The rise in cancer cases worldwide, particularly in India, necessitates the
development of quick and accurate diagnosis methods. A new initiative aims to utilize
machine learning to enhance cancer gene detection, thereby saving time and reducing
manual labor in conventional diagnostic procedures. The MERN stack tool and a
machine learning algorithm are utilized to create a full-stack website that rapidly
identifies probable malignant mutations. The approach combines Naive Bayes, Linear
Regression, and Random Forest Classifier models for data processing and analysis.
This cutting-edge strategy aims to revolutionize cancer diagnosis, enabling prompt and
potentially life-saving therapies. This initiative represents a technological achievement
and a crucial step towards reducing cancer prevalence. Additionally, our proposed
model achieves an accuracy of 88 percent. The core contribution of this work lies in the
integration of multiple machine learning algorithms into a unified, full-stack cancer
gene detection system—capable of handling various cancer types, deployed in realtime via cloud infrastructure, and designed for practical clinical use through high
performance, feature explanation ability, and accessibility.
Keywords: Cancer, Classification, Genes, Health system, Linear regression, Machine learning, Naive bayes, Random forest.
