A Cloud Based Breast Cancer Risk Prediction (BCRP) System

• Published in: High Performance Computing and Networking Vol. 853; pp. 535 - 549
• Main Authors: Desai, Madhavi B., Mistry, Vipul H.
• Format: Book Chapter
• Language: English
• Published: Singapore Springer 2022; Springer Singapore
• Series: Lecture Notes in Electrical Engineering
• Subjects: Breast cancer; Gradient boosting; KNN; Logistic regression; Machine learning; Prediction
• ISBN: 9789811698842; 9811698848
• ISSN: 1876-1100; 1876-1119
• DOI: 10.1007/978-981-16-9885-9_44

Breast cancer is one of the main causes of cancer across the world for women. Early diagnostics of cancer considerably increases the chances of correct treatment and survival. However, this diagnosis process is tedious and often leads to a disagreement between pathologists. Machine learning algorithms and computer aided tools have significant potential for improvement in diagnosis process. It is a need of time to implement an Artificial Intelligence based breast cancer risk prediction system. In this paper our aim to develop a cloud based model that is capable of detecting the breast cancer at an early stages. In the pre-processing stage, missing values are replaced by mean and one hot encoding method is used for converting categorical attributes of dataset into numeric. This paper also analyzes the performance of various classification models i.e., Logistic Regression, Decision Tree, Naïve Bayes, Gradient Boosting, Random Forest, KNN, Linear Discriminant Analysis and Multilayer Perceptron. The implementation of a machine learning model is done in python using jupyter notebook. This model is deployed in cloud using IBM cloud services. This application will be useful to doctors for making decision whether a patient is benign or malignant.