You have no items in your shopping cart.
ABSTRACT
One of the most prevalent malignancies in women today is ovarian cancer. Ovarian cancer has fewer symptoms in its early stages. Ovarian cancer is important because the prognosis of ovarian cancer allows patients to use clinical potential. In this study, a novel method for the automatic detection of ovarian cancer using machine learning models was demonstrated. This method integrates ensemble and feature selection techniques. Ovarian cancer data from Kaggle was included in the dataset utilized in this investigation. Although missing values are first disputed, preparing the data balances the values. Six classifiers, including SVM, KNN, Logistic regression, Naive bayes, MLP, and Decision tree, are used to categorize the features. Three feature selection methods, including Chisquare, information gain, and gain ratio, extract the most important features. The goal of the work is to efficiently use ensemble and feature selection approaches to data in order to develop a computational model that can predict ovarian cancer. This work will help oncologists in the near future by giving patients a second way to forecast their diagnosis using the SVM feature selection model, which increases the predictive model's accuracy.
