Abstract: Breast cancer is one of the leading types of cancer in the world, affecting many people every year. Early diagnosis with high accuracy is vital for treatment and patient care. In this project, publicly available cancer data sets from the University of California, Irvine Repository (kaggle.com) were analysed. Data analysis reveals that cancer morphological features, such as radius, perimeter, and area, exhibit a very high correlation coefficient in the detection process. The decision tree model revealed that the concave point is a highly relevant predictor, with a threshold of 0.048 to distinguish between malignant and benign tumors. The logistic regression model achieved an accuracy of 80.95% and an F1 score of 0.75, indicating good overall classification performance; however, a precision score of 0.60 suggests a moderate capability to minimize false predictions. By leveraging machine learning models and interactive dashboards (utilizing advanced data analytics and visualization), the work supports healthcare professionals in making more informed decisions regarding tumor classification and patient care.

Keywords: Breast Cancer, Interactive Dashboard, Machine Learning, Visualization Tool, Detection/Risk Management

Download: | DOI: 10.17148/IMRJR.2026.030107