District-Level Food Environment Indicators and Social Vulnerability in São Paulo
Authors: Pedro Lemes Sixel Lobo, Eric Tokuda, Kuruvilla Joseph Abraham, Roberto Fray, Dirce Maria Marchioni, Alexandre Cláudio Botazzo Delbem, Rogerio Salvini
Organizations: Instituto de Informática, Universidade Federal de Goiás, Goiânia, GO, Brazil · Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos, SP, Brazil · Escola Superior de Agricultura Luiz de Queiroz da Universidade de São Paulo, USP, Piracicaba, SP, Brazil · Faculdade de Saúde Pública, USP, São Paulo, SP, Brazil
Urban food environments may reflect broader socioeconomic inequalities, but district-level evidence remains limited in Brazilian cities. This study examined whether indicators of food retail and street-market availability discriminate between levels of social vulnerability across the 96 districts of São Paulo. We conducted an exploratory cross-sectional ecological analysis integrating the São Paulo Social Vulnerability Index (IPVS), establishment records from the Relação Anual de Informações Sociais (RAIS), and street-market data from CAISAN. Census-sector information was aggregated at the district level. Twenty districts without an IPVS classification were excluded, resulting in 76 observations. The outcome distinguished districts classified as IPVS level 1 from those classified as levels 2--7. Predictors described the densities of healthy and unhealthy food establishments, the number of street markets, and the availability of establishments selling fresh or in natura food. Eight conventional machine-learning classifiers were evaluated using leave-one-out cross-validation. Reported mean F-scores ranged from 0.62 to 0.75, with XGBoost obtaining the highest value. In the Random Forest model, the densities of healthy and unhealthy food establishments jointly accounted for approximately 60% of the total impurity-based feature importance. These findings indicate that publicly available food-environment indicators contain information associated with the district-level distribution of social vulnerability. However, the small ecological sample, class imbalance, outcome binarization, and cross-sectional design limit predictive generalization and preclude causal or household-level interpretations.
Figures & tables
Compression
Comparison
Statistic
Significance
min
Mean–median
0.9219
0.00029997
min
Mean–no reduction
0.7770
9.999×10−5
min
Median–no reduction
0.9114
9.999×10−5
gzip
Mean–median
0.6425
0.00019998
gzip
Mean–no reduction
0.4476
0.0065993
gzip
Median–no reduction
0.8404
9.999×10−5
TABLE I: Mantel-test results comparing distance matrices obtained before and after district-level aggregation.
Index
IPVS category
# districts
0
Not classified
20
1
Extremely low vulnerability
56
2
Very low vulnerability
7
3
Low vulnerability
8
4
Medium vulnerability
1
5
High vulnerability (urban)
0
TABLE II: Distribution of IPVS categories across the 96 districts of São Paulo.
Variable
Type
Observed range
Density of healthy establishments
Continuous
8.31–192.41
Density of unhealthy establishments
Continuous
0.00–172.92
Number of street markets
Integer
0–22
Number of natural-food establishments
Integer
1–125
Establishments selling in natura food
Integer
3–147
São Paulo Social Vulnerability Index
Integer
0–7
TABLE III: Food-environment predictors and outcome used in the analysis.
Model
F-score
KNN
0.62 (0.49)
LDA
0.72 (0.45)
NB
0.71 (0.45)
DT
0.68 (0.46)
RF
0.70 (0.46)
GB
0.68 (0.46)
TABLE IV: Mean F-score and standard deviation obtained by the classification models under leave-one-out cross-validation.
Fig. 1: Impurity-based importance of the food-environment variables in the Random Forest model.
Model
Hyperparameters
KNN
leaf_size =1; n_neighbors =1; p =2; weights = uniform
Urban planning uses geospatial data, machine learning, and optimization to analyze cities and guide transport, land use, housing, and climate decisions.
