Machine Learning Classification of FNA-Derived Cell Nuclei Features for Breast Cancer Prediction

In the female population worldwide, breast cancer is a prevalent and potentially lethal form of malignancy. Timely and precise identification is essential for enhancing patient results. The main objective of this work is to use logistic regression to classify breast cancer as malignant or benign using the Breast Cancer Wisconsin (Diagnostic) dataset. Features extracted from digitized pictures of fine needle aspirate (FNA) of breast masses are included in the collection. The reliability of the logistic regression model was assessed using several performance measures, such as accuracy, precision, recall, and F1-score. The model exhibited strong performance with a precision of 95.32% on the test set, underscoring its potential as a very efficient instrument for diagnosing breast cancer. Due to its straightforwardness and comprehensibility, these results indicate that logistic regression can be a valuable supplement to the diagnostic process, facilitating early identification and improving patient results.