This article analyzes Reverse Logistics (RL) practices associated with the concept of Circular Economy (CE), comparing studies conducted before and after the implementation of the National Solid Waste Policy (NSWP) in Brazil. Data from companies in the Sul Fluminense region were analyzed using the Analytic Hierarchy Process to prioritize RL practices and identify those related to CE. The research included companies from nine Brazilian economic sectors that engage in some form of RL. The comparison of results aimed to evaluate the influence of the NSWP on these practices, with data analyzed using the Super Decisions software (version 3.2) to establish priorities and aggregate them using the Aggregating Individual Priorities method. It was observed that the implementation of the NSWP in 2010 emphasized the importance of sustainability. Although the concept of CE is recent, its operationalization is based on consolidated RL practices such as recycling, remanufacturing, and material reuse. The study provides insights to optimize and expand these practices, facilitating the transition from a linear economy to a circular one.

Objective: Low birth weight (LBW) is a public health problem strongly associated with infant mortality. This study aimed to identify the spatial distribution of infant mortality in newborns with LBW (750–2,500 g) at term (≥37 weeks of gestation), due to their being small for gestational age, analyzing its association with mother-related determinants, as well as to identify priority areas of mortality in the State of São Paulo, 2010–2019. Methods: Infant mortality rate was analyzed in the division of neonatal mortality and postneonatal mortality of newborns with LBW at term. The empirical Bayesian method smoothed the rates, the univariate Moran index was used to measure the degree of spatial association between the municipalities, and the bivariate Moran index was employed to identify the existence of a spatial association between the rates and the selected determinants. Thematic maps of excess risk and local Moran were prepared to identify spatial clusters, adopting 5% as a significance level. Results: The excess risk map showed that more than 30% of the municipalities had rates above the state rate. High-risk clusters were identified in the southwest, southeast, and east regions, mainly among more developed municipalities. The determinants of adolescent mothers, mothers over 34 years of age, low education, human development index, social vulnerability index, gross domestic product, physicians, and pediatric beds showed a significant association with the rates evaluated. Conclusions: Priority areas and significant determinants associated with reduced mortality in newborns with LBW were identified, suggesting the need for intervention measures to achieve the Sustainable Development Goal.

RESUMO Objetivo: Analisar a distribuição espacial dos nascimentos prematuros e sua associação com indicadores maternos, sociais e de serviços de saúde na região metropolitana de São Paulo, Brasil, 2010-2019. Métodos: Estudo ecológico utilizando dados sobre recém-nascidos pré-termo dos 39 municípios da região metropolitana de São Paulo. Utilizou-se o índice de Moran (Im) global univariado para avaliar a associação espacial da prematuridade, e o índice de Moran local univariado por meio do mapa de clusters (LISA) para a identificação de padrões e aglomerados espaciais. Também foi utilizado o índice de Moran global bivariado para analisar a autocorrelação espacial com os indicadores maternos, sociais e de serviços de saúde. Resultados: Foram registrados 3.103.898 nascidos vivos no período 2010-2019, dos quais 331.174 (10,7%) foram prematuros. O índice de Moran global mostrou independência espacial (Im=0,05; p-valor=0,233) da proporção dos nascimentos prematuros entre municípios. No entanto, na análise espacial local foi possível identificar aglomerado espacial estatisticamente significativo entre os municípios de Biritiba Mirim, Guararema e Salesópolis, com proporções altas de nascimentos pré-termo. Na análise bivariada, identificou-se associação espacial significativa positiva com proporções de mães menores de 20 anos (Im=0,17; p-valor=0,024) e mães com baixa escolaridade (Im=0,17; p-valor=0,020), e associação espacial significativa negativa com IDH (Im=-0,14; p-valor=0,039). Conclusão: A abordagem espacial local identificou agrupamento espacial situado no extremo leste da região metropolitana de São Paulo, onde ações dos gestores de saúde são necessárias para minimizar a ocorrência de partos prematuros.

Objective: To analyze spatial distribution of preterm births and their association with maternal, social, and health services indicators in the metropolitan region of São Paulo, Brazil, 2010-2019. Methods: Ecological study using data on preterm newborns from 39 municipalities in the metropolitan region of São Paulo. Univariate global Moran’s index (Im) was used to evaluate spatial association of prematurity, and univariate local Moran’s index by using the cluster map (LISA) to identify spatial patterns and clusters. Bivariate global Moran’s index was also used to analyze spatial autocorrelation with maternal, social, and health services indicators. Results: A total of 3,103,898 live births were registered in period 2010-2019, of which 331,174 (10.7%) were preterm. The global Moran’s index showed spatial independence (Im=0.05; p-value=0.233) of the proportion of preterm births between municipalities. However, in the local spatial analysis it was possible to identify a statistically significant spatial cluster between the municipalities of Biritiba Mirim, Guararema and Salesópolis, with high proportions of preterm births. In the bivariate analysis, a significant positive spatial association was identified with proportions of mothers under 20 years old (Im=0.17; p-value=0.024) and mothers with low schooling (Im=0.17; p-value=0.020), and a significant negative spatial association with HDI (Im=-0.14; p-value=0.039). Conclusions: The local spatial approach identified a spatial cluster located in the far east of the metropolitan region of São Paulo, where actions by health managers are needed to minimize occurrence of preterm births.

The emergence of Machine Learning (ML) technologies and their integration into agriculture has demonstrated a significant impact on disease detection in crops, enabling continuous monitoring and enhancing risk planning and management. This study applied image processing techniques such as thresholding, gamma correction, and the Stretched Neighborhood Effect Color to Grayscale (SNECG) method, alongside ML, to develop a predictive model for identifying five types of rice diseases. The ML techniques used included Logistic Regression, Multilayer Perceptron, Support Vector Machines, Decision Trees, and Random Forests (RF). Hyperparameters were optimized and evaluated through 5-fold cross-validation. In the results, the SNECG method successfully converted images to grayscale, capturing essential features of lesions on rice leaves. The ML models developed with these techniques showed evaluation metrics exceeding 80%, with the RF model (precision = 88.31%) demonstrating superior performance. Additionally, the RF model was integrated into an interface designed for agricultural decision-making. The practical application of the developed model could significantly improve the ability to detect and manage diseases in rice crops.