索引于
  • 学术期刊数据库
  • 打开 J 门
  • Genamics 期刊搜索
  • 期刊目录
  • 中国知网(CNKI)
  • 西马戈
  • 乌尔里希的期刊目录
  • 参考搜索
  • 哈姆达大学
  • 亚利桑那州EBSCO
  • OCLC-WorldCat
  • 普布隆斯
  • 米亚尔
  • 大学教育资助委员会
  • 日内瓦医学教育与研究基金会
  • 欧洲酒吧
  • 谷歌学术
分享此页面

抽象的

Comparing Decision Tree-Based Ensemble Machine Learning Models for COVID-19 Death Probability Profiling

Carlos Pedro Goncalves*, Jose Rouco

Background: Age group, sex and underlying comorbidity or disease have been identified as major risk factors in COVID-19 severity and death risk.

Aim: We compare the performance of major decision tree-based ensemble machine learning models on the task of COVID-19 death probability prediction, conditional on three risk factors: age group, sex and underlying comorbidity or disease, using the US Centers for Disease Control and Prevention (CDC)’s COVID-19 case surveillance dataset.

Method: To evaluate the impact of the three risk factors on COVID-19 death probability, we extract and analyze the conditional probability profile produced by the best performing model.

Result: The results show the presence of an exponential rise in death probability from COVID-19 with the age group, with males exhibiting a higher exponential growth rate than females, an effect that is stronger when an underlying comorbidity or disease is present, which also acts as an accelerator of COVID-19 death probability rise for both male and female subjects. These results are discussed in connection to healthcare and epidemiological concerns and in the degree to which they reinforce findings coming from other studies on COVID-19.