Scholarlink

In December 2019, a new coronavirus emerged in Wuhan, Hubei province, China, giving rise to the disease named COVID-19, caused by SARS-CoV-2, a highly contagious severe acute respiratory virus. Rapidly spreading outside China, the WHO declared a pandemic in March 2020. Symptoms of infection include fever, weakness, dry cough, headache, dyspnoea, myalgia, as well as blood abnormalities and other biochemical indicators. In view of the rapid spread of COVID-19, it is becoming imperative to explore the use of machine learning techniques for a variety of applications, such as accurate and rapid diagnosis, as well as the detection of individuals most likely to contract the disease. The aim of this article is to present a method for the early identification of patients at increased risk of developing severe symptoms of COVID-19, using a database available in Côte d'Ivoire. Through the application of machine learning techniques, we solve a classification problem to predict the state (negative, positive) of individuals in relation to COVID-19. Models were trained on 80% of the dataset, while the remaining 20% was used for testing. The results of the model performance evaluation indicate that the decision tree model shows the highest accuracy, reaching 97%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of COVID-19 Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Diako Doffou Jérome,
  • Johnson Grâce Yénin Edwige,
  • Sandjé Marcelin,
  • Patrice E. Mensah

摘要

In December 2019, a new coronavirus emerged in Wuhan, Hubei province, China, giving rise to the disease named COVID-19, caused by SARS-CoV-2, a highly contagious severe acute respiratory virus. Rapidly spreading outside China, the WHO declared a pandemic in March 2020. Symptoms of infection include fever, weakness, dry cough, headache, dyspnoea, myalgia, as well as blood abnormalities and other biochemical indicators. In view of the rapid spread of COVID-19, it is becoming imperative to explore the use of machine learning techniques for a variety of applications, such as accurate and rapid diagnosis, as well as the detection of individuals most likely to contract the disease. The aim of this article is to present a method for the early identification of patients at increased risk of developing severe symptoms of COVID-19, using a database available in Côte d'Ivoire. Through the application of machine learning techniques, we solve a classification problem to predict the state (negative, positive) of individuals in relation to COVID-19. Models were trained on 80% of the dataset, while the remaining 20% was used for testing. The results of the model performance evaluation indicate that the decision tree model shows the highest accuracy, reaching 97%.