Najwa Meilani
Politeknik Negeri Jember

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Breast Cancer Classification Using the C4.5 Method with the Breast Cancer Wisconsin Dataset Najwa Meilani; Intan Novitasari; Aprilia Wulandari; Naurah Ananda; Muhammad Yunus
Journal of Public Health and Community Systems Vol. 1 No. 1 (2026): June
Publisher : PT Litera Integra Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67580/nexura.v1i1.14

Abstract

Breast cancer is one of the most life-threatening diseases in the world, particularly among women. This study applies the C4.5 algorithm to classify breast cancer using the Breast Cancer Wisconsin (Diagnostic) Dataset from the UCI Machine Learning Repository, consisting of 569 samples with 30 numerical features. The methods employed include data preprocessing (removal of the ID column), application of the Decision Tree algorithm with entropy criterion representing the Information Gain Ratio in a Python- and Streamlit-based implementation, and model evaluation using an 80:20 data split. Experimental results show that the C4.5 model achieves an accuracy of 95.6%, with an average Precision of 95.7%, average Recall of 95.6%, and average F1-Score of 95.6%. The perimeter_worst attribute was identified as the root node of the decision tree with a threshold value of 114.45, confirming the dominant role of tumor cell geometry size as a predictor of malignancy. This study concludes that the C4.5 algorithm is an effective and interpretable approach for breast cancer classification and has the potential to serve as the basis for a clinical decision support system in oncology.