International Journal of Computer Techniques Volume 12 Issue 5 | Cancer Detection and Classification using Random Forest, NN and XGBoost Algorithm of Machine Learning
Cancer Detection and Classification using Random Forest, NN and XGBoost Algorithm of Machine Learning
Authors: Manasa T P, Dr. Mohammed Tajuddin
Department of Computer Science & Engineering, Dayananda Sagar College of Engineering, Bangalore Institute of Technology, Visveswaraya Technological University, Bengaluru, Karnataka, India
Emails: tpmanasa@bit-bangalore.edu.in, tajuddin-cs@dayanandasagar.edu
Journal: International Journal of Computer Techniques (IJCT)
Volume: 12 | Issue: 5 | Page: 100 | Publication Date: September – October 2025
ISSN: 2394-2231 | Journal URL: https://ijctjournal.org/
Abstract
This paper proposes a machine learning–based framework for cancer detection and classification using Random Forest, Neural Networks, and XGBoost. The system achieved 99.45% accuracy and 99.95% AUC in cancer detection, and 93.94% accuracy in cancer type classification. The study highlights the effectiveness of ML and DL algorithms in early diagnosis and decision support for healthcare applications.
Keywords
Human Healthcare, Random Forest, Recognition, CNN, XGBoost
Conclusion
The proposed system demonstrates high accuracy in detecting and classifying cancer types using ML algorithms. It supports timely diagnosis and contributes to improved patient outcomes. Future work may explore integration with real-time clinical data and multimodal analysis for broader applicability.
References
Includes 14+ references from Clinical Chemistry, Science Translational Medicine, NCCN Guidelines, and Nature Reviews Cancer covering biomarkers, screening protocols, and ML applications in oncology.
