Scholarlink

<p>A pandemic is a disease outbreak&#xa0;that affects an alarmingly high percentage of the population and spreads over a large geographic area. Some diseases are more likely to start pandemics because they are contagious and can cause&#xa0;severe illness or death. The most recent lethal disease to emerge and cause global devastation among all other pandemics is COVID-19. Since the COVID-19 disease breakout in December 2019, it has become a global pandemic that has caused millions of people throughout the planet. Modern information technology applications have emerged as a result of the pandemic’s heightened demand for healthcare products and services. To effectively manage future pandemic-prone diseases and slow their vigorous spread, their early detection is crucial. New-age technologies, such as artificial intelligence, internet of things, cloud computing, etc., are therefore a major asset in the fight against such terrible diseases. Therefore, the current study employs the proposed architecture of a recurrent neural network (RNN) for the accurate identification of patients infected with COVID-19 disease through analysis of its major symptoms. Before classification, extra trees-based feature selection was used to collect the most significant features that accurately characterize COVID-19 positive or COVID-19 negative classes. This work also takes into account several deep learning models viz., RNN, Bi-LSTM, GRU, LSTM along with other machine learning models such as Logistic Regression to identify the COVID-19 pandemic. The thorough analysis of results shows that, the RNN classifier appears to perform better than the other classifiers in the early diagnosis of this fatal disease, with an accuracy of 98.70%, sensitivity of 97.81%, specificity of 95.55%, precision value equal to 98.97%, F1-score of 96.16%, and false discovery rate of 1.03% only. Therefore, the proposed RNN-based approach can help identify fatal infections caused by pandemic-prone diseases at an early stage, enabling timely intervention and containment.</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

Recurrent neural network-based automated early detection of pandemic-prone diseases through symptoms analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月8日

查看全文
  • Aditika Tungal,
  • Kuldeep Singh,
  • Prabhsimran Singh,
  • Ateeq Ur Rehman,
  • Sandeep Sood,
  • Vishnu Kant,
  • Anand Kumar,
  • Seada Hussen,
  • Habib Hamam

摘要

A pandemic is a disease outbreak that affects an alarmingly high percentage of the population and spreads over a large geographic area. Some diseases are more likely to start pandemics because they are contagious and can cause severe illness or death. The most recent lethal disease to emerge and cause global devastation among all other pandemics is COVID-19. Since the COVID-19 disease breakout in December 2019, it has become a global pandemic that has caused millions of people throughout the planet. Modern information technology applications have emerged as a result of the pandemic’s heightened demand for healthcare products and services. To effectively manage future pandemic-prone diseases and slow their vigorous spread, their early detection is crucial. New-age technologies, such as artificial intelligence, internet of things, cloud computing, etc., are therefore a major asset in the fight against such terrible diseases. Therefore, the current study employs the proposed architecture of a recurrent neural network (RNN) for the accurate identification of patients infected with COVID-19 disease through analysis of its major symptoms. Before classification, extra trees-based feature selection was used to collect the most significant features that accurately characterize COVID-19 positive or COVID-19 negative classes. This work also takes into account several deep learning models viz., RNN, Bi-LSTM, GRU, LSTM along with other machine learning models such as Logistic Regression to identify the COVID-19 pandemic. The thorough analysis of results shows that, the RNN classifier appears to perform better than the other classifiers in the early diagnosis of this fatal disease, with an accuracy of 98.70%, sensitivity of 97.81%, specificity of 95.55%, precision value equal to 98.97%, F1-score of 96.16%, and false discovery rate of 1.03% only. Therefore, the proposed RNN-based approach can help identify fatal infections caused by pandemic-prone diseases at an early stage, enabling timely intervention and containment.