Prediction of Breast Cancer using K-Nearest Neighbors Algorithm
Dr. Pravin Game
Department of Computer Engineering
Pimpri Chinchwad College of Engineering
Pune, Maharashtra
pravin.game@pccoepune.org
Gayatri Galange
Department of Computer Engineering
Pimpri Chinchwad College of Engineering
Pune, Maharashtra
gayati.galange20@pccoepune.org
Aakanksha Ghodake
Department of Computer Engineering
Pimpri Chinchwad College of Engineering
Pune, Maharashtra
aakanksha.ghodake20@pccoepune.org
Khushbu Bhonde
Department of Computer Engineering
Pimpri Chinchwad College of Engineering
Pune, Maharashtra
khushbu.bhonde20@pccoepune.org
Sakshi Divakar
Department of Computer Engineering
Pimpri Chinchwad College of Engineering
Pune, Maharashtra
sakshi.divakar20@pccoepune.org
Abstract—Breast cancer is a disease in which cells in the human breast grow and divide in an uncontrolled way, creating a mass of tissue called a tumor. Breast cancer can occur in both men and women, but it is much more common in women. The exact cause of breast cancer is not known, but it is believed to be a combination of genetic and environmental factors. The K-Nearest Neighbors (KNN) algorithm is a machine learning algorithm that can be used for prediction tasks such as breast cancer prediction. This algorithm is a nonparametric, simple, and intuitive algorithm that is easy to understand and implement. Unlike other machine learning algorithms, the KNN algorithm does not require a separate training phase and is effective with small datasets, where the number of training samples is limited. When properly tuned and trained, the KNN algorithm can achieve high accuracy in classification tasks, including breast cancer prediction. Overall, the KNN algorithm can be a good choice to predict whether a given breast tumor is malignant (cancerous) or benign (non-cancerous) due to its simplicity, flexibility, and effectiveness with small or high-dimensional datasets. Through implementation and studies, it is found that KNN for breast cancer prediction gives promising results. The accuracy of the K Nearest Neighbour method was found to be 96.5% after implementation. This study highlights the potential of machine learning algorithms in improving breast cancer diagnosis and can aid in clinical decision-making.
Keywords— Benign, Malignant, Machine learning, Thermal Imaging, Classification, Breast Cancer, Tumor, Decision tree.
