Enhancing Breast Cancer Prediction: A Comparative Study of Machine Learning Algorithms

Abstract — In this study, a comparative research analysis was performed of three of the most significant Machine Learning algorithms, namely Logistic Regression, Random Forest, and K Nearest Neighbors (KNN) to improve the model for breast cancer prediction. Using the complete patient data set comprising 569 patients, we assessed the predictive accuracy of all the showcases of the algorithms. The results showed that Logistic Regression achieved the highest accuracy at 97.37%, followed nearly by Random Forest at 96.49%, and KNN at 94.74%. These outcomes show the effectiveness of machine learning in increasing the practical accuracy of breast cancer prediction and, highlighting the importance of algorithm selection based on performance metrics. This study aims to contribute to the ongoing efforts to enhance early diagnosis and personalized treatment strategies for breast cancer patients, thereby improving overall patient outcomes. Index Terms— Breast Cancer, Machine Learning Algorithms, Prediction, Healthcare, Random Forest, Logistic Regression, K-Nearest Neighbours.