Comparative Analysis of Machine Learning Techniques for Cervical Cancer Prediction

This chapter delves into the comparative analysis of machine learning techniques for predicting cervical cancer, focusing on Decision Trees, Artificial Neural Networks (ANN), Naive Bayes classifiers, K-Nearest Neighbours (KNN), and Support Vector Machines (SVM). The study evaluates these algorithms using the WEKA and Orange platforms, providing a thorough assessment of their predictive accuracy, sensitivity, and specificity. The dataset, sourced from Kaggle, includes a diverse set of important characteristics and elements, offering a valuable resource for examination. The research highlights the importance of selecting the appropriate algorithm based on data type, problem complexity, and computational requirements. The experimental results reveal that Decision Trees achieved the highest accuracy, followed closely by KNN and SVM. The study concludes that while each algorithm has its advantages and disadvantages, the optimal choice depends on factors such as data type, problem complexity, and the specific requirements of the application. This analysis provides valuable insights for practitioners and researchers interested in utilizing data-driven approaches in healthcare and other fields.