Exploratory analysis identified logistic regression and random forest as effective in breast cancer diagnosis models, indicating potential for resource-constrained settings.
Key Points
Accuracy can be achieved in breast cancer diagnosis with fewer variables in machine learning models, demonstrating efficiency.
The random forest classifier and logistic regression delivered high performance in classifying tumors as malignant or benign.
Using the Wisconsin Breast Cancer Dataset, machine learning models were evaluated based on sensitivity, specificity, and accuracy.
This approach can improve early detection of breast cancer in regions with limited diagnostic resources.