Graduation Year

2025

Document Type

Dissertation

Degree

Ph.D.

Degree Name

Doctor of Philosophy (Ph.D.)

Degree Granting Department

Electrical Engineering

Major Professor

Ghulam Rasool, Ph.D.

Co-Major Professor

Yasin Yilmaz, Ph.D.

Committee Member

Mia Naeini, Ph.D.

Committee Member

Nathan Parker, Ph.D.

Committee Member

Ravi Prakash Ramachandran, Ph.D.

Keywords

Cancer Cachexia, Deep Learning, Large Language Models, Machine Learning, Robustness, Uncertainty Quantification

Abstract

Cancer cachexia is a metabolic syndrome characterized by substantial skeletal muscle loss, impacting cancer patients' survival and quality of life. Despite its clinical significance, early detection remains a challenge due to the lack of standardized diagnostic criteria and the reliance on indirect markers. This work presents an AI-driven approach to enhance cachexia detection and monitoring by integrating multiple deep learning methodologies. We explore transformer architectures for time-series analysis to model sequential medical data, enabling disease prediction and progression modeling. To ensure robust and reliable decision-making in clinical settings, we explore Bayesian deep neural networks for uncertainty estimation. Additionally, we introduce SMAART-AI, an automated deep learning pipeline for skeletal muscle segmentation from computed tomography scans, facilitating automated and reliable muscle assessment. Extending on this framework, we develop a multimodal AI model that integrates clinical data, radiology images, lab reports, and clinical notes to improve cachexia prediction through informed decision making. By synthesizing techniques from different AI subfields, this work establishes an interdisciplinary framework for enhancing cancer cachexia tracking and diagnostic accuracy, enabling early intervention and personalized treatment plans.

Download

Share

COinS