An analytical prediction of breast cancer using machine learning.

Chilukuri, N.V.S. Guru Sai Sarma; Bano, Shahana; Tholeti, Guru Sree Ram; Kamma, Sai Pavan; Niharika, Gorsa Lakshmi

Abstract

Breast cancer is one of the most frequent cancers among women, affecting about 2 million people. There is 98% chance of 5-years survival rate if detected at early stage. The data about breast cancer used in this paper is the Wisconsin dataset, which is taken from Kaggle. This is a classification problem; there are two classes (0 representing a non-malignant tumor, 1 representing malignancy). Min-max scalar is used for preprocessing of data, to limit data within certain range (known as scaling). The algorithms used for classification are support vector classifier, random forest, naïve Bayes, decision tree and k-nearest neighbours. Evaluation metrics - such as area under curve-rectified operational characteristics curve, confusion matrix, recall score - were used to determine accuracy. To avoid overfitting, cross validation is used where k fold value is 3. Support vector classifier and random forest gave the highest accuracy.

Citation

CHILUKURI, N.V.S.G.S.S., BANO, S., THOLETI, G.S.R., KAMMA, S.P. and NIHARIKA, G.L. 2022. An analytical prediction of breast cancer using machine learning. In Kumar, A., Senatore, S. and Gunjan, V.K. (eds.) Proceedings of the 2nd International conference on data science, machine learning and applications (ICDSMLA 2020), 21-22 November 2020, Pune, India. Lecture notes in electrical engineering, 783. Singapore: Springer [online], pages 185-202. Available from: https://doi.org/10.1007/978-981-16-3690-5_17

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2nd International conference on data science, machine learning and applications (ICDSMLA 2020)
• Start Date: Nov 21, 2020
• End Date: Nov 22, 2020
• Acceptance Date: Oct 15, 2020
• Online Publication Date: Nov 9, 2021
• Publication Date: Dec 31, 2022
• Deposit Date: Jun 7, 2024
• Publicly Available Date: Jun 7, 2024
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 185-202
• Series Title: Lecture notes in electrical engineering
• Series Number: 783
• Series ISSN: 1876-1100; 1876-1119
• ISBN: 9789811636899
• DOI: https://doi.org/10.1007/978-981-16-3690-5_17
• Keywords: Breast cancer detection; Artificial neural networks; Artificial intelligence and medicine; Random forests; Decision trees
• Public URL: https://rgu-repository.worktribe.com/output/2063956