Comparative Study Based on Analysis of Coronavirus Disease (COVID-19) Detection and Prediction Using Machine Learning...

Area of Science:

• Computer Science
• Medicine
• Public Health

Background:

• The COVID-19 pandemic has highlighted the need for accurate disease prediction.
• Existing diagnostic methods lack 100% accuracy, necessitating advanced prediction strategies.
• Supervised learning methods are increasingly recognized for their predictive capabilities.

Purpose of the Study:

• To evaluate and compare machine learning models for identifying and forecasting infectious diseases, including COVID-19.
• To determine the most effective machine learning approach for disease diagnosis and prediction.
• To enhance public health strategies through reliable disease forecasting.

Main Methods:

• Utilizing supervised learning techniques, specifically classification and regression models.
• Comparing the performance of various machine learning algorithms for disease prediction.
• Analyzing input variables and derived outputs to optimize prediction accuracy.

Main Results:

• Supervised learning models generally outperform unsupervised methods in disease prediction accuracy.
• Classification models demonstrate superior performance compared to other machine learning models.
• The study identifies key models for effective disease detection and forecasting.

Conclusions:

• Machine learning, particularly classification models, offers a promising avenue for accurate disease prediction.
• Implementing robust prediction mechanisms is crucial for managing public health crises like COVID-19.
• Further research into supervised learning can significantly aid in disease diagnosis and survival rates.