Applying formal concept analysis to characterize infant mortality

Abstract

Infant mortality is characterized by the death of children under one year of age, a problem that affects a large part of the world’s population. In this context, we applied Formal Concept Analysis (FCA), a mathematical technique used in data analysis, to characterize infant mortality in two regions of the state of Minas Gerais: Belo Horizonte and Vale do Jequitinhonha. The aim is to describe infant mortality through data sets from the SIM and SINASC repositories. With FCA, concepts and rules that determine the main factors that contribute to infant mortality were extracted. Three scenarios were created for analysis. The first pointing out that weight, gestation, and APGAR are determinants for the child’s survival. In the second neonatal periods were used indicating that mortality, in the scenario where the child is born with low weight and early gestation, is higher than in the post-neonatal period. The third scenario was analyzed based on the International Classification of Diseases (ICD) indicating factors for mortality such as conditions and malformations in the post-neonatal period. The results reveal associations between different variables, allowing the profile of infant mortality to be traced in each region.