Search

Abstract Objective The present study intends to describe the profile of hospitalization and ambulatory rehabilitation of patients ≥ 50 years old due to hip fracture in the Brazilian Public Health System (SUS, in the Portuguese acronym). Methods This is a cross-sectional study of patients hospitalized due to hip fracture in the SUS between 2008 and 2017. Data included 441,787 hip fracture-related hospitalizations from the hospitalization database of the department of informatics of the Brazilian Unified Health System (SIH/DATASUS, in the Portuguese acronym), and data of patients who underwent rehabilitation from the ambulatory database of the department of informatics of the Brazilian Unified Health System (SIA/DATASUS, in the Portuguese acronym.). Results Most of hip fracture-related hospitalizations (83.5%) happen to people ≥ 50 years old, with an average annual growth of 5.6% in hip fracture-related hospitalizations. The costs for the government have been growing in the same proportion and reached almost BRL 130 million in 2017, although with a 13.6% decrease in average cost per hospitalization. Besides the financial impact, hip fractures result in an in-hospital mortality rate around 5.0% in patients aged ≥ 50 years old. In addition, the percentage of patients that have undergone hip fracture-related rehabilitation increased from 2008 (14.0%) to 2012 (40.0%), and remained stable after that. Conclusions The progressive increase in the incidence of hip fractures shows the financial and social impact, and the need for immediate actions to prevent this rising trend. Hip fractures are a risk for secondary fractures, the prevention is crucial, and the orthopedist plays a central role in this process.

Objectives: Our aim was to test if machine learning algorithms can predict cancer mortality (CM) at an ecological level and use these results to identify statistically significant spatial clusters of excess cancer mortality (eCM).Methods: Age-standardized CM was extracted from the official databases of Brazil. Predictive features included sociodemographic and health coverage variables. Machine learning algorithms were selected and trained with 70% of the data, and the performance was tested with the remaining 30%. Clusters of eCM were identified using SatScan. Additionally, separate analyses were performed for the 10 most frequent cancer types.Results: The gradient boosting trees algorithm presented the highest coefficient of determination (R2 = 0.66). For total cancer, all algorithms overlapped in the region of Bagé (27% eCM). For esophageal cancer, all algorithms overlapped in west Rio Grande do Sul (48%–96% eCM). The most significant cluster for stomach cancer was in Macapá (82% eCM). The most important variables were the percentage of the white population and residents with computers.Conclusion: We found consistent and well-defined geographic regions in Brazil with significantly higher than expected cancer mortality.