Date of Award
Spring 5-2020
Degree Type
Thesis
Degree Name
M.S.
Degree Program
Computer Science
Department
Computer Science
Major Professor
Dr. Md Tamjidul Hoque
Second Advisor
Dr. Chindo Hicks
Third Advisor
Dr. Minhaz Zibran
Fourth Advisor
Dr. Christopher Summa
Abstract
Prostate cancer (PCa) is the second most common cancer in men in the US. Many Prostate cancers are Indolent and don’t result in cancer mortality, even without treatment. However, a significant proportion of patients with Prostate cancer have aggressive tumors that progress rapidly to metastatic disease and are often dangerous. Currently, treatment decisions for PCa patients are guided by various stratification algorithms. Among these parameters, the most important predictor of PCa mortality is the Gleason Grade (ranges from 6 to 10). Although current risk stratification tools are moderately effective, limitation remains in their ability to distinguish truly Indolent from aggressive and potentially lethal disease. Here we propose the use of Machine Learning (ML) for the classification of PC patients as having either indolent or aggressive using transcriptome data. We hypothesize that genomic alterations could lead to measurable changes distinguishing indolent from aggressive tumors. We also trained a Stacking-based model with a different set of combinations of classifiers. The highest overall accuracy of our stacking model (all samples with Gleason Grade: 6, 7, 8, 9, and 10) is 95.758% and (samples with Gleason Grade: 6, 8, 9, and 10) is 97.19%.
Recommended Citation
Mamidi, Yashwanth Karthik Kumar, "Classification of Prostate Cancer Patients into Indolent and Aggressive Using Machine Learning" (2020). University of New Orleans Theses and Dissertations. 2757.
https://scholarworks.uno.edu/td/2757
Rights
The University of New Orleans and its agents retain the non-exclusive license to archive and make accessible this dissertation or thesis in whole or in part in all forms of media, now or hereafter known. The author retains all other ownership rights to the copyright of the thesis or dissertation.