Goodchild MF, Maguire DJ, Rhind DW, 2015. Geographic information science and systems. John Wiley & Sons.

Lotfata A, Georganos S, Kalogirou S, Helbich M, 2022. Ecological associations between obesity prevalence and neighborhood determinants using spatial machine learning in Chicago, Illinois, USA. ISPRS Internat J Geo-Information 11:550. DOI: https://doi.org/10.3390/ijgi11110550

Meyer H, Reudenbach C, Wöllauer S, Nauss T, 2019. Importance of spatial predictor variable selection in machine learning applications–Moving from data reproduction to spatial prediction. Ecological Modelling 411:108815. DOI: https://doi.org/10.1016/j.ecolmodel.2019.108815

Mielke HW, Gonzales CR, Powell ET, 2019. Curtailing lead aerosols: effects of primary prevention on declining soil lead and children's blood lead in metropolitan New Orleans. Int J Environ Res Public Health 16:2068. DOI: https://doi.org/10.3390/ijerph16122068

Morgenstern H, 1995. Ecologic studies in epidemiology: Concepts, principles, and methods. Ann Rev Public Health 16:61–81. DOI: https://doi.org/10.1146/annurev.pu.16.050195.000425

Morgenstern H, 1998. Ecologic studies. In K. J. Rothman & S. Greenland (Eds.), Modern Epidemiology (2nd ed., pp. 459–480). Lippincott Williams & Wilkins.

Openshaw S, 1984. The modifiable areal unit problem. Concepts and techniques in modern geography. Geobooks.

Pearl J, 2009. Causality. Cambridge University Press. DOI: https://doi.org/10.1017/CBO9780511803161

Pickett KE, Pearl M, 2001. Multilevel analyses of neighbourhood socioeconomic context and health outcomes: A critical review. J Epidemiol Comm Health 55:111–22. DOI: https://doi.org/10.1136/jech.55.2.111

Robert SA, Reither EN, 2004. A multilevel analysis of race, community disadvantage, and body mass index among adults in the United States. Soc Sci Med 59:2421–34. DOI: https://doi.org/10.1016/j.socscimed.2004.03.034

Roberts DR, Bahn V, Ciuti S, Boyce MS, Elith J, Guillera‐Arroita G, Hauenstein S, Lahoz‐Monfort JJ, Schröder B, Thuiller W, Warton DI, Wintle BA, Hartig F, Dormann CF, 2017. Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography 40:913-29. DOI: https://doi.org/10.1111/ecog.02881

Ruzzin J, 2012. Public health concern behind the exposure to persistent organic pollutants and the risk of metabolic diseases. BMC Public Health 12:298. DOI: https://doi.org/10.1186/1471-2458-12-298

Sallis JF, Floyd MF, Rodriguez DA, Saelens BE, 2012. Role of built environments in physical activity, obesity, and cardiovascular disease. Circulation 125:729-37. DOI: https://doi.org/10.1161/CIRCULATIONAHA.110.969022

Shwartz-Ziv R, Armon A, 2022. Tabular data: Deep learning is not all you need. Information Fusion 81:84-90. DOI: https://doi.org/10.1016/j.inffus.2021.11.011

Sparks DL, Singh B, Siebecker MG, 2022. Environmental soil chemistry. Elsevier.

Swinburn BA, Sacks G, Hall KD, McPherson K, Finegood DT, Moodie ML, Gortmaker SL, 2011. The global obesity pandemic: shaped by global drivers and local environments. Lancet, 378: 378:804-14. DOI: https://doi.org/10.1016/S0140-6736(11)60813-1

Tchounwou PB, Yedjou CG, Patlolla AK, Sutton DJ, 2012. Heavy Metal Toxicity and the Environment. Exp Suppl 101:133-64. DOI: https://doi.org/10.1007/978-3-7643-8340-4_6

Thayer KA, Heindel JJ, Bucher JR, Gallo MA, 2012. Role of environmental chemicals in diabetes and obesity: a National Toxicology Program workshop review. Environ Health Perspect 120:779-89. DOI: https://doi.org/10.1289/ehp.1104597

U.S. Census Bureau, 1994. Geographic Areas Reference Manual. U.S. Department of Commerce, Economics and Statistics Administration.

United States Department of Agriculture, Natural Resources Conservation Service, 2021. Soil Survey Geographic Database (SSURGO). Available from: https://www.nrcs.usda.gov/resources/data-and-reports/soil-survey-geographic-database-ssurgo

Valavi R, Elith J, Lahoz-Monfort JJ, Guillera-Arroita G, 2019. blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models. Methods Ecol Evolut 10:225–32. DOI: https://doi.org/10.1111/2041-210X.13107

Wakefield J, 2008. Ecologic studies revisited. Ann Rev Public Health 29:75–90. DOI: https://doi.org/10.1146/annurev.publhealth.29.020907.090821

Wolpert DH, 1992. Stacked generalization. Neural Networks 5:241-59. DOI: https://doi.org/10.1016/S0893-6080(05)80023-1

Wood SN, 2017. Generalized additive models: an introduction with R. Chapman and Hall/CRC. DOI: https://doi.org/10.1201/9781315370279

Zhang X, Holt JB, Lu H, Wheaton AG, Ford ES, Greenlund KJ, Croft JB, 2014. Multilevel regression and poststratification for small-area estimation of population health outcomes: a case study of chronic obstructive pulmonary disease prevalence using the behavioral risk factor surveillance system. Am J Epidemiol 179:1025–33. DOI: https://doi.org/10.1093/aje/kwu018

Zou H, Hastie T, 2005. Regularization and variable selection via the elastic net. J Royal Statist Soc Series B: Statist Methodol 67:301-20. DOI: https://doi.org/10.1111/j.1467-9868.2005.00503.x