Optimizing Cervical Cancer Prediction, Harnessing the Power of Machine Learning for Early Diagnosis

Abstract

Cervical cancer is one of the most widespread ovarian cancers in the world. It is linked up with multiple risk factors such as Sexually transmitted diseases, human papillomavirus and smoking. Death rate can be reduced if early diagnosis is possible. In addition if early prediction can be possible it will help greatly patients as well as doctors to give them proper treatment immodestly. Our study focuses on various machine learning algorithms to forecast early detection of cervical cancer. Dataset for this work has been collected from kaggle.com. The given dataset consists of various demographic and medical features related to an individual’s sexual and reproductive health. With proper tuning of parameters using cross-validation in the training set, the XGB Classifier achieves an accuracy of 98% and a ROC AUC of 99%.