A Survey on Machine and Deep Learning Techniques for Breast Cancer Prediction

Breast cancer is a leading cause of cancer-related mortality among women worldwide, making early and accurate diagnosis essential for effective treatment and improved patient outcomes.In recent years, machine learning (ML) and deep learning (DL) techniques have emerged as promising tools for predicting and classifying breast cancer using gene expression and clinical data.However, existing studies face several limitations.Many rely solely on ML or DL approaches, lack comprehensive strategies for feature selection or extraction, and demonstrate inconsistent performance across datasets.These gaps result in models that are insufficiently accurate, uninterpretable, or unable to generalize well to unseen data.This work aims to address these challenges by conducting a detailed literature survey of existing ML and DL models applied to breast cancer prediction.The objectives include identifying common datasets, performance metrics, model types, and feature-engineering techniques.A structured methodology was followed to analyze peer-reviewed studies and extract trends in performance and limitations.Findings show that, while DL models outperform traditional ML in terms of accuracy, they often lack transparency and robust feature engineering.In conclusion, a unified approach combining advanced feature selection and extraction methods with DL techniques is necessary to develop accurate, generalizable breast cancer prediction systems.