Profile of deaths mentioning ischemic and hemorrhagic stroke in Brazil: a population-based machine learning analysis

Brazil has the highest stroke rates in Latin America. The aim of this study was to investigate the profile of deaths mentioning stroke in Brazil between 2000 and 2019 and the relationship between multiple causes of death and stroke subtype. Deaths mentioning stroke and other conditions were identified using individual death records from the country’s mortality information system (SIM). Strokes were grouped into the following subtypes according to the International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10) codes: ischemic stroke (IS); hemorrhagic stroke (HS); and unspecified stroke (US). Descriptive statistics were used to describe the distribution of stroke subtypes by demographic category, region and period. A decision tree model was built to identify the strongest factors distinguishing IS from HS. There were 2,459,742 deaths mentioning stroke. The following sociodemographic groups accounted for the highest proportion of overall deaths in their respective categories: the 60-79 age group (46.6%); white people (57%); married people (41.9%); and people with less than 3 years of education (62.1%). There was a progressive increase in the number of deaths mentioning stroke over the study period. The most common type of stroke was US, accounting for more than 60% of deaths. The most frequent group of causes of death in the subtype HS was hypertensive diseases (40.6%), while the most frequent group in subtypes IS and US was diseases of the respiratory system (48.30% and 42.30%, respectively). The decision tree analysis revealed that IS was more likely to occur in patients aged 60 years and over and in cases where respiratory diseases, endocrine diseases, arrhythmias, ischemic heart disease and heart failure were present. However, in younger patients without the previous mentioned diseases but where diseases of the nervous system were present HS was more frequent. The analysis of multiple causes of death enabled the identification of different diseases and factors associated with deaths mentioning IS, HS and US. The decision tree analysis identified the strongest factors distinguishing IS from HS. These findings can serve as guidance for defining the specific needs of each stroke subtype.