Cervical Cancer Prediction Using Machine Learning

Abstract

Cervical cancer is one of the deadliest diseases among women globally, particularly in low-income countries where early detection and treatment are limited. This project proposes a Machine Learning-based Prediction System to detect the risk of cervical cancer at an early stage. By analyzing various factors such as age, sexual health, hormonal usage, genetic history, and prior diagnoses, the system applies classification techniques to estimate the risk category. A Decision Tree classifier is employed to model patterns and identify frequent combinations of high-risk attributes. The system predicts the likelihood and stage of cervical cancer by assigning risk scores based on patient inputs and classifying them into risk levels: low, intermediate, high, and very high. This automated approach supports medical practitioners by improving diagnostic accuracy and enabling timely intervention. The project is built using Python, MySQL, and Anaconda, offering a scalable and interpretable diagnostic tool for early-stage cervical cancer prediction. Keywords: Sign language, information retrieval, computer vision, natural language processing, accessibility, deaf individuals.