Scholarlink

<p>Air pollution is the fifth and sixth leading risk factor for global mortality and reduced life expectancy. Studies have established a link between atmospheric pollution and the incidence, hospitalization, and mortality rates of pulmonary tuberculosis (PTB). The city of Zabol has experienced persistent dust storms for several years, with an average annual PM<sub>10</sub> concentration of 206&#xa0;µg/m³—more than nine times the permissible limit. The results of this study indicate a significant correlation between increased PM<sub>10</sub> levels and the incidence of tuberculosis. To model the disease, machine learning (ML) techniques, including support vector machines (SVM) and k-nearest neighbors (KNN), were employed. Among these, SVM demonstrated the highest accuracy, with a correlation coefficient of 92.4% between the experimental data and the model’s training outputs.</p>

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

Investigation of tuberculosis incidence and particulate matter concentration in the middle east

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月21日

查看全文
  • Morteza Esfandyari,
  • Maryam Sarkhosh,
  • Javad Shahraki,
  • Aliasghar Najafpoor,
  • Saeed Akhlaghi

摘要

Air pollution is the fifth and sixth leading risk factor for global mortality and reduced life expectancy. Studies have established a link between atmospheric pollution and the incidence, hospitalization, and mortality rates of pulmonary tuberculosis (PTB). The city of Zabol has experienced persistent dust storms for several years, with an average annual PM10 concentration of 206 µg/m³—more than nine times the permissible limit. The results of this study indicate a significant correlation between increased PM10 levels and the incidence of tuberculosis. To model the disease, machine learning (ML) techniques, including support vector machines (SVM) and k-nearest neighbors (KNN), were employed. Among these, SVM demonstrated the highest accuracy, with a correlation coefficient of 92.4% between the experimental data and the model’s training outputs.