International Journal For Multidisciplinary Research

E-ISSN: 2582-2160     Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 4 (July-August 2025) Submit your research before last 3 days of August to publish your research paper in the issue of July-August.

Artificial Intelligence Approaches for COVID-19 Detection Using Boosting Algorithms

Author(s) Ms. Chitra Devi Thangavelu, Ms. Abinaya R, Ms. Dhanvandhini S, Mr. Sivakumar R
Country India
Abstract The ongoing global impact of the COVID-19 pandemic has underscored the need for rapid, accurate, and accessible diagnostic tools. In this study, we present an artificial intelligence (AI)-driven framework for the diagnosis of COVID-19 using four state-of-the-art boosting-based machine learning algorithms: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Gradient Boosting, and Categorical Boosting (CatBoost). These models were trained and evaluated using a dataset comprising both clinical and demographic features of patients, enabling the identification of infection status based on readily available health indicators. The evaluation of model performance was conducted using standard classification metrics such as accuracy, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC). Among the models tested, CatBoost and XGBoost demonstrated superior recall and AUC values, making them especially valuable in minimizing false negatives a critical factor in disease detection scenarios where missed cases can lead to further transmission and delayed treatment. The study emphasizes that boosting algorithms, particularly CatBoost and XGBoost, are not only accurate but also computationally efficient and well-suited for handling structured tabular data. Their effectiveness in this application supports their potential integration into clinical decision support systems, especially in resource-constrained healthcare environments where diagnostic capabilities are limited. Overall, the findings validate the utility of boosting-based AI models as robust, scalable, and practical solutions for enhancing early COVID-19 detection and aiding frontline medical practitioners in timely decision-making.
Keywords COVID-19 Diagnosis, Machine Learning, Boosting Algorithms, XGBoost, AdaBoost, Gradient Boosting, Binary Classification, CatBoost
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 4, July-August 2025
Published On 2025-07-27
DOI https://doi.org/10.36948/ijfmr.2025.v07i04.51705
Short DOI https://doi.org/g9vpkm

Share this