Publication Date
Spring 2025
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Saptarshi Sengupta
Second Advisor
William Andreopoulos
Third Advisor
Vijaya Bashyam
Keywords
Generative AI, Retrieval Augmented Generation, LLM as a Judge
Abstract
Healthcare is one of the most important fields that benefits from advancements in Artificial Intelligence (AI). From classic models like linear regression to cuttingedge transformers, AI is applied across various healthcare subdomains, such as drug discovery, predictive analytics, and personalized medicine, to name a few. These techniques enable medical practitioners to make more informed decisions, significantly improving both the speed and accuracy of diagnoses and treatments. Machine learning has played a transformative role in oncology, especially in areas like early detection, diagnosis, treatment planning, and patient monitoring, by analyzing medical images, clinical information, genomic data, sensor information. Our research aims to develop a solution for predicting cancer patient survivability using an emerging approach in AI, called Generative AI. Specifically, we will leverage Large Language Models, a powerful subset of Generative AI, including other facets of AI, namely Natural Language Processing (NLP), Machine Learning (ML), and Rule based systems. We also look into how Retrieval Augmented Generation can be used to derive insights from larger datasets, followed by evaluation of the responses given by LLMs, using the LLM as a Judge approach. This research enables us to capture insights from unstructured data that can go unnoticed in traditional machine learning pipelines. By integrating generative models with retrieval mechanisms, our goal is to deliver more context-aware and clinically relevant insights. Additionally, the evaluation process involves comparing multiple responses and evaluating accuracy across different models.
Recommended Citation
Vaidyanathan, Jyothi, "Retrieval-Augmented Generation for Survival Analysis in Cancers: Methods and Evaluation on the Surveillance, Epidemiology, and End Results Database" (2025). Master's Projects. 1522.
DOI: https://doi.org/10.31979/etd.7mk8-5kya
https://scholarworks.sjsu.edu/etd_projects/1522