Area-based social risk indices summarize residents' socioeconomic conditions but incompletely capture physical features of place that may affect health. We evaluated whether numerical representations of physical place produced by four geospatial foundation model families from 2022 satellite data explained residual variance in tract-level associations between the Area Deprivation Index, Social Deprivation Index, and Social Vulnerability Index with health outcomes. We used LightGBM to predict variables from the American Community Survey and 40 chronic disease and health-behavior outcomes from CDC PLACES across 82,646 census tracts in the contiguous United States, evaluating performance across 10 held-out states. Among survey variables, models were moderately predictive of some variables including housing type (R-squared up to 0.54) but weak for disability, unemployment, and income disparity. For health outcomes, models explained up to 54% of variance left unexplained by social risk indices, with the largest gains for annual checkups, arthritis, and high blood pressure. Mean total variance explained by geospatial foundation models across the 40 health-related outcomes increased from 0.31 in the smallest tract-size decile to 0.39 in the largest. Geospatial foundation models capture health-relevant features of place not represented by conventional social risk indices and may usefully augment them in epidemiological analyses.
Nathaniel Hendrix, Carl Y. Zhang, Chris Heitzig +2
Center for Professionalism and Value in Health Care, American Board of Family Medicine 1016 16th St NW Ste 800 Washington, DC 20036 United States of America · Stanford Center on Longevity, Stanford University Palo Alto, CA USA · Center for Population Health Sciences, School of Medicine, Stanford University Palo Alto, California, United States of America +1
Accurate, up-to-date income data at the sub-municipal scale is essential for social policy in middle-income countries, yet in Brazil it depends on a costly decennial census whose intercensal gap recently exceeded a decade. We test whether the composition of crowd-sourced Google Maps Points of Interest (POIs) can serve as a high-frequency, low-cost proxy for household income across the 26,625 census sectors of the municipality of Sao Paulo. Using a theoretically motivated set of POI categories retrieved from Google Places, we represent each sector by its POI counts, decompose these high-dimensional, sparse features with principal component analysis (PCA) and non-negative matrix factorization (NMF), and train a sweep of regression models to predict census-derived income. Under a data leakage-aware spatial validation design the best model (NMF with gradient boosting) attains a held-out R^2 of 0.65, with performance stable across feature-extraction methods. Interpretable decompositions reveal which POI types carry the income signal. These results suggest that commercial, crowd-sourced geospatial data can complement conventional income statistics during intercensal periods, and we discuss extensions toward multidimensional poverty and the capabilities framework.
Adrienne C. Kinney, Anya Workman, Ademar Takeo Akabane +5
Hastings Initiative for AI and Humanity, Bowdoin College, Brunswick, Maine, United States · Department of Digital and Computational Studies, Bowdoin College, Brunswick, Maine, United States · Postgraduate Program in Urban Infrastructure Systems, Polytechnique School, Pontifical Catholic University of Campinas, Campinas, São Paulo, Brazil +3
Food access is multidimensional, but population-level measurement still relies heavily on geography because perceived dimensions of access are difficult to measure at scale. Here, we use 25,125 Google Maps reviews from 49 grocery stores in Raleigh, North Carolina, to measure five dimensions of food access: availability, accessibility, affordability, accommodation, and acceptability. We identify review topics with unsupervised topic modeling and assign them to access dimensions using zero-shot classification, with 85.4% agreement against manual coding. The resulting store-level measures capture distinct aspects of food access and reveal barriers that geographic proximity alone does not capture. Comparisons between nearby stores in the same chain further show that identical store policies can be perceived very differently across locations, consistent with food access reflecting the fit between residents and their food environment. Perceived food access also follows systematic socioeconomic and demographic patterns that broadly parallel, but do not replicate, those observed for geographic access. These results show that online grocery reviews can provide a scalable complement to geographic measures of food access.
Teresa Groton, Benjamin rachunok
Operations Research Department, North Carolina State University, Raleigh, 27607, United States of America · Industrial and Systems Engineering Department, North Carolina State University, Raleigh, 27607, United States of America