Scholarlink

<p>The disease known as COVID-19, which arises from the complex and diverse family of coronaviruses, has significantly progressed into a global pandemic that has been associated with a multitude of adverse consequences affecting both individuals and the broader societal fabric. These repercussions encompass a wide array of detrimental effects on immune health, overall well-being, substantial economic downturns, rising unemployment rates, and a stark inadequacy of medical resources available to combat the crisis. In this context, the timely and accurate diagnosis of COVID-19 emerges as the single most vital strategy for effectively managing the disease, with the overarching goal of reducing mortality rates while simultaneously curbing its rampant transmission across various communities. In the pursuit of this objective, researchers have explored a variety of diagnostic methodologies tailored for COVID-19, with a predominant reliance on advanced imaging techniques such as computed tomography (CT) scans and chest X-rays, while also emphasizing the application of innovative data mining approaches, particularly those rooted in machine learning and deep learning paradigms. The primary focus of this scholarly paper is to meticulously investigate the strategies based on machine learning and deep learning that are employed for the purpose of forecasting the trajectory and impact of COVID-19. Empirical findings derived from various studies indicate that the implementations of deep learning technologies in the realm of COVID-19 diagnosis generally yield faster approximate solutions when juxtaposed with conventional data mining algorithms, as well as more traditional and established diagnostic techniques. Consequently, this results in markedly superior outcomes when such deep learning methods are compared against deterministic algorithms that have historically been utilized in similar contexts. Thus, the ongoing evolution of diagnostic technologies continues to play a pivotal role in shaping the future landscape of public health responses to pandemics, particularly in relation to COVID-19. In conclusion, the integration of machine learning and deep learning methodologies into the diagnostic processes represents not only a significant advancement in medical technology but also a critical step towards improving the overall efficacy of healthcare systems in managing infectious diseases.</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

A comprehensive review of the methods of intelligent diagnosis and prediction of COVID-19 disease using machine learning and deep learning techniques

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月29日

查看全文
  • Rasoul Farahi,
  • Mehri Pakzad

摘要

The disease known as COVID-19, which arises from the complex and diverse family of coronaviruses, has significantly progressed into a global pandemic that has been associated with a multitude of adverse consequences affecting both individuals and the broader societal fabric. These repercussions encompass a wide array of detrimental effects on immune health, overall well-being, substantial economic downturns, rising unemployment rates, and a stark inadequacy of medical resources available to combat the crisis. In this context, the timely and accurate diagnosis of COVID-19 emerges as the single most vital strategy for effectively managing the disease, with the overarching goal of reducing mortality rates while simultaneously curbing its rampant transmission across various communities. In the pursuit of this objective, researchers have explored a variety of diagnostic methodologies tailored for COVID-19, with a predominant reliance on advanced imaging techniques such as computed tomography (CT) scans and chest X-rays, while also emphasizing the application of innovative data mining approaches, particularly those rooted in machine learning and deep learning paradigms. The primary focus of this scholarly paper is to meticulously investigate the strategies based on machine learning and deep learning that are employed for the purpose of forecasting the trajectory and impact of COVID-19. Empirical findings derived from various studies indicate that the implementations of deep learning technologies in the realm of COVID-19 diagnosis generally yield faster approximate solutions when juxtaposed with conventional data mining algorithms, as well as more traditional and established diagnostic techniques. Consequently, this results in markedly superior outcomes when such deep learning methods are compared against deterministic algorithms that have historically been utilized in similar contexts. Thus, the ongoing evolution of diagnostic technologies continues to play a pivotal role in shaping the future landscape of public health responses to pandemics, particularly in relation to COVID-19. In conclusion, the integration of machine learning and deep learning methodologies into the diagnostic processes represents not only a significant advancement in medical technology but also a critical step towards improving the overall efficacy of healthcare systems in managing infectious diseases.