A Study on Cervical Cancer Prediction using Various Machine Learning Approaches

Abstract

Cervical cancer is a major cause of mortality for women, and early detection is crucial for successful treatment Recent studies have investigated the use of machine learning for early detection of cervical cancer, but challenges remain. This paper evaluates the performance of different machine learning algorithms, including logistic regression, bagging, random forest, and XG Boost, for predicting cervical cancer. The study analyzes challenges in working with cervical cancer data, such as dealing with imbalanced datasets and limited data availability. To address these challenges, the paper proposes an approach that combines the strengths of the different algorithms to develop a more accurate and reliable model for early detection of cervical cancer. To assess the effectiveness of the proposed approach, the study uses standard metrics, including accuracy, precision, recall, and F1 score. The findings indicate that the proposed approach outperforms the individual machine learning algorithms in terms of predictive accuracy and precision. The paper emphasizes the need for further research in this area and highlights the potential of machine learning to enhance the early detection of cervical cancer. By proposing a new approach that addresses the challenges faced by existing methods, the paper aims to contribute to efforts to improve cervical cancer detection and treatment.