A New Enhanced Predictive Model for Cervical Cancer Classification based on CatBoost and CNN Algorithms

Cervical cancer is a disease affecting women worldwide, including in impoverished countries, and it poses a significant threat to their reproductive health. The main drawback of this cancer is that it shows no early signs. Additionally, social factors and individual errors during manual testing hinder screening for this disease. Therefore, developing a model using machine learning and deep learning is a significant and trustworthy option that offers greater support than traditional detection methods. In this research, we used two powerful algorithms (CatBoost and CNN) to tackle the problem of cervical cancer classification. Two datasets are used: the “<em>Risk Factors Cervical Cancer</em>” and “ <em>Malhari</em>”, where the first dataset is textual data. After applying the CatBoost algorithm, we reached an accuracy of 100% for “ <em>Kag Risk Factors Cervical Cancer</em>” data. The second dataset has two types of images (“ <em>Pap S mear</em>” and “<em>Colposcopy</em>”), where we reached an accuracy of 87.2% for the “ <em>Pap S mear</em>” type, and 91.1% for the “<em>Colposcopy</em>” type by applying the newly developed CNN algorithm.