1Professor and HOD, Department of CSE (AI&ML), Malla Reddy College of Engineering and Technology & MRTC, MRV, Maisammaguda, Hyderabad, Telangana, India. Email: dranagaraju.cse@gmail.com
2Assistant Professor, Department of Computer Science, University College for Women (A), VCIWU (Veeranari Chakali Ilamma Women's University), Hyderabad, Telangana. Email: shekarreddy08@gmail.com
3Associate Professor, Department of CSE, School of Engineering, Anurag University, Hyderabad, Telangana State. Email: shyamprasadcse@anurag.edu.in
Chronic Obstructive Pulmonary Disease (COPD) is a progressive respiratory condition that poses a significant global health challenge. Early detection and risk prediction are essential to enable timely clinical intervention and reduce long-term complications. This project presents an intelligent COPD Risk Prediction System powered by machine learning and an interactive web interface for efficient risk assessment. The system is designed with flexibility—utilizing a single, high-accuracy model trained on comprehensive medical data, including demographic, lifestyle, and clinical parameters. Multiple algorithms, such as Logistic Regression, Random Forest, XGBoost, CatBoost, and Gradient Boosting, were evaluated using accuracy, confusion matrix, and classification reports. The best-performing model is deployed through a real-time Streamlit interface, allowing users to input their details and instantly receive COPD risk classification as Low, Medium, or High. This approach demonstrates the potential of combining predictive analytics with an accessible, user-friendly platform to support early COPD detection—especially in rural health centers, telemedicine services, and public screening programs where advanced diagnostic tools may be limited.
Keywords: NA
How to cite this article: Nagaraju A, Shekar Reddy T, Shyam Prasad T. Gradient Boosting Algorithm For Chronic Obstructive Pulmonary Disease (COPD) Risk Prediction In Machine Learning. Int J Drug Deliv Technol. 2026;16(15s): 1089-1096. DOI: 10.25258/ijddt.16.15s.120
Source of support: Nil.
Conflict of interest: None