An Extensive Analysis of Machine Learning Models to Predict the Breast Cancer Recurrence

Abstract

This paper presents an in-depth exploration of various machine-learning models for predicting breast cancer recurrence. Leveraging a comprehensive dataset, we systematically evaluate the performance of multiple algorithms, considering factors such as accuracy, sensitivity, specificity, and computational efficiency.

The forecasting system was developed using fourteen varied machine learning (ML) methods to predict the likelihood of breast cancer recurrence. The prognostic model's performance was evaluated using multiple measures including the area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score. Following this assessment, the most appropriate machine learning (ML) algorithm was selected, and the significance of features was identified.

Through rigorous experimentation and analysis, we identify key insights into the strengths and limitations of different approaches, offering valuable guidance for selecting the most suitable model for breast cancer recurrence prediction. The findings contribute to enhancing the accuracy and interpretability of breast cancer recurrence prediction systems, thereby facilitating informed clinical decision-making.