Comprehensive Analysis of Machine and Deep Learning Models for Breast Cancer Diagnosis and Risk Assessment with Diverse Datasets

Breast cancer, a pervasive global health challenge, demands innovative diagnostic approaches for timely intervention and improved outcomes. This study presents an extensive investigation into the application of machine learning (ML) and deep learning (DL) techniques for breast cancer diagnosis and risk assessment. Utilizing the Wisconsin Breast Cancer Database (WBCD) and the NKI Breast Cancer dataset, our study employs a diverse range of ML models, including Support Vector Machines, Random Forests, Decision Trees, K-nearest neighbors, Naive Bayes, and Logistic Regression, alongside DL models such as Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). The investigation incorporates comprehensive data preprocessing, feature selection, and 10fold cross-validation to optimize model performance. Results showease the CNN outperformed with $98.24 \%$ accuracy on the WBCD dataset, while the Decision Tree model leads on the NKI dataset with $91 \%$. Precision, recall, and F1-Score metrics provide a nuanced evaluation of model efficacy. The study not only addresses the limitations of previous works but also introduces a holistic approach, emphasizing the significance of diverse datasets in enhancing breast cancer diagnostic accuracy that holds promise for impactful advancements in healthcare. The findings pave the way for practical applications, including the development of a userfriendly mobile application for personalized breast cancer detection and risk evaluation to foster personalized and timely interventions.