Cervical Cancer Prediction Using XG boost

Cervical cancer is a disease that predominantly affects women and is frequently fatal. Contrarily, early cervical cancer identification reduces mortality and other impacts. Early detection of cervical cancer might be aided by risk factors. We suggested research for the early diagnosis of cervical cancer using three ensemble-based classification approaches, including extreme Gradient Boosting (XGBoost) for optimisation. The study makes use of the 36 risk variables and the four objectives from the data collection on cervical cancer risk factors (Hinselmann, Schiller, Cytology, and Biopsy). The four objectives form the cornerstone of the most widely used cervical cancer detection techniques. The success of the suggested research is evaluated using its accuracy, sensitivity, specificity, positive predictive accuracy (PPA), and negative predictive accuracy (NPA). A technique was also used to provide better results with less characteristics. Less traits have also resulted in better outcomes. When compared to earlier benchmark studies for cervical cancer detection using a reduced risk factors data set, the suggested models exhibit noticeably better accuracy.