Document Type
Thesis
Date of Award
3-2025
School/College
College of Science, Engineering, and Technology (COSET)
Degree Name
MS in Computer Science
Committee Chairperson
Dr. M. Farrukh Khan
Committee Member 1
Dr. Sleem Aladdin
Committee Member 2
Dr. Khaled Kamel
Committee Member 4
Dr. Momoh A. Yakubu
Abstract
This study explores the integration of eXplainable Artificial Intelligence (XAI) techniques in genomic medicine to improve breast cancer prognosis and treatment decision-making. Using data from The Cancer Genome Atlas (TCGA), the research establishes a baseline through traditional machine learning (ML) models, including Random Forest (RF), Support Vector Classifier (SVC), Decision Tree, Naïve Bayes, K-Nearest Neighbors (KNN), and XGBoost. These models are evaluated for their predictive performance in assessing patient outcomes based on genetic variations. TCGA is a comprehensive public database that provides multidimensional genomic and clinical data for various cancer types, including breast cancer. It offers detailed molecular characterizations, such as mutations, gene expression profiles, and copy number variations, making it a valuable resource for developing predictive models in cancer research. To address the black-box nature of traditional ML models, the study incorporates XAI methods, specifically SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), to enhance model interpretability. These techniques provide insight into how specific genetic features contribute to cancer progression and treatment responses. Additionally, the Synthetic Minority Over-sampling Technique (SMOTE) is applied to handle class imbalance, ensuring more robust and equitable model predictions. By leveraging XAI, this research aims to bridge the gap between complex genomic data and clinical applicability, offering transparent, interpretable insights that enhance personalized treatment strategies. The findings contribute to the ongoing effort to integrate AI-driven models into precision oncology, fostering trust among healthcare professionals and enabling more informed, data-driven treatment decisions for breast cancer patients.
Copyright
Copyright © for this work is retained by the author. Any documents and information presented are protected by copyright under US Copyright laws and are the property of the author. All Rights Reserved. For permission to use this content please contact the author or the Graduate School at Texas Southern University ([email protected]).
Recommended Citation
Marith, Tooba Maryam, "Explainable AI(XAI) In Genomic Medicine: Interpreting The Impact Of Genetic Variants On Breast Cancer Prognosis" (2025). Theses (2016-Present). 91.
https://digitalscholarship.tsu.edu/theses/91