Stroke Deaths Profile and Its Subtypes in Brazil: Analysis Using Machine Learning.

IF 3.1 3区医学 Q2 CARDIAC & CARDIOVASCULAR SYSTEMS

Global Heart Pub Date : 2025-10-03 eCollection Date: 2025-01-01 DOI:10.5334/gh.1476

Alessandro Rocha Milan de Souza, Letícia Martins Raposo, Glenda Corrêa Borges de Lacerda, Paulo Henrique Godoy

{"title":"Stroke Deaths Profile and Its Subtypes in Brazil: Analysis Using Machine Learning.","authors":"Alessandro Rocha Milan de Souza, Letícia Martins Raposo, Glenda Corrêa Borges de Lacerda, Paulo Henrique Godoy","doi":"10.5334/gh.1476","DOIUrl":null,"url":null,"abstract":"Background: Brazil has one of the highest stroke rates in Latin America. It is important to understand the impact of other causes of death and sociodemographic factors, as this may contribute to a better comprehension of the stroke mortality process. Machine learning provides a means to explain this process.Objective: To investigate the stroke deaths profile and its subtype in Brazil using machine learning.Methods: This is a time series analysis where deaths mentioning stroke and other conditions were identified using individual death records from the country's mortality information system (SIM) between 2000 and 2019. Strokes were grouped into the following subtypes: ischemic stroke (IS), hemorrhagic stroke (HS), and unspecified stroke (US). A decision tree model was built to identify the strongest factors distinguishing IS from HS.Results: There were 2,459,742 deaths mentioning stroke. 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 62% of deaths. Among HS deaths, hypertensive diseases were the most frequent group of associated causes (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, HS was more frequent in younger patients without these conditions but with nervous system diseases.Conclusions: The decision tree analysis identified the strongest factors distinguishing IS from HS, highlighting variables involved in each subtype of stroke-related death that can be recognized in clinical practice. These variables may also support the redistribution of deaths initially classified as unspecified stroke.","PeriodicalId":56018,"journal":{"name":"Global Heart","volume":"20 1","pages":"85"},"PeriodicalIF":3.1000,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12493032/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Heart","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.5334/gh.1476","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Brazil has one of the highest stroke rates in Latin America. It is important to understand the impact of other causes of death and sociodemographic factors, as this may contribute to a better comprehension of the stroke mortality process. Machine learning provides a means to explain this process.

Objective: To investigate the stroke deaths profile and its subtype in Brazil using machine learning.

Methods: This is a time series analysis where deaths mentioning stroke and other conditions were identified using individual death records from the country's mortality information system (SIM) between 2000 and 2019. Strokes were grouped into the following subtypes: ischemic stroke (IS), hemorrhagic stroke (HS), and unspecified stroke (US). A decision tree model was built to identify the strongest factors distinguishing IS from HS.

Results: There were 2,459,742 deaths mentioning stroke. 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 62% of deaths. Among HS deaths, hypertensive diseases were the most frequent group of associated causes (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, HS was more frequent in younger patients without these conditions but with nervous system diseases.

Conclusions: The decision tree analysis identified the strongest factors distinguishing IS from HS, highlighting variables involved in each subtype of stroke-related death that can be recognized in clinical practice. These variables may also support the redistribution of deaths initially classified as unspecified stroke.

Abstract Image

查看原文本刊更多论文

巴西中风死亡概况及其亚型：使用机器学习的分析

背景：巴西是拉丁美洲中风发病率最高的国家之一。了解其他死亡原因和社会人口因素的影响很重要，因为这可能有助于更好地理解中风死亡过程。机器学习提供了一种解释这一过程的方法。目的：利用机器学习研究巴西脑卒中死亡概况及其亚型。方法：这是一项时间序列分析，其中使用2000年至2019年期间国家死亡率信息系统（SIM）中的个人死亡记录确定涉及中风和其他疾病的死亡。卒中分为以下亚型：缺血性卒中（IS），出血性卒中（HS）和未明确的卒中（US）。建立了决策树模型来识别区分IS和HS的最强因素。结果：有2,459,742例死亡与中风有关。在研究期间，涉及中风的死亡人数逐渐增加。最常见的中风类型是美国，占死亡人数的62%以上。HS死亡中，高血压疾病是最常见的相关原因组（40.6%），而IS和US亚型中最常见的相关原因组是呼吸系统疾病（分别为48.30%和42.30%）。决策树分析显示，IS更有可能发生在60岁及以上的患者以及存在呼吸系统疾病、内分泌疾病、心律失常、缺血性心脏病和心力衰竭的患者中。然而，HS在没有这些疾病但有神经系统疾病的年轻患者中更为常见。结论：决策树分析确定了区分IS和HS的最强因素，突出了在临床实践中可以识别的卒中相关死亡的每个亚型所涉及的变量。这些变量也可能支持最初归类为未明确中风的死亡的重新分配。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Global Heart Medicine-Cardiology and Cardiovascular Medicine

CiteScore

5.70

自引率

5.40%

发文量

审稿时长

5 weeks

期刊介绍： Global Heart offers a forum for dialogue and education on research, developments, trends, solutions and public health programs related to the prevention and control of cardiovascular diseases (CVDs) worldwide, with a special focus on low- and middle-income countries (LMICs). Manuscripts should address not only the extent or epidemiology of the problem, but also describe interventions to effectively control and prevent CVDs and the underlying factors. The emphasis should be on approaches applicable in settings with limited resources. Economic evaluations of successful interventions are particularly welcome. We will also consider negative findings if important. While reports of hospital or clinic-based treatments are not excluded, particularly if they have broad implications for cost-effective disease control or prevention, we give priority to papers addressing community-based activities. We encourage submissions on cardiovascular surveillance and health policies, professional education, ethical issues and technological innovations related to prevention. Global Heart is particularly interested in publishing data from updated national or regional demographic health surveys, World Health Organization or Global Burden of Disease data, large clinical disease databases or registries. Systematic reviews or meta-analyses on globally relevant topics are welcome. We will also consider clinical research that has special relevance to LMICs, e.g. using validated instruments to assess health-related quality-of-life in patients from LMICs, innovative diagnostic-therapeutic applications, real-world effectiveness clinical trials, research methods (innovative methodologic papers, with emphasis on low-cost research methods or novel application of methods in low resource settings), and papers pertaining to cardiovascular health promotion and policy (quantitative evaluation of health programs.