Machine Learning Applications in Predicting Breast Cancer Survival Using Gene Information

Kasaraghatta Thimmaraya Gowda, Sharath (2021) Machine Learning Applications in Predicting Breast Cancer Survival Using Gene Information. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (984kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Gene Expression is a computation concept that replicates human thinking and logic by distributing the information at various levels of precision. Implementing Gene and therapies in the prediction of breast cancer survivability using gene expression through designing of a system enhances the machine learning performance. The suggested method uses data granulation to train and test the classifier at various hierarchies. There are two aspects to the project presented, one where breast cancer histopathological image dataset is used to predict breast cancer with the image dataset then the second dataset, also the main objective of the project, to use the METABRIC breast cancer gene dataset to predict the survival of breast cancer patients using the gene information. To appraise the performance of the planned method, a PCA(Dimensionality Reduction on Gene) system is used based on the preferred technique such as Multilayer Perceptron, K Nearest Neighbours , Support Vector Classifier, and Tensorflow Boosted Estimator’s Method. Two different health datasets are applied in the comparative analysis to evaluate the performance of the preferred approach to various classifiers. Multiple Instance learning is the novel approach carried out on Breast cancer prediction using Histopathological images, while Tensorflow Boosted estimators is the novel approach performed on Breast cancer Survivability. Results show that the proposed method improves the performance of the classification and generates improved level of prediction accuracy than the Convolutional Neural Network and Artificial Neural Networks. The accuracy of Attention based multiple instance learning for breast cancer prediction was about 91.04% while the accuracy of survivability of breast cancer patients using gene information is 100%.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software R Medicine > R Medicine (General) H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	06 Dec 2021 10:46
Last Modified:	06 Dec 2021 10:46
URI:	https://norma.ncirl.ie/id/eprint/5173

Actions (login required)

View Item