Covid-19 Risk Prediction with Ensemble Boosting Algorithms

Abstract

COVID-19 risk prediction using machine learning techniques is an active area of research and development. Using machine learning algorithms, it is possible to identify individuals who are at high risk of developing severe symptoms if they are infected with the virus. The prediction is based on several factors such as age, gender, underlying medical conditions, and other demographic information. This study aims to introduce a Covid-19 risk prediction methodology based on ensemble boosting algorithms. To verify the effectiveness of the applied ensemble boosting algorithms, we compare them with a variety of well-known classification algorithms on a dataset containing 18 features and 1,048,576 unique patients. The results indicate that ensemble boosting algorithms can perform better in risk prediction than other classifiers. When comparing the boosting models, it is observed that all of them produce similar results, but LightGBM is computationally the most efficient in comparison to the other ensemble boosting algorithms.

Ähnliche Arbeiten