Prediction and Diagnosis of Breast Cancer Using Machine Learning Algorithms

Syed Shafi Ahmed

Department of Statistics, University of Lucknow, Lucknow, India.

Yash Srivastava *

Department of Statistics, University of Lucknow, Lucknow, India.

Mohd. Ghalib Khan

Centre of Biostatistics, Institute of Medical Sciences, BHU, India.

*Author to whom correspondence should be addressed.


Abstract

Breast cancer is one of the most prevalent and fatal forms of cancer in India. It ranks the second most common cancer in rural areas and the most common in urban areas. According to a report by the International Agency for Research on Cancer, there were over 2.26 million new breast cancer cases and nearly 685,000 deaths from breast cancer globally. With a significant portion of India's population being young, the number of women diagnosed with breast cancer is expected to increase, reaching alarming levels due to a lack of awareness and delays in diagnosis. While breast cancer cannot be prevented, early detection and timely treatment can significantly improve survival rates. This study uses K-Nearest Neighbour (K-NN), Random Forest, Decision Trees (CART), Support Vector Machine (SVM), and Naïve Bayes to aid oncologists in identifying and diagnosing breast cancer, thereby assisting in treatment decision-making. We present a predictive model for the early detection of breast cancer and compare the results of the employed models for effective detection.

Keywords: Machine learning, breast cancer, classification, prediction


How to Cite

Ahmed, Syed Shafi, Yash Srivastava, and Mohd. Ghalib Khan. 2024. “Prediction and Diagnosis of Breast Cancer Using Machine Learning Algorithms”. Asian Journal of Research in Medical and Pharmaceutical Sciences 13 (3):54-60. https://doi.org/10.9734/ajrimps/2024/v13i3261.