Análise da acessibilidade geográfica para pessoas hipertensas na cidade de Fortaleza-CE

• Ano de defesa: 2024
• Autor(a) principal: Borges, Joao Manoel da Silva Lins
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Palavras-chave em Português: Pesquisa espacial; Ciência de dados; Hipertensão arterial
• Link de acesso: https://biblioteca.sophia.com.br/terminalri/9575/acervo/detalhe/586183

Cardiovascular Diseases (CVD) are among the leading causes of death in Brazil and worldwide. An example is Hypertension, which, being a silent disease, is the main risk factor for CVD. With advances in technology, there is a growing availability of health data, providing opportunities to extract significant findings. This work aims to identify the variables most correlated with the distance traveled by users to Primary Health Care Units (PHCUs) to request a prescription for antihypertensive medication. The analysis seeks to assist public health managers by providing information on the geographic accessibility of hypertensive patients in Fortaleza, to improve the planning and allocation of resources, ensuring better access and quality of health services offered to the hypertensive population. The Euclidean distance traveled by users averaged about 1 kilometer. When grouping the data by PHCUs, the main results revealed that the attributes total number of prescriptions issued, number of health professionals, minimum distance to the bus stop, and age had the highest correlations, with values of 0.38, 0.34, -0.25, and -0.21, respectively. Regarding multiple linear regression, which estimates the relationship between a dependent variable and one or more independent variables, being used to predict values, the attributes that best contributed to the coefficient of determination (R²) were quantity of prescriptions issued, Human Development Index (HDI) of the neighborhood, age, and number of bus stops near the PHCUs. The model with these four variables resulted in an R² of 0.284. Keywords: Spatial Analysis. Data Science. Hypertension. Public Health.