Detection of Cervical Cancer using ML Algorithms

Abstract

Cervical cancer is one of the leading causes of cancer-related deaths among women worldwide, particularly in low- and middle-income regions where access to regular screening and early diagnostic services is limited. Despite being highly preventable and curable when detected in its early stages, late diagnosis remains a major challenge due to the reliance on traditional screening methods such as Pap smears and HPV tests, which require laboratory infrastructure, trained medical professionals, and are prone to human interpretation errors. With advancements in artificial intelligence and data-driven healthcare analytics, there is a growing opportunity to support clinical decision-making through automated diagnostic assistance. This project presents a machine learning–based predictive system designed to assess the likelihood of cervical cancer using demographic, behavioral, and medical risk factor data. The dataset undergoes preprocessing steps including handling missing values, data normalization, and feature selection to ensure model reliability and robustness. Multiple classification algorithms such as Logistic Regression, Support Vector Machine (SVM), Decision Tree, and Random Forest are trained and evaluated, with Random Forest demonstrating superior performance in terms of accuracy, precision, sensitivity, and overall predictive capability. The system is integrated into a user-friendly interface that allows healthcare practitioners or patients to input relevant information and receive real-time risk assessment results, potentially enabling earlier intervention and reducing the burden on medical personnel. By providing an accessible and scalable screening tool, this work highlights the significant role of machine learning in improving cervical cancer awareness, supporting early diagnosis, and enhancing healthcare outcomes, especially in resource-constrained settings.