Abstract: Cervical cancer is a major public health problem affecting women worldwide. Early diagnosis and treatment of cervical cancer can greatly improve patient outcomes. Machine learning methods can increase the accuracy and efficiency of cervical cancer diagnosis. This project aims to improve the diagnosis of cervical cancer using several machine learning algorithms, including CatBoost, SVM, logistic regression, decision trees, and Naive Bayes classification.

We collect and pre-process patient information related to cervical cancer, such as medical records, examination results and biopsy reports. Train and evaluate each machine learning algorithm on your data and compare their performance. The results of this project will help determine which machine learning algorithms are most effective in improving the diagnosis of cervical cancer. This project has the potential to contribute to the development of more accurate and effective tools for the diagnosis of cervical cancer.

 
Keywords: CatBoost, SVM, Logistic Regression, Decision Tree.

| DOI: 10.17148/IARJSET.2023.10505