Machine learning research towards combating COVID-19: Virus detection, spread prevention, and medical assistance

Area of Science:

• Medical Informatics
• Artificial Intelligence
• Epidemiology

Background:

• The COVID-19 pandemic, originating in December 2019, has caused a global health crisis.
• High-risk populations include individuals with pre-existing conditions and those over 60.
• The urgent need for effective diagnostic and therapeutic strategies is paramount.

Purpose of the Study:

• To survey the role of Machine Learning (ML) in addressing the COVID-19 pandemic.
• To explore ML applications in screening, forecasting the spread, and vaccine development.
• To provide a comprehensive overview of ML algorithms applicable to combating the virus.

Main Methods:

• Literature review of Machine Learning applications in COVID-19 research.
• Categorization of ML algorithms based on their use in screening, forecasting, and vaccine discovery.
• Analysis of existing ML models and their performance in pandemic response.

Main Results:

• Machine Learning is instrumental in developing rapid diagnostic tools for COVID-19.
• ML models demonstrate significant potential in predicting epidemic trajectories and resource allocation.
• ML accelerates the identification of potential vaccine candidates and therapeutic targets.

Conclusions:

• Machine Learning offers powerful tools to enhance COVID-19 screening, tracking, and prediction.
• Continued research and implementation of ML are crucial for effective pandemic management and future outbreak preparedness.
• ML integration into healthcare systems can significantly improve response to global health emergencies.