1*Research Scholar, Department of Computer Science & Engineering, Bhagwant University, Ajmer, Rajasthan, India, 305023
2Assistant Professor, Department of Computer Engineering, Mahila Engineering College, Ajmer, Rajasthan, India, 305002
3Professor, Department of Electrical and Electronics Engineering, Bhagwant University, Ajmer, Rajasthan, India, 305023
One of the most prevalent diseases among women globally is breast cancer, and early, precise detection greatly enhances prediction and treatment outcomes. Using tabular diagnostic data, this study gives an in-depth review of a number of popular machine learning methods for breast cancer detection. The methodology covers data preprocessing, feature engineering, model development, and evaluation protocols. Support Vector Machines, K-Nearest Neighbors, Decision Trees, Random Forests, Gradient Boosting, Multilayer Perceptron, and Logistic Regression are among the models that are analysed. Accuracy, precision, recall, F1-score, and ROC AUC are incorporated in stratified cross-validation to evaluate performance. In addition, we analyse each model's benefits as well as drawbacks, highlight feature importance as well as interpretability aspects, and provide recommendations for selecting suitable models in clinical decision-support applications.
Keywords: Breast Cancer Detection, Machine Learning, Classification, Logistic Regression, Random Forests, Support Vector Machine.
How to cite this article: Singh YA, Kumar SV. Adaptive Machine Learning Models for Breast Cancer Detection: Accuracy-Based Evaluation. Int J Drug Deliv Technol. 2026;16(10s): 551-557; DOI: 10.25258/ijddt.16.10s.68
Source of support: Nil.
Conflict of interest: None